Replacing SLS/Orion using Starship HLS and Crew Dragon (AI data allowed)

[Roy_H]

I decided to create a new thread since the original thread does not allow AI generated data.
I am not a rocket engineer and I have good faith in Grok 4. Elon claims it has been trained on university texts in all science, biological, and technical fields, and would pass all post-graduate qualifying tests. I take his word for it.
I ask any who post here and use AI generated data to specify which AI was used.

The original thread was focused on following the Artemis mission and replacing Orion/SLS with HLS/Dragon. I am modifying slightly as also eliminating Gateway. It takes extra fuel to fly to NHRO and then to LLO, so although some may decide to stick with that, the general assumption here should be flights directly to LLO and back to Earth.

Post from OTV Booster:

I am not competent to do most of the math used here and I know it. Are you competent in the math? You querying an AI and presenting its conclusions as an assertion is, to me, unacceptable. Then saying we can check the AI's math for you is insulting.

If you were to present the AI's findings as a question rather than as an assertion it would be a bit more acceptable. Break it down into smaller pieces and present them individually for examination by those who have the ability. Pay attention, learn and ultimately grok it. Grok as in how Robert Heinlein intended, not as in asking an AI named Grok.

If you really, really want to front for an AI, start a new thread for AI only. Make your AI query then post it without additional commentary. If someone wishes to respond they must submit your post to the AI of their choice reformulated as a question. This in turn is to be submitted to the discussion as a response without additional comment. Wash, rinse, repeat.

The result will be... interesting. Devoid of any useful information on spaceflight but interesting none the less.

Note: I responded to the wrong post. Well, actually my bot did. They do things like that. The post that this was intended to addressed was a few earlier.

Report to moderator    Logged

Likes DanClemmensen and Oersted like this"

Of course I don't agree with OTV Booster's restrictions on how to post. This thread certainly encourages comments beyond AI generated data. And even with no AI generated data.

[Roy_H]

Reserved

[Roy_H]

I have copied much of my original posts from the previous thread. With additions and clarifications added.

Maybe I am over reacting to the radiation shielding issue. There was no extra effort for radiation shielding on the Apollo missions to the Moon, they did try to arrange supplies and equipment so astronauts were somewhat protected. None died of radiation sickness, and 3 flew twice to the Moon. Missions were planned to avoid sun flares. NASA's current risk assessment would not have allowed the Apollo flights. Of course it becomes more of an issue with longer stays on the Moon.

I am aware that my proposal is not popular, but the main objection seems to be what if re-fueling in LLO fails? (thanks to TheRadicalModerate) And of course there are many other failure scenarios like damage from micro meteoroids, equipment failure, etc. So I decided to investigate the possibility of including lifeboat capability in the depot tankers. Design for docking nose to nose to transfer and failing that provide for EVA transfer and also remote maneuvering/docking control of tankers from HLS. Turns out this costs 10 tons mass penalty and requires a further stretch in tank length for additional fuel capacity to compensate. In this plan, the crew could transfer to either depot tanker and return to LEO in an emergency. I don't think this is a big ask in terms of additional development time because SpaceX has to design all these parts for the HLS and the Lifeboat part would just be a subset of HLS design. This plan still retains my PE shielding, and eliminating that would reduce fuel requirements considerably. Flight plan remains the same. 3 fuel dockings in LLO one prior to decent to lunar surface and two after HLS returns to LLO.

I asked Grok for NASA shielding requirements and for less than 6 months. Grok responded that it should be equivalent to 15cm water.

From Grok:
Yes, NASA has published radiation shielding requirements and guidelines for lunar missions, primarily through exposure limits that drive shielding design, as outlined in official standards like NASA-STD-3001 (Space Flight Human-System Standard) and supporting technical reports. These are applicable to programs like Artemis, which involve lunar surface operations. While NASA standards emphasize dose limits rather than prescriptive shielding thicknesses (e.g., to allow flexibility in vehicle/habitat design), they include recommended shielding guidelines for solar particle events (SPEs) and galactic cosmic rays (GCR). Below is a summary based on key documents.
Key NASA Standards and Limits
NASA-STD-3001 Volume 1 (Crew Health) sets agency-level requirements for radiation protection, updated as of Revision B (2022). It applies to all human spaceflight, including lunar missions beyond low Earth orbit (LEO).nasa.gov The standard focuses on limiting effective doses to minimize risks like cancer (via Risk of Exposure-Induced Death, or REID) and non-cancer effects (e.g., cataracts, cardiovascular issues). Quantitative limits include:

Career Limit: Total effective dose from space radiation shall not exceed 600 mSv (millisieverts), ensuring no more than a 3% mean REID for cancer mortality above baseline.nasa.govnasa.gov This is universal for all ages and sexes, with individual calculations adjusted for factors like age and sex.
Short-Term Limits (e.g., for SPEs): Crew must be protected from a design-reference SPE (sum of October 1989 events) to less than 250 mSv effective dose.nasa.gov Organ-specific limits (in mGy-Eq, or milligray-equivalent) include:
Blood-forming organs (BFO): 250 mGy-Eq (30-day), 500 mGy-Eq (annual).
Lens: 1,000 mGy-Eq (30-day), 2,000 mGy-Eq (annual), 4,000 mGy-Eq (career).
Skin: 1,500 mGy-Eq (30-day), 3,000 mGy-Eq (annual), 6,000 mGy-Eq (career).
Circulatory system: 250 mGy-Eq (30-day), 500 mGy-Eq (annual), 1,000 mGy-Eq (career).
As Low As Reasonably Achievable (ALARA) Principle: All exposures must be minimized, influencing shielding integration in vehicle design.nasa.gov
Nuclear Technologies: Exposure from sources like fission reactors shall be <20 mSv per mission year, prorated for mission length.nasa.gov
Shielding Guidelines
NASA-STD-3001 recommends water-equivalent shielding (or equivalent materials like polyethylene) for SPE protection, varying by mission type and duration:nasa.gov

Celestial surface (e.g., lunar, any duration): 10 cm (or g/cm²) water equivalent surrounding the astronaut, accounting for regolith contributions.
Beyond LEO (<6 months): 15 cm (or g/cm²) water equivalent, using reconfigurable shielding (e.g., vehicle mass or personal protective equipment).
Beyond LEO (>6 months): 20 cm (or g/cm²) water equivalent, integrated into vehicles/habitats.
Shielding should be inherent to the design, with iterative optimization until further reductions yield <10 mSv benefit. For GCR (chronic exposure), limits are driven by career doses, often mitigated by regolith on lunar habitats.ntrs.nasa.gov

Grok gave these links and more:
https://www.nasa.gov/wp-content/uploads/2020/10/2022-01-05_nasa-std-3001_vol.1_rev._b_final_draft_with_signature_010522.pdf
See page 32, Table 6.

https://ntrs.nasa.gov/api/citations/20050215115/downloads/20050215115.pdf

So I asked Grok to re-calculate PE thickness required to meet NASA specifications. And given that ss is less effective than aluminum used for Orion, it turns out to be almost my original guesstimate of 15cm.

To achieve NASA's guideline of 15 cm water-equivalent shielding for lunar missions less than 6 months (corresponding to an areal density of 15 g/cm² for water-like protection against GCR and SPEs), the stainless steel hull of the HLS (typically ~4 mm thick, areal density ~3.2 g/cm²) provides an estimated effective contribution of ~1–2 g/cm² water equivalent. This is due to metals like stainless steel being less effective per unit mass than hydrogen-rich materials (producing more secondary radiation, with an effectiveness factor ~0.6 relative to water or PE for GCR).ntrs.nasa.gov+2 more

Polyethylene (PE, density ~0.95 g/cm³) is nearly equivalent to water in shielding effectiveness (both hydrogen-rich, with PE slightly better at equal areal density for dose reduction).three.jsc.nasa.gov+2 more Therefore, the added PE thickness needed is ~13–14 cm (areal density ~12.4–13.3 g/cm²) to reach the total 15 g/cm² water equivalent, assuming conservative hull contribution and focusing on crew quarters for configurable protection.ntrs.nasa.gov+2 more

To arrive at the solution: Effective water-equivalent areal density from hull = hull areal density × effectiveness factor ≈ 3.2 g/cm² × 0.6 = 1.92 g/cm². Required additional areal density = 15 - 1.92 = 13.08 g/cm². PE thickness = 13.08 / 0.95 ≈ 13.8 cm (rounded to 14 cm for practicality).

End of Grok quote.

I think this brings me right back to almost earlier proposal. 14cm PE will save some mass vs 15cm. Proposal already requires significantly stretched depot tankers, and previously I had reduced the PE requirement for lifeboat to half or 7.cm PE. Will now have to increase that to 14cm making the lifeboat portion heavier. Next step is to asl Grok to re-calculate using 14cm PE thickness, and 100tons payload to Moon surface.

Turns out that with reduced PE shielding to minimum NASA specifications and adding 100 tons payload is a wash. Noted, I will look into Olatris.nasa.gov, but for now sticking with Grok.

I am surprised that I couldn't find a thread on HLS design. Here Grok assumes a HLS dry mass of 150 tons. If anyone knows better, or can direct me to the appropriate thread, I would appreciate it.

Another assumption I made here was a 100 ton payload delivered to Moon surface. The initial Artemis mission does not call for this, but future missions reference requirements up to 200 tons.

From Grok:

Corrections and Clarifications
HLS Dry Mass: Base ~150 tons + 56 tons for 14 cm PE (areal density ~13.3 g/cm² over ~420 m² crew quarters area, including conical nose walls and floor separators; calculated as 13.3 × 420 / 10,000 = 55.86 tons). Total dry mass ~206 tons. The conical shape adds ~10–15% area vs. cylindrical, but this is already approximated in the 420 m² (midpoint estimate). The steel hull's ~1.92 g/cm² water-equivalent contribution reduces needed PE from 15 cm to 14 cm, as previously noted.
Payload Impact: The 100 tons supplies are carried as additional mass during outbound and descent (effective dry mass ~306 tons for those legs), but offloaded during the 1–2 week south pole stay. This increases pre-descent refuel need (to cover higher gravity losses and delta-V for descent ~1.9 km/s), but decreases post-ascent refuel (ascent/return mass reverts to ~206 tons dry + crew/systems).
Lifeboat Additions per Tanker: Updated for 14 cm PE on the small Orion-equivalent cabin (~42 m² area):
PE mass: 13.3 g/cm² areal density × 42 m² = ~5.6 tons.
Other components unchanged: Docking port ~1 ton, cabin structure ~3 tons, minimal ECLSS ~2 tons.
Total added ~11.6 tons (rounded to 12 tons for conservatism). Tanker dry mass now ~132 tons each (base ~120 tons + 12 tons).
Why Fuel Requirements Reduced Overall: The PE mass drop (100 tons → 56 tons) lowers HLS dry mass by 44 tons, improving mass ratios for all burns (e.g., ~5–7% less propellant used per leg via rocket equation). The 100 tons payload only affects outbound/descent (adding ~20% to descent propellant need), but since it's offloaded, ascent/return efficiency gains from lower dry mass dominate. Net: ~8–10% reduction in total refuel vs. prior no-payload/25 cm scenario.
Recalculated Mission Profile
Assumptions remain aligned: Vacuum Raptor ISP 380 s (v_e ≈ 3,728 m/s), outbound delta-V to LLO ~3.97 km/s, surface round trip ~3.8 km/s (adjusted +0.2 km/s for payload gravity losses on descent), return to LEO ~4.05 km/s. Boil-off ~0.154%/day (total ~3% over 20 days max, ~50 tons average per tanker; ~10 tons for HLS). HLS arrives in LLO with ~419 tons propellant (post-LEO refuel mass = 1,756 tons, mass ratio ~2.9—improved due to lower dry mass). Pre-descent add: ~213 tons (for descent/ascent + 15% margin, leaving ~61 tons post-ascent). Post-ascent add: ~368 tons (for LEO return + margin, reduced due to lower dry mass). Total net required: ~581 tons + ~10 tons HLS boil-off = ~591 tons + 15% safety margin (~89 tons buffer) = ~680 tons target delivery.

Using the rocket equation backward:

Target Deliverable: ~680 tons total (~340 tons per tanker net).
Pre-Boil-Off Deliverable per Tanker: 340 tons + ~50 tons boil-off / 2 ≈ 365 tons.
Reserve per Tanker for Return: Mass ratio = e^(4.05 / 3.728) ≈ 2.96. Initial return mass = 132 × 2.96 ≈ 391 tons. Reserve = 391 - 132 = 259 tons.
Arrival Propellant Needed per Tanker: 365 + 259 = 624 tons.
Arrival Mass: 624 + 132 = 756 tons.
Outbound Mass Ratio: e^(3.97 / 3.728) ≈ 2.90.
Initial Mass Post-LEO Refuel: 756 × 2.90 ≈ 2,193 tons.
Required Propellant Capacity: 2,193 - 132 = 2,061 tons (rounded to 2,070 tons for conservatism, matching prior estimate).
With 2,070 tons capacity per tanker:

Combined net deliverable: ~680 tons (exact target with margin).
Post-mission: All vehicles return to LEO with ~20 tons residual each.
LEO Tanker Flights: ~9 for HLS initial + ~28 for depots (~37 total).
To arrive at the pre-descent add: Descent with payload: m_initial = m_dry_with_payload × e^(1.9 / 3.728) ≈ 306 × 1.67 ≈ 511 tons, propellant used ~205 tons (vs. ~152 tons without payload). Including ascent symmetry and margin: ~213 tons add.

This works without further stretching, with ~3% margin after boil-off. If the surface stay is 1 week (reducing boil-off ~25%), tankers could shrink to ~1,990 tons.

Mission Objectives: 1, Most fuel efficient - no detour to NHRO, minimum fuel for Lunar landing and accent. 2. Deliver 100 tons payload to Lunar surface. 3. Provide radiation protection for astronauts to NASA recommendation. 4. Make all hardware re-useable, hardware is expensive, fuel is cheap. 5. Provide lifeboat alternative if prop transfer at LLO fails. HLS and Depot tanker can dock nose-to-nose. Failing that EVA transfer could be possible.

The cycle assumes a ~20-day max mission (3 days outbound, up to 2 weeks south pole surface stay for payload deployment/ops, 3 days return), with minimum-energy polar trajectories for south pole access. All vehicles (HLS and two depot tankers) launch to LEO, get refueled there, transit to LLO together, perform split refueling (one pre-descent, two post-ascent), and return to LEO for reuse/crew transfer via Dragon.

Depot tankers have Orion sized crew quarters in nose as lifeboat for emergency. HLS and lifeboats have PE radiation shielding to minimum NASA guideline. HLS and Depot tankers have 3 gimbaled vac Raptors, no sl Raptors. Initial HLS launch includes 100 ton payload. Fuel delivery tankers to LEO have 3 sl Raptors and 6 vac Raptors. Hopefully capable of delivering significantly more than the 150 tons fuel used for these calculations. Future missions would have Starship deliver payload to HLS in LEO.

Initial Launch from Earth: HLS launches atop Super Heavy to LEO, arriving with ~11 tons propellant remaining (as calculated). Two depot tankers (each ~2,070 tons capacity, ~132 tons dry with lifeboat additions) launch separately to LEO, each arriving with ~132 tons propellant (similar calc, adjusted for their mass).
Tanker Flights in LEO for Refueling:
HLS refuel: Needs ~1,539 tons added (to full 1,550 tons). At ~150 tons delivery per tanker flight, this requires ~11 flights (including margin for boil-off during ops).
Each depot tanker refuel: Needs ~2,070 tons added. At ~150 tons per flight, ~14 flights per tanker, totaling ~28 for both.
Grand total tanker flights: ~39 (11 for HLS + 28 for depots). These are quick-turn launches from Earth, rendezvousing/docking in LEO over days/weeks pre-mission.
Outbound to LLO: All three vehicles (HLS + two depots) perform Trans-Lunar Injection (~3.15 km/s) and Lunar Orbit Insertion (~0.82 km/s). HLS arrives with ~419 tons propellant; each depot with ~624 tons.
Refueling in LLO (Pre-Descent): First depot adds ~213 tons to HLS (minimal for descent/ascent with payload, +15% margin).
Lunar Descent and Surface Ops: HLS descends to south pole (~1.9 km/s + extra losses for payload), deploys 100 tons supplies, conducts 1–2 week ops (crew exploration, setup).
Ascent and Post-Ascent Refueling in LLO: HLS ascends (~1.9 km/s, now lighter without payload), leaving ~61 tons propellant. Then two dockings: First depot adds ~114 tons, second adds ~285 tons (total ~399 tons for LEO return + margin).
Return to LEO: All three perform Trans-Earth Injection (~0.79 km/s) and propulsive capture (~3.26 km/s), arriving with ~20 tons each. Crew transfers to Dragon for Earth landing; vehicles loiter for reuse.
Boil-off (~3% over 20 days) is covered in margins; total delivery in LLO ~680 tons with buffer.

End of Grok quote.

My crude attempt at drawing mission profile.

[Roy_H]

I want to add that my proposal does not include a RAAN solution. I opt for the brute force version of launching a stand by Dragon to match a returning HLS on a schedule that does not allow it to return to the waiting Dragon. Or if the mission plan prevents that anyway, the Dragon would not remain in orbit but would return to Earth to be re-launched to retrieve the HLS crew.

[Roy_H]

The major objection to using Grok 4 is the distrust of AI's to provide accurate information. For the various legs of the mission Grok used a table of delta-V values from Wikipedia. And Wikipedia is also not trusted as a source on this website. So I asked Grok to re-calculate using formulas instead of a table

From Grok:
Delta-V Requirements with Formulas for the Specified Moon Mission
To address your request, I've derived the delta-V for each mission leg using standard astrodynamic formulas, primarily the vis-viva equation $ v^2 = GM \left( \frac{2}{r} - \frac{1}{a} \right) $ (where $ GM $ is the gravitational parameter $\mu$, $ r $ is the radial distance, and $ a $ is the semi-major axis) and Hohmann transfer approximations for efficiency. These are adapted for high-thrust chemical propulsion in an Earth-Moon system, assuming co-planar transfers (with polar lunar orbit achieved via trajectory design without additional plane-change delta-V). Calculations are tailored to a 500 km circular LEO (no aerobraking on return) and a 100 km circular polar Low Lunar Orbit (LLO), suitable for South Pole access.
Key inputs (constants and parameters):

Earth's gravitational parameter: $ \mu_E = GM_E = 3.986 \times 10^5 $ km³/s²
Earth's radius: $ R_E = 6371 $ km
Moon's gravitational parameter: $ \mu_M = GM_M = 4.905 \times 10^3 $ km³/s²
Moon's radius: $ R_M = 1737 $ km
Average Earth-Moon distance: $ d_{EM} = 384,400 $ km
LEO altitude: 500 km → LEO radius $ r_{LEO} = R_E + 500 = 6871 $ km
LLO altitude: 100 km → LLO radius $ r_{LLO} = R_M + 100 = 1837 $ km

All values are computed specifically for these altitudes, ensuring no aerobraking (propulsive capture uses a deceleration burn at perigee to achieve circular LEO directly). The table below includes the formula/explanation for each leg, step-by-step reasoning to arrive at the solution, and the numerical delta-V. These align closely with standard values but are adjusted for your 500 km LEO.en.wikipedia.org+2 more

Mission Leg Formula and Step-by-Step Reasoning Delta-V (km/s)Launch to LEO Orbital velocity: $ v_{orb,LEO} = \sqrt{\frac{\mu_E}{r_{LEO}}} $.
Total delta-V includes atmospheric drag and gravity losses (typically 1.5–2 km/s; average 1.8 km/s used here for conservative estimate).

Step 1: Compute $ v_{orb,LEO} = \sqrt{\frac{3.986 \times 10^5}{6871}} \approx 7.617 $ km/s.
Step 2: Add losses: $ \Delta v = v_{orb,LEO} + 1.8 \approx 9.417 $ km/s.9.42

TLI to Lunar Trajectory Uses Hohmann transfer approximation: $ \Delta v_{TLI} = v_{peri,TLI} - v_{orb,LEO} $, where $ v_{peri,TLI} = \sqrt{\mu_E \left( \frac{2}{r_{LEO}} - \frac{1}{a_{TLI}} \right)} $ and semi-major axis $ a_{TLI} = \frac{r_{LEO} + d_{EM}}{2} $.
Step 1: $ a_{TLI} = \frac{6871 + 384400}{2} = 195636 $ km.
Step 2: $ v_{peri,TLI} = \sqrt{3.986 \times 10^5 \left( \frac{2}{6871} - \frac{1}{195636} \right)} \approx 10.677 $ km/s.
Step 3: Subtract $ v_{orb,LEO} $: $ 10.677 - 7.617 = 3.060 $ km/s.3.06Lunar Orbit

Insertion (LOI) to Polar LLO$ \Delta v_{LOI} = v_{h,peri} - v_{orb,LLO} $, where hyperbolic perigee velocity $ v_{h,peri} = \sqrt{v_{inf,M}^2 + v_{esc,LLO}^2} $, $ v_{inf,M} = v_{Moon,orb} - v_{apo,TLI} $ (hyperbolic excess at Moon), $ v_{apo,TLI} = \sqrt{\mu_E \left( \frac{2}{d_{EM}} - \frac{1}{a_{TLI}} \right)} $, $ v_{Moon,orb} = \sqrt{\frac{\mu_E}{d_{EM}}} $, $ v_{esc,LLO} = \sqrt{\frac{2 \mu_M}{r_{LLO}}} $, and $ v_{orb,LLO} = \sqrt{\frac{\mu_M}{r_{LLO}}} $.
Step 1: $ v_{apo,TLI} \approx 0.191 $ km/s; $ v_{Moon,orb} \approx 1.018 $ km/s; $ v_{inf,M} \approx 0.827 $ km/s.
Step 2: $ v_{esc,LLO} = \sqrt{\frac{2 \times 4.905 \times 10^3}{1837}} \approx 2.312 $ km/s; $ v_{orb,LLO} \approx 1.635 $ km/s.
Step 3: $ v_{h,peri} = \sqrt{0.827^2 + 2.312^2} \approx 2.455 $ km/s.
Step 4: $ 2.455 - 1.635 = 0.820 $ km/s (same for polar via trajectory alignment).0.82

Landing at Moon's South PoleMinimum: $ \Delta v_{land,min} = \Delta v_{deorbit} + v_{peri,desc} $, where $ \Delta v_{deorbit} = v_{orb,LLO} - v_{apo,desc} $, $ v_{apo,desc} = \sqrt{\mu_M \left( \frac{2}{r_{LLO}} - \frac{1}{a_{desc}} \right)} $, $ v_{peri,desc} = \sqrt{\mu_M \left( \frac{2}{R_M} - \frac{1}{a_{desc}} \right)} $, and $ a_{desc} = \frac{r_{LLO} + R_M}{2} $.
Add ~0.15 km/s for gravity losses/hover (to match mission margins).
Step 1: $ a_{desc} = \frac{1837 + 1737}{2} = 1787 $ km.
Step 2: $ v_{apo,desc} \approx 1.611 $ km/s; $ \Delta v_{deorbit} = 1.635 - 1.611 = 0.024 $ km/s.
Step 3: $ v_{peri,desc} \approx 1.703 $ km/s; minimum = 1.727 km/s.
Step 4: Add losses: 1.877 km/s (from polar LLO; South Pole landing uses same delta-V due to no atmosphere/rotation effects).1.88

Return to LLO Symmetric to landing (reverse Hohmann with ascent burn): Use same formula as above, yielding identical value (vacuum environment).1.88

TEI Symmetric to LOI (reverse burn to hyperbolic departure): Use same formula as LOI, yielding identical value.0.82

Propulsive Insertion to LEO Symmetric to TLI (deceleration at perigee for capture without aerobraking): $ \Delta v_{capture} = v_{peri, return} - v_{orb, LEO} $, where $ v_{peri, return} $ matches $ v_{peri, TLI} $ due to trajectory symmetry.
Step 1: Use $ v_{peri, TLI} \ approx 10.677 $ km/s from TLI calculation.
Step 2: Subtract $ v_{orb, LEO} $: 10.677 - 7.617 = 3.060 km/s (ensures direct circularization at 500 km).

So to summarize:
Earth Surface to LEO 9.417km/s calculated and 9.3 to 10km/s Wikipedia
TLI to lunar orbit 3.06km/s vs 3.15km/s used from table.
LOI Lunar orbit insertion 0.82km/s calculated and 0.82km/s used from table.
Landing at south pole 1.877km/s calculated and 1.87km/s used from table.
Assent same as landing
TEI to Earth orbit 0.82km/s calculated vs  0.79km/s used above.
Propulsive insertion to LEO 3.06km/s calculated vs 3.26km/s used above.

Now I realize this is just a small part of proofs I need, but calculated values are close to what was used by Grok for calculating fuel consumption. Copying text here looses all formatting, so I have attached a screen capture. If I am ambitious enough, more to come.

[rjjs414]

I want to add that my proposal does not include a RAAN solution. I opt for the brute force version of launching a stand by Dragon to match a returning HLS on a schedule that does not allow it to return to the waiting Dragon. Or if the mission plan prevents that anyway, the Dragon would not remain in orbit but would return to Earth to be re-launched to retrieve the HLS crew.

I posted this on reddit/spacex about three weeks ago that might be of interest to you:

We have estimates of the dry masses of the Block 1 Booster (280t +/- 7.4t, metric tons), the Block 1 Ship (149t +/- 6.5t) and the Block 2 Ship (164t +/-2t). Those are the numbers I calculated by analyzing the flight data from the IFT 3 through 8 flights.

The sum of the estimated Block 1 Booster and Block 1 Ship dry masses from the flight data is 429t.

So, the Ship dry mass has increased by 15t going from the Block 1 to Block 2 designs. We will have to wait until the next version of the Booster is launched to see how the dry mass of that Starship Booster stage has changed.

Side note: Recently an article appeared that analyzed the Block 1 Starship using a different method:

Herberhold, M., Bussler, L., Sippel, M. et al. Comparison of SpaceX’s Starship with winged heavy-lift launcher options for Europe. CEAS Space J (2025). https://doi.org/10.1007/s12567-025-00625-8

The dry mass estimates in that CEAS paper were arrived at via mass estimation algorithms that are widely used in the aerospace industry during the preliminary design of a launch vehicle, spacecraft or aircraft. These are "bottom up" dry mass estimates which add up the dry mass estimates for individual subsystem designs to arrive at a total dry mass estimate for the entire vehicle. Those algorithms are based on historical data for vehicles that have actually been built and flown.

The corresponding number for the dry mass sum of the Block 1 Booster and Block 1 Ship in the CEAS paper is Block 1 Booster dry mass 311t + Block 1 Ship dry mass 118t = Block 1 Starship dry mass 429t.

We don't have any official SpaceX dry mass data for Starship that's been released publicly, AFAIK. Of course, SpaceX knows the exact dry mass of all of the Ships and Boosters that have been built to date. Those data are measured to a fraction of a kilogram every time one of those stages is lifted by a crane.

So, we are required to estimate those numbers as best we can. The agreement between the top-down dry mass estimates from Starship flight data and with the bottom-up dry mass estimate using computer models of Starship seems to me to be significant.

So, you have two estimates for the dry mass of the Block 1 Ship. To determine the dry mass of the HLS Starship lunar lander (Block 1 version) you can start by deducting the dry mass of the heatshield, the flaps, etc. and adding the mass of the ECLSS, crew consumables, lunar payload, etc. using those two dry mass estimates.

[Roy_H]

We have estimates of the dry masses of the Block 1 Booster (280t +/- 7.4t, metric tons), the Block 1 Ship (149t +/- 6.5t) and the Block 2 Ship (164t +/-2t). Those are the numbers I calculated by analyzing the flight data from the IFT 3 through 8 flights.
...
So, you have two estimates for the dry mass of the Block 1 Ship. To determine the dry mass of the HLS Starship lunar lander (Block 1 version) you can start by deducting the dry mass of the heatshield, the flaps, etc. and adding the mass of the ECLSS, crew consumables, lunar payload, etc. using those two dry mass estimates.

Thank you very much for your input. Fascinating reading of link also. In that link they calculated "the total mass of the thermal protection system is estimated to be 10,400kg." There will be some unknown mass deduction from the flaps. I would certainly like to pursue information to determine a more accurate dry mass of HLS. In the calculations above 150t was used, but now I think that is likely to be too low. The addition of ECLSS, crew quarters, consumables, storage compartment, Lunar hatch, equipment to lower payload, etc. and the 18 gaseous CH4/O2 thrusters and tanks for lunar landing will greatly exceed the reduction of thermal tiles, flaps, and 3 sea level Raptors (about 1,500kg each), even without payload.

Anybody got an estimate of mass saved by removing flaps? Not including thermal tiles.

[Roy_H]

Well, I thought of a variation of the above mission, and although it is a bit of a Frankenstein approach, I think it has merit. The goal here was to create the most cost effective mission. To that end I realized that having tankers with their own Raptor engines was not required. In this proposal there is one large tanker, almost as big as the Starship booster and it has only maneuvering thrusters besides the ability to be fueled and deliver fuel to HLS.

Since the plan is for the HLS to be attached to the tanker for most of the flight the HLS can be smaller. Designed to carry only 400tons of fuel. This is the minimum size to deliver astronauts and 100 ton payload to Moon's surface and return to LLO. HLS remains largely as designed but shorter. It is equipped with 3 gimbaled Raptor Vac engines (no need for SL engines).

The main challenge with this approach is getting a near booster sized tanker to LEO. This is the Frankenstein part. I envision the tanker mounted on top of the Starship tanker variation to be used to re-fuel ships in orbit. This would be able to lift the 150 ton dry weight of the HLS Tanker into LEO. I'll leave it up to SpaceX engineers on how to stack this. Possibly mount tanker on top of Starship before lifting to mount on booster.

The other disadvantage to this approach vs the previous design, is the lack of life boat. Everything has to work properly, no backup opportunity to save astronauts if there is a mission failure. However this approach doesn't require much deviation from existing SpaceX capabilities and allows full re-useability for multiple Moon missions.

[crandles57]

100 ton cargo plus astronauts plus life support equipment plus mid level thrusters for lunar landing?
That seems ambitious?
Also extra gravity losses as only 3 engines (but I assume you have figured out how that works with less fuel for the launch because there is less mass.)

How does the efficiency of that compare to doing 2 50 ton cargo loads and sending the astronauts separately allowing the tank to be smaller? Thus the stack of tank on top of a normal (or payload shortened?) starship would be less tall and unwieldy?

[Roy_H]

100 ton cargo plus astronauts plus life support equipment plus mid level thrusters for lunar landing?
That seems ambitious?

I think it is quite reasonable. I even included an extra 50 tons for PE radiation shielding in the calculation.

Also extra gravity losses as only 3 engines (but I assume you have figured out how that works with less fuel for the launch because there is less mass.)

Yes, there are extra gravity losses, but even a fully loaded standard size HLS with just 3 Raptor Vac engines would still make it to orbit. Just costs some extra fuel.

How does the efficiency of that compare to doing 2 50 ton cargo loads and sending the astronauts separately allowing the tank to be smaller? Thus the stack of tank on top of a normal (or payload shortened?) starship would be less tall and unwieldy?

Sounds to me to be a lot of extra complication for almost zero gain. You seem to be focused on the HLS tanker being unwieldly. I admit that is true in terms to getting it to LEO, but once it is in space, size is irrelevant. Even if it was broken down as you suggest to several smaller tankers, would they still have to be balanced on top of a Starship to get to LEO? If so again no advantage, simply takes more flights.

Edit:
If the concept of perching the huge tank on top of the Starship is unfeasible, an alternative would be to have 4 Vac Raptor engines installed and have this mounted directly on top of the booster. Then it could fly itself to orbit just like any other upper stage. Of course it would only be partly fueled, just enough to get to the desired orbit. The engines could then be removed as unneeded extra baggage.

[crandles57]

100 ton cargo plus astronauts plus life support equipment plus mid level thrusters for lunar landing?
That seems ambitious?

I think it is quite reasonable. I even included an extra 50 tons for PE radiation shielding in the calculation.

Also extra gravity losses as only 3 engines (but I assume you have figured out how that works with less fuel for the launch because there is less mass.)

Yes, there are extra gravity losses, but even a fully loaded standard size HLS with just 3 Raptor Vac engines would still make it to orbit. Just costs some extra fuel.

How does the efficiency of that compare to doing 2 50 ton cargo loads and sending the astronauts separately allowing the tank to be smaller? Thus the stack of tank on top of a normal (or payload shortened?) starship would be less tall and unwieldy?

Sounds to me to be a lot of extra complication for almost zero gain. You seem to be focused on the HLS tanker being unwieldly. I admit that is true in terms to getting it to LEO, but once it is in space, size is irrelevant. Even if it was broken down as you suggest to several smaller tankers, would they still have to be balanced on top of a Starship to get to LEO? If so again no advantage, simply takes more flights.

Edit:
If the concept of perching the huge tank on top of the Starship is unfeasible, an alternative would be to have 4 Vac Raptor engines installed and have this mounted directly on top of the booster. Then it could fly itself to orbit just like any other upper stage. Of course it would only be partly fueled, just enough to get to the desired orbit. The engines could then be removed as unneeded extra baggage.

I suppose I would guess the 100 tons could be packed densely enough that you don't run out of payload volume. It is only the fuel section that is shortened, I assume.

I was thinking one smaller engineless depot making the trip three times, which is extra complexity. You have to send the dry mass of the HLS ships 3 times in addition to the total payload rather than just once. So presumably yes it is more tanker flights as well as extra complexity of more lunar trips.

I guess you can somehow attach extra mass to bottom of starship for the lift so that the catch points used are below the centre of mass of the empty starship plus empty depot/tank

[DanClemmensen]

I guess you can somehow attach extra mass to bottom of starship for the lift so that the catch points used are below the centre of mass of the empty starship plus empty depot/tank

At some point you exceed the lifting capacity of the chopsitcks/tower.

[Roy_H]

I guess you can somehow attach extra mass to bottom of starship for the lift so that the catch points used are below the centre of mass of the empty starship plus empty depot/tank

At some point you exceed the lifting capacity of the chopsitcks/tower.

You guys have brought up some real valid objections why my idea of perching the booster sized tanker on top of Starship won't work.

So back to plan B. More akin to a booster mounted on top of the booster, but with only minimal engines mounted to achieve orbit. I think 4 Vac Raptors would be sufficient.

Now there needs to be some in space assembly as I envision external fuel lines from the tanker, mounted on the nose of HLS, down to the fuel ports used to initially fuel the HLS while on the launch pad. I don't know enough about rate of fuel flow, would this be high enough for the 3 Raptor engines mounted in the HLS? If not enough for 1 Raptor? Or alternatively maybe the fuel ports on the HLS should be sized to allow for the high required fuel rate, not for the fuel rate available when filled for launching.

So if we have to do some in space assembly anyhow, does this make the idea of removing the 4 Raptors from the tanker and replacing them with a module to mount to HLS and have fittings and pipes for the fuel transfer realistic? These extra parts would be brought up by a separate Starship flight and the Raptors could be put back in the Starship payload bay for return to Earth. I realize this would not be simple, as the attachment and disengagement has to be all automated. Also would this in orbit assembly be best performed by astronauts brought up on Dragon? Or can it be all automated?

Another issue is about retaining the fuel in the tanker. I expect that one side should be polished to best reflect sunlight and the other anodized or painted black to best radiate heat. Then the tanker would be oriented with the shiny side to the sun. But I do not expect this to be enough and some additional active cooling would need to be added. Anybody have knowledge on how efficient retaining fuel for weeks could be? I need to spend some time reading another thread about in space fueling, and should probably ask this question there.

Edit:
I consulted Grok and found that the Vac Raptor consumes fuel at about 735kg/s and that the fueling rate for Starship on the pad was in the range of 500kg/s to 750kg/s, so possibly high enough to sustain a single Raptor boosting from LEO to LLO. Again according to Grok, using 3 Raptor engines will allow a single burn to achieve TLI resulting in a transit time of about 3 days. Using a single Raptor will require 3 burns on 3 orbits and extend transit time about 10%. This means several more hours spent in the Van Allen belts, and because of gravity losses, is slightly less efficient. Probably a reasonable trade-off vs fuel lines about 4 times larger.

[Roy_H]

Well it seems that the more I dig into this, the more difficult it becomes. My initial fuel requirement seems to be a bit low, and it did not include a safety margin. Initially I was working with a 5% boil-off but that may have been to little. In an attempt to improve this I looked into boil-off mitigation. NASA has done a lot of work for fuel depot in LEO and borrowing from their studies I found that the tanker is best wrapped in a Multi-Layer-Insulation with various layers of aluminum coated mylar and spacers. Minimum suggested for the 3 week plus timelines is 30 layers. This plus active cooling can bring boil-off losses below 0.05%. Providing the 5% recommended extra fuel capacity comes with a 41% penalty.

Playing around with active cooling, I settled on an arrangement with a boom projecting out the nose of the tanker with two solar panels about 23m on a side articulated to always point at the Sun. the radiator for the active cooling could be mounted in the shade of one panel with a counter weight at the far end of the other panel. The radiator would be mounted 90° behind the center of the solar panel and have it's own rotating motor so the panel would be edge wise to Earth during LEO operations. All this with electronics, motors, and batteries (mounted in the nose) would add about 2.5 metric tons to the tanker. Even with the tanker extended to contain 4,000 metric tons of fuel (standard booster is about 3,400 metric tons) The complete mission only had 40 tons spare fuel left at end of mission. Far less than the recommended 5%.

All this extra equipment, solar panels, MLI, etc. would be added after the tanker was in LEO. I used a 500km orbit for LEO in calculations (slightly less fuel required for TLI and an altitude with less debris than lower orbits). As discussed in previous post, I proposed the HLS have smaller fuel tanks with 400 metric tons fuel and the QD fuel port with liquid CH4 and O2 ports doubled in diameter (on average? maybe the O2 port should be much larger than the CH4 port?). This so the 3 Vac Raptors in the HLS can have full thrust fuel from the tanker. As before I proposed in the booster-to-tanker conversion that the Raptor engines be removed in orbit and replaced with a module to attach to the nose of the HLS and have fuel lines external to HLS to the HLS QD port. All these parts, fuel transfer module, solar panels, MLI etc. brought up in a separate Starship flight and that Starship could return to Earth with the removed Raptors.

As fanciful as all this may seem, I think most of it is applicable to any version of Moon mission. That is mitigating boil-off with MLI and active cooling should be seriously considered for all missions with a goal to bring large payloads to Moon surface.

To get to 5% fuel reserve, it would take a whopping 5,400 ton capacity tanker.

Edit:
In terms of safety margin propellent required, I think the 5% needs only to be applied to the return from LLO. If after arriving in LLO, fuel reserves are too low, the landing part of the mission can be aborted and just return to LEO. With this in mind I asked Grok for a re-calculation. Reply is attached. Curiously Grok found discrepancies in it's own previous responses and now says with new reduced reserves being only 5% at LLO, now says a tanker with 4,300 ton capacity will provide the desired safety margin.

4,300 metric ton capacity is still much larger than standard SH booster, but much closer to feasible.

[Roy_H]

In my original proposal, with 2 lifeboat tankers accompanying the standard HLS, I assumed 5% fuel boil-off for the mission. Turns out this is the minimum estimated by NASA for the HLS portion of Artemis mission. The range was from 5% to 15%. The 5% range was with some mitigation of MLI or active cooling. So the original mission I proposed would have required some in-space assembly, and if that is going to be done anyway, why not a full 30 layer MLI and active cooling as I described above. This would bring boil-off for the mission to be less than 1.5% for the mission. That in turn means the lifeboat tankers could be slightly smaller.

I know this whole thread started with the objective of a Moon mission with minimal modification to SpaceX current design goals. That minimal modification has turned out to be more than I expected, but in my opinion both scenarios are still viable. There still remains the question, is it possible for SpaceX to get the required large tanker into orbit for my latest proposal. This is the 4,300 metric ton version. There would not be room in the Megabay to stack another 12 meters of booster tank, so the only viable alternative is to increase the diameter to 10.5 meters. I have often wondered why SpaceX has chosen tall skinny designs. Would it be easy to build a 10.5 m diameter version?  If this could be done and launched into LEO then I still think it is the best most long term (because of reusability) solution for Moon missions.

[Roy_H]

Well, here I go again with variation 3.

This time more akin to version 1 but further optimized so only one lifeboat tanker is required. To reduce TLI fuel requirement I changed the LEO launch altitude to 900Km and have added the same insulation and active cooling specs as are proposed for the HLS to the Lifeboat tanker. That is 50-layer MLI plus solar panels and cooling radiator etc. As before in the HLS, I have added more PE radiation shielding (about 50t) so it covers all occupied area, not just an emergency shelter. Otherwise HLS remains as designed. The added Multi Layer Insulation (MLI) and active cooling adds about 2.5t mass but has benefit of reducing boil-off to 1.5% for the mission. These changes allow a single Lifeboat tanker with 4,050 metric ton fuel capacity. HLS remains at 1,200 ton capacity. Also dry mass is lower than in the first proposal due to Grok finding more accurate estimates of dry mass. As before, HLS and Lifeboat Tanker have 3 gimballed Vac Raptor engines and no sea level engines.

This mission requires the Lifeboat tanker, HLS and cargo Starship to be launched into a 200km LEO. The cargo Starship will contain all the supplies required to outfit HLS and Lifeboat tanker with the MLI shielding, solar panels and radiators required. I am assuming SpaceX is planning on doing this anyway for HLS as I cannot envision the HLS being launched with these items already attached. I am also assuming that a Dragon mission will be required to aid in unloading the Starship and mounting the equipment on HLS and Lifeboat. If SpaceX has figured out how to automate this without astronauts EVA then so much the better. The initial launch of HLS can include the 100 ton payload for the Moon, and future flights will have this cargo delivered to LEO via Starships. As before the lifeboat portion of the tankers have the same PE radiation shielding recommended by NASA, and interior volume equivalent to Orion.

I am not sure how SpaceX will arrange solar panels and shielding, but I think a pair of solar panels mounted on either side to the nose section with dual axis rotation so they can always be oriented to face the Sun. The radiator(s) would be mounted 90° behind the solar panels to always be shaded. The Multi Layer Insulation would be wrapped around the cylindrical portion of the ships. During TLI and TEI coast phase they could be oriented with nose pointing toward the Sun so the solar panels would shade the rest of the rocket. The square solar panels would be quite large, about 20m on side.

Mission sequence is now:
1. launch HLS, Lifeboat tanker, cargo Starship and crewed Dragon into 200km LEO.
2. Astronauts perform EVA and assemble solar panels, radiator, and MLI shielding on HLS and Lifeboat Tanker.
3. Lifeboat tanker and HLS are fully fueled by 22 Starship Tankers. Assuming 150t fuel delivered per flight.
4. Lifeboat tanker and HLS fly to 900km circular orbit.
5. 3 more Starship tankers fly to 900km orbit and top off HLS and Lifeboat tanker.
6. Crew arrive via Dragon and board HLS.
7. HLD and Lifeboat tanker fly to LLO at 100km altitude. Polar orbit.
8. Lifeboat Tanker adds 247 tons fuel to HLS.
9. HLS performs Moon landing remains for about 2 weeks and unloads 100t cargo.
10. HLS launches to LLO.
11. Lifeboat tanker adds 253 tons fuel to HLS.
12. Lifeboat tanker and HLS return to 900km LEO
13. Astronauts transfer to Dragon for EDL to Earth.

Lifeboat tanker and HLS remain in orbit for future missions. When required they will return to 200km altitude for fuel and cargo for next mission.

I have included screenshots of Grok responses and links visited to get information. Diagram of mission profile attached.

[Twark_Main]

I used a 500km orbit for LEO in calculations (slightly less fuel required for TLI and an altitude with less debris than lower orbits).

To reduce TLI fuel requirement I changed the LEO launch altitude to 900Km

Your AI is apparently too sycophantic to bring this to your attention — human to the rescue!!  — but using a higher parking orbit is less fuel-efficient, not more.

One of the ways NASA fit the lunar rover into the mass budget was by lowering the parking orbit from 100 nm to 90 nm. This increased the Oberth effect and made the trajectory more efficient.

If you're looking to avoid space debris, 500 or (especially) 900 km aren't great choices.

[Roy_H]

To reduce TLI fuel requirement I changed the LEO launch altitude to 900Km

Your AI is apparently too sycophantic to bring this to your attention — human to the rescue!!  — but using a higher parking orbit is less fuel-efficient, not more.

One of the ways NASA fit the lunar rover into the mass budget was by lowering the parking orbit from 100 nm to 90 nm. This increased the Oberth effect and made the trajectory more efficient.

If you're looking to avoid space debris, 500 or (especially) 900 km aren't great choices.

Interesting chart showing space debris. I had been going by a much older data. But it does seem to be largely variable depending on who made the chart. Yours is from NASA 2009. From https://www.esa.int/ESA_Multimedia/Images/2025/04/ESA_Space_Environment_2025_figure_2 This was from April this year and shows 900km to be above most satellites, but debris is still high. Debris > 10cm is lower. I will no longer claim that a benefit of 900km orbit is less debris, just less satellites. The primary reason for the 900km orbit is to save fuel for TLI and TEI. It is interesting that this chart does not include SpaceX Starlink satellites, at 360km to 450km orbits and over 6,000 to date.

Had to look up Oberth effect. Says higher speed is better. This appeared to be only applied to elliptical orbits. You are correct in that orbiting speed is higher at lower altitude. However this seems counter intuitive. You have to add energy in the orbital direction to raise to a higher orbit. If choosing a TLI from a lower orbit results in fuel savings, then starting at GEO would be much worse and starting a few thousand km below Lunar orbit would be disastrous requiring almost infinite fuel.

[Twark_Main]

Indeed, the charts show you want to be lower than 500 km, not higher.

No the Oberth effect doesn't just apply to elliptical orbits. Yes the Oberth effect is counterintuitive, but I'm sure AI can explain it better than me. 

[InterestedEngineer]

Indeed, the charts show you want to be lower than 500 km, not higher.

No the Oberth effect doesn't just apply to elliptical orbits. Yes the Oberth effect is counterintuitive, but I'm sure AI can explain it better than me. 

The Oberth effect is easy to explain - why spend all that energy to raise your fuel to a 900km orbit when you can raise it to a 150km orbit for a lot less energy?

The lower altitude you throw stuff out the back, the less work you have to do to raise that stuff to a higher orbit.

[Roy_H]

The Oberth effect is easy to explain - why spend all that energy to raise your fuel to a 900km orbit when you can raise it to a 150km orbit for a lot less energy?

If your goal is just to reach any orbit, yes it takes less fuel to reach a lower orbit. In this case the goal is to reach Moon orbit.

The lower altitude you throw stuff out the back, the less work you have to do to raise that stuff to a higher orbit.

Please define higher orbit. I haven't attempted to make any calculations, so don't take this example too literally.
I would be willing to agree that it takes less fuel to go from a 150km orbit to a 350km orbit than it would to go from a 400km orbit to a 600km orbit. Both raising by 200km. But it does not take less work to go from 150km orbit to 600km orbit than it does starting at 400km. Please provide proof that it takes less work to go from 150km to 600km than from 400 km to 600km.

[Roy_H]

To reduce TLI fuel requirement I changed the LEO launch altitude to 900Km

Your AI is apparently too sycophantic to bring this to your attention — human to the rescue!!  — but using a higher parking orbit is less fuel-efficient, not more.

One of the ways NASA fit the lunar rover into the mass budget was by lowering the parking orbit from 100 nm to 90 nm. This increased the Oberth effect and made the trajectory more efficient.

Indeed, the charts show you want to be lower than 500 km, not higher.

I agree, there is no advantage to the 900km orbit with regards to debris. I will cease to make such a claim. But it is out of the area with large numbers of satellites. The reason to go to the 900km orbit is to save fuel for TLI, not to avoid debris.

No the Oberth effect doesn't just apply to elliptical orbits. Yes the Oberth effect is counterintuitive, but I'm sure AI can explain it better than me. 

Attached explanation by Grok. It explains how raising the initial orbit saves fuel. Not costing more as you claim.

[Twark_Main]

First, let's recognize that this is a textbook example of the limitations of this human/AI hybrid approach. Sycophancy means AI will avoid — and even act against — real fact-checking.

With that out of the way let's rescue our friend Roy here.

The Oberth effect is easy to explain - why spend all that energy to raise your fuel to a 900km orbit when you can raise it to a 150km orbit for a lot less energy?

If your goal is just to reach any orbit, yes it takes less fuel to reach a lower orbit. In this case the goal is to reach Moon orbit.

In this case too, starting in a lower Earth orbit is more efficient.

I haven't attempted to make any calculations, so don't take this example too literally.
 ... Please provide proof that it takes less work to go from 150km to 600km than from 400 km to 600km.

The correct question is: does it take more fuel to go from 150 to 900 and then from 900 to 500,000, or straight from 150 to 500,000?

I'm lazy and don't want to do the Hohmann transfer math, so I just Googled "Hohmann transfer calculator" and found this.

150-900: 413.26 m/s

900-500,000: 2991.01 m/s

150-500,000: 3166.17 m/s


So that's 3404.27 m/s versus 3166.17 m/s, or a 238.10 m/s reduction in delta-v thanks to Oberth.

[Roy_H]

The correct question is: does it take more fuel to go from 150 to 900 and then from 900 to 500,000, or straight from 150 to 500,000?

I'm lazy and don't want to do the Hohmann transfer math, so I just Googled "Hohmann transfer calculator" and found this.

150-900: 413.26 m/s

900-500,000: 2991.01 m/s

150-500,000: 3166.17 m/s

So that's 3404.27 m/s versus 3166.17 m/s, or a 238.10 m/s reduction in delta-v thanks to Oberth.

Ah, So you change the question in order to prove your point.

Your own data shows that the delta V is greater going from 150 - 500,000: of 3166.17m/s than 900 - 500,000: of 2991.01 m/s for a savings of 175.16 m/s.

My goal was to use the smallest possible tanker ship to carry fuel to get to the moon and back. Not to use the least amount of total fuel. And you have proven Grok was right.

[InterestedEngineer]

The correct question is: does it take more fuel to go from 150 to 900 and then from 900 to 500,000, or straight from 150 to 500,000?

I'm lazy and don't want to do the Hohmann transfer math, so I just Googled "Hohmann transfer calculator" and found this.

150-900: 413.26 m/s

900-500,000: 2991.01 m/s

150-500,000: 3166.17 m/s

So that's 3404.27 m/s versus 3166.17 m/s, or a 238.10 m/s reduction in delta-v thanks to Oberth.

Ah, So you change the question in order to prove your point.

Your own data shows that the delta V is greater going from 150 - 500,000: of 3166.17m/s than 900 - 500,000: of 2991.01 m/s for a savings of 175.16 m/s.

My goal was to use the smallest possible tanker ship to carry fuel to get to the moon and back. Not to use the least amount of total fuel. And you have proven Grok was right.

How many hours have you put into playing KSP?

Your intuitions appear wrong, so my guess is next to none.

If you want really good intuition on how to plan a space mission, then KSP is your friend.  It's cheap, go play it for a while, you intuition will be updated.

Grok cannot compete with KSP enforced human intuition.  Though I suspect if you added the prompt "let's plan something just like we would in KSP" it might spit out better answers, since there are many KSP forum posts on the topic.

[Twark_Main]

The correct question is: does it take more fuel to go from 150 to 900 and then from 900 to 500,000, or straight from 150 to 500,000?

I'm lazy and don't want to do the Hohmann transfer math, so I just Googled "Hohmann transfer calculator" and found this.

150-900: 413.26 m/s

900-500,000: 2991.01 m/s

150-500,000: 3166.17 m/s

So that's 3404.27 m/s versus 3166.17 m/s, or a 238.10 m/s reduction in delta-v thanks to Oberth.

Ah, So you change the question in order to prove your point.

Your own data shows that the delta V is greater going from 150 - 500,000: of 3166.17m/s than 900 - 500,000: of 2991.01 m/s for a savings of 175.16 m/s.

My goal was to use the smallest possible tanker ship to carry fuel to get to the moon and back. Not to use the least amount of total fuel.

I anticipated that reply, lol.

If that's your goal, you and Grok are still doing it wrong. You'd be better off (both in smallest tanker size and least amount of total fuel) by using an intermediate parking orbit that's an elliptical orbit with a 150 km perigee rather than a circular 900 km orbit.

Again, a human would've immediately recognized this problem, but Grok consistently shows it doesn't know the right question to ask (a more valuable skill than just being able to answer the question when someone has asked the wrong question).


This is gold, keep going. Don't let humans and facts ruin the glorious AI future! You're doing a marvelous job showing the pitfalls of AI, don't stop now. 

[Roy_H]

I anticipated that reply, lol.

If that's your goal, you and Grok are still doing it wrong. You'd be better off (both in smallest tanker size and least amount of total fuel) by using an intermediate parking orbit that's an elliptical orbit with a 150 km perigee rather than a circular 900 km orbit.

Again, a human would've immediately recognized this problem, but Grok consistently shows it doesn't know the right question to ask (a more valuable skill than just being able to answer the question when someone has asked the wrong question).

This is gold, keep going. Don't let humans and facts ruin the glorious AI future! You're doing a marvelous job showing the pitfalls of AI, don't stop now. 

Again I feel compelled to clarify my goals. In your elliptical orbit there are issues I wish to avoid, one is that it swings into the Van Allan Belt and two, makes multiple passes through the greatest number of satellite orbits where course adjustments might have to be made, and three, it is more difficult to launch other ships to the same elliptical orbit vs a circular orbit. I did not want to send the Dragon crew into the Val Allan Belt in order to match orbit with the HLS. If you confine the elliptical orbit to a 900km apogee, then the Oberth benefit is less than the gravity losses.

However, I agree that technically you are right. Just doesn't align with my goals. And Grok did not ask the wrong question, I posed my questions to Grok to find the most optimal plan to meet all my criteria.

[Twark_Main]

I anticipated that reply, lol.

If that's your goal, you and Grok are still doing it wrong. You'd be better off (both in smallest tanker size and least amount of total fuel) by using an intermediate parking orbit that's an elliptical orbit with a 150 km perigee rather than a circular 900 km orbit.

Again, a human would've immediately recognized this problem, but Grok consistently shows it doesn't know the right question to ask (a more valuable skill than just being able to answer the question when someone has asked the wrong question).

This is gold, keep going. Don't let humans and facts ruin the glorious AI future! You're doing a marvelous job showing the pitfalls of AI, don't stop now. 

Again I feel compelled to clarify my goals. In your elliptical orbit there are issues I wish to avoid, one is that it swings into the Van Allan Belt

Depends on the apogee height. You can still get the same delta-v reduction on the final burn without reaching the inner belt.

and two, makes multiple passes through the greatest number of satellite orbits where course adjustments might have to be made

Most of the object density (and collision risk) is in a ring near the poles, whereas this would be passing through those altitudes closer to the equator, so it's not actually as concerning as the simple altitude plot would suggest.

and three, it is more difficult to launch other ships to the same elliptical orbit vs a circular orbit.

Despite TheRadicalModerate's fearmongering, this isn't really true.

I did not want to send the Dragon crew into the Val Allan Belt in order to match orbit with the HLS. If you confine the elliptical orbit to a 900km apogee, then the Oberth benefit is less than the gravity losses.

Can I see the math? 

The inner belt starts at around 5,000 km, so there's plenty of margin here.

However, I agree that technically you are right. Just doesn't align with my goals. And Grok did not ask the wrong question, I posed my questions to Grok to find the most optimal plan to meet all my criteria.

Right. The problem is that AI doesn't push back. It's incapable of doing so. It prioritizes sycophancy over questioning whether "the requirements are wrong" (to borrow an Elon Musk phrase).

AI is seductive because it promises access to a smart person, but without the annoying part where the smart person is ever smarter than you. Problem is, that's the most important part. 

[xvel]

LLMs are perfectly capable of pushing back, commercial models are just not trained to do so as such a product would not sell well to a wide audience.

[Roy_H]

I anticipated that reply, lol.

If that's your goal, you and Grok are still doing it wrong. You'd be better off (both in smallest tanker size and least amount of total fuel) by using an intermediate parking orbit that's an elliptical orbit with a 150 km perigee rather than a circular 900 km orbit.

Again, a human would've immediately recognized this problem, but Grok consistently shows it doesn't know the right question to ask (a more valuable skill than just being able to answer the question when someone has asked the wrong question).

This is gold, keep going. Don't let humans and facts ruin the glorious AI future! You're doing a marvelous job showing the pitfalls of AI, don't stop now. 

Again I feel compelled to clarify my goals. In your elliptical orbit there are issues I wish to avoid, one is that it swings into the Van Allan Belt

Depends on the apogee height. You can still get the same delta-v reduction on the final without reaching the inner belt.

and two, makes multiple passes through the greatest number of satellite orbits where course adjustments might have to be made

Most of the object density (and collision risk) is in a ring near the poles, whereas this would be passing through those altitudes closer to the equator, so it's not actually as concerning as the simple altitude plot would suggest.

and three, it is more difficult to launch other ships to the same elliptical orbit vs a circular orbit.

Despite TheRadicalModerate's fearmongering, this isn't really true.

I did not want to send the Dragon crew into the Val Allan Belt in order to match orbit with the HLS. If you confine the elliptical orbit to a 900km apogee, then the Oberth benefit is less than the gravity losses.

Can I see the math? 

The inner belt starts at around 5,000 km, so there's plenty of margin here.

However, I agree that technically you are right. Just doesn't align with my goals. And Grok did not ask the wrong question, I posed my questions to Grok to find the most optimal plan to meet all my criteria.

Right. The problem is that AI doesn't push back. It's incapable of doing so. It prioritizes sycophancy over questioning whether "the requirements are wrong" (to borrow an Elon Musk phrase).

AI is seductive because it promises access to a smart person, but without the annoying part where the smart person is smarter than you. Problem is, that's the most important part. 

Ah, thank you. Now I feel this discussion is finally addressing my real problems. I was under the impression that the lower limit of Van Allan Belt was closer to 1,200km and wanted to be conservatively below that. If it is acceptable to send the Dragon and crew to higher orbits then I view this as beneficial.

Also for the issue of elliptical orbit through the main belt of satellites does merit re-consideration. I guess I am intuitively apposed to the idea, but probably not rational.

If I accept your recommendations, then this plan becomes even more desirable. What would you suggest as the highest apogee for Dragon crew to fly and avoid extra radiation exposure? In order to firm up this plan, I would need more accurate estimates on the dry mass of HLS and my proposed Lifeboat Tanker. But I was worried that the tanker size would be too large to be practical (as was my giant tanker in the previous proposal) and looked for solutions to minimize that. Also, what is the practical limit of Dragon launched on Falcon 9 with recovered booster? How high of an elliptical orbit could it reach with a perigee of 150km? I have finally come around to your approach and believe with those improvements this mission profile would be very attractive.

[Twark_Main]

Reaching a 900 km circular orbit takes 413.26 m/s, so if we use the same delta-v that ensures that Dragon has enough fuel to reach the rendezvous point. That works out to 150x1740 km.


If you just want to achieve the same final burn delta-v as the original 900x900 circular orbit (ie saving 175.16 m/s for a final TLI burn of 2991.01 m/s), that works out to 150x770 km. Surprisingly it's entirely below 900 km!

Polaris Dawn hit 1,500 km, but even at that altitude I seem to recall they were expecting (like ISS) most radiation would be encountered when crossing over the South Atlantic Anomaly. I have not yet seen the radiation data from that mission.

[Roy_H]

Grok tells me that Dragon can achieve a 5,000km HEEO with booster landing at sea instead of land. Using a 5,000km HEEO the Lifeboat Tanker can be 1,360 ton capacity and total Starship Tanker flights reduced from 25 to 24. Not as much savings as I had hoped, but still an improvement.

[Greg Hullender]

The Oberth effect is easy to explain - why spend all that energy to raise your fuel to a 900km orbit when you can raise it to a 150km orbit for a lot less energy?

If your goal is just to reach any orbit, yes it takes less fuel to reach a lower orbit. In this case the goal is to reach Moon orbit.

The lower altitude you throw stuff out the back, the less work you have to do to raise that stuff to a higher orbit.

Please define higher orbit. I haven't attempted to make any calculations, so don't take this example too literally.
I would be willing to agree that it takes less fuel to go from a 150km orbit to a 350km orbit than it would to go from a 400km orbit to a 600km orbit. Both raising by 200km. But it does not take less work to go from 150km orbit to 600km orbit than it does starting at 400km. Please provide proof that it takes less work to go from 150km to 600km than from 400 km to 600km.

This one puzzled me for quite a while too (and I can do orbital calculations), so maybe I can make it clear what's happening here.

First, the higher up you place your depot, the more expensive it's going to be to put fuel in it. But because the tanker is only about 50% fuel by weight even in the very lowest usable orbit, that means half or more of the fuel you burn lifting it to a higher orbit is wasted moving the mass of the vehicle--not the fuel in it. So if you really wanted a depot at 900 km, you'd do best to fill up two depos in very low Earth orbit, boost them both up to 900 km, and have one of them top the other one off. Perhaps you already understand this point. (Apologies if so.)

But the second point is that the faster your rocket is going, the better a burn you get. This is the Oberth effect everyone is talking about. Intuitively, this is because the rocket has to put energy into moving both the vehicle and the propellant. You're paying to send the rocket to the moon, but you're also paying to send the exhaust on its own trip. You'd like to avoid that, if possible.

So if your rocket flies past the Earth at the exact same speed as the exhaust, then all the energy (relative to the Earth) goes into the rocket; the exhaust, which comes out at zero velocity relative to the Earth, simply falls to the ground. This turns out to be such a big effect, that the best way to get to the moon from your 900 km-high orbit is probably to a) retrofire to move to a 900 x 200 km orbit b) wait until closest approach to the Earth c) fire enough to boost into TLI. That is, the Oberth effect is so big that it's worth it to burn fuel to drop from a higher orbit into a lower (elliptical) orbit just so you can maximize the effect.

However, if you kept all your fuel in LEO all along then you don't have to do this. On the other hand, some proposals do call for using tandem depots such that you'd fuel up two depots, then fill a starship from one of them and have the starship plus the other depot go into a highly elliptical orbit. (Of a few days duration.) The second depot tops off the starship, and at the next perigee, it does a big Oberth burn. It can actually achieve solar escape velocity this way.

Another phenomenon you might not know about is that an elliptical orbit is faster than a circular one at perigee and slower at apogee. That is, a 900 x 200 km elliptical orbit is faster than a 200 km circular orbit at perigee and slower than a 900 km circular orbit at apogee. In the case of twin depots, that's all to the good, since you get that extra speed for your biggest burn.

If you like, I'll work out the math for when the best way to reach escape velocity from Earth orbit at altitude h is to use Oberth and when it's not. It's not hard, but I have to be in the right mood, and dinner is almost ready. :-)

[Robotbeat]

Grok tells me that Dragon can achieve a 5,000km HEEO with booster landing at sea instead of land. Using a 5,000km HEEO the Lifeboat Tanker can be 1,360 ton capacity and total Starship Tanker flights reduced from 25 to 24. Not as much savings as I had hoped, but still an improvement.

Are you sure? What’s the actual calculation?

BTW, there’s a big difference between V3 and V4. Twice the capacity.

[Roy_H]

Grok tells me that Dragon can achieve a 5,000km HEEO with booster landing at sea instead of land. Using a 5,000km HEEO the Lifeboat Tanker can be 1,360 ton capacity and total Starship Tanker flights reduced from 25 to 24. Not as much savings as I had hoped, but still an improvement.

Are you sure? What’s the actual calculation?

BTW, there’s a big difference between V3 and V4. Twice the capacity.

it's actually a lot of work to show the calculation, I did it for the last post showing the latest mission diagram. Copy and paste doesn't work because all the formatting gets lost, so I resorted to screen captures. But I can certainly to it for this one. You can look at that one to get the general idea, obviously a new one would show different values.

My mission profile assumes V4 for 150 ton payload to LEO.

[Roy_H]

So if your rocket flies past the Earth at the exact same speed as the exhaust, then all the energy (relative to the Earth) goes into the rocket; the exhaust, which comes out at zero velocity relative to the Earth, simply falls to the ground. This turns out to be such a big effect, that the best way to get to the moon from your 900 km-high orbit is probably to a) retrofire to move to a 900 x 200 km orbit b) wait until closest approach to the Earth c) fire enough to boost into TLI. That is, the Oberth effect is so big that it's worth it to burn fuel to drop from a higher orbit into a lower (elliptical) orbit just so you can maximize the effect.

However, if you kept all your fuel in LEO all along then you don't have to do this. On the other hand, some proposals do call for using tandem depots such that you'd fuel up two depots, then fill a starship from one of them and have the starship plus the other depot go into a highly elliptical orbit. (Of a few days duration.) The second depot tops off the starship, and at the next perigee, it does a big Oberth burn. It can actually achieve solar escape velocity this way.

Another phenomenon you might not know about is that an elliptical orbit is faster than a circular one at perigee and slower at apogee. That is, a 900 x 200 km elliptical orbit is faster than a 200 km circular orbit at perigee and slower than a 900 km circular orbit at apogee. In the case of twin depots, that's all to the good, since you get that extra speed for your biggest burn.

If you like, I'll work out the math for when the best way to reach escape velocity from Earth orbit at altitude h is to use Oberth and when it's not. It's not hard, but I have to be in the right mood, and dinner is almost ready. :-)

Thank you for your clear explanation. My goal wasn't primarily lowest total fuel, just smallest possible supporting tanker. And returning HLS and Lifeboat Tanker to an orbit accessible by Dragon launched on Falcon 9, booster recovered. I consider hardware is expensive and fuel is cheap because SpaceX plans on re-using the same Starship Tankers with recovery of both the booster and tanker. In previous example the Lifeboat Tanker is significantly larger than the HLS, in the last case using HEEO it is about the same size.

[Roy_H]

Another iteration using elliptical orbit to take advantage of Oberth effect.

What I asked of Grok:
 Ok, here we go again determining minimum Lifeboat Tanker fuel capacity necessary for the mission profile. HLS dry mass in increased by 50t PE radiation shielding for crew (covering all crew area, not just a small shelter) and likewise 10t PE shielding on Lifeboat Tanker with crew quarters equivalent to Orion and of course all necessary crew support equipment and food necessary to return to LEO from LLO. HLS carries 100t payload to be deposited on Moon south pole per Artemis destination. HLS and Lifeboat tanker are equipped with 3 Vac Raptors (zero sl Raptors), 50 layer MLI and appropriate sized pair of solar panels (dual axis control allowing always pointing at Sun) with active cooling to keep fuel at 100°K. Fuel tanks sized for this temperature and CH4 at 1 bar and O2 at 6 bar. HLS remains as designed with the exception of additional PE. 5% fuel reserve for HLS returning from LLO to LEO and a smaller 1% fuel reserve for Lifeboat Tanker returning from LLO to LEO. New mission profile: Launch Lifeboat Tanker and HLS to 200km circular orbit with HLS having 100t payload included. Both loaded with the maximum fuel still allowing them to achieve orbit. Starship and Dragon meet up to install MLI and solar panels. Tanker Starships as required to fill Lifeboat tanker and HLS. Lifeboat tanker and HLS go to elliptical orbit, on plane suitable for TLI, 3000km x 200km. More Starship Tanker missions to top off Lifeboat Tanker and HLS in their elliptical orbit. But to save a little, instead of the previous 6 Starship Tankers flying to HEEO, one Starship tankers remains in 200km orbit, another Starship tanker makes flights to partially fill the first Starship tanker, and then only one Starship tanker has to fly to the HEEO to top off Lifeboat Tanker and HLS. Dragon crew arrives and boards HLS, Dragon performs EDL. Lifeboat Tanker and HLS perform TLI to LLO (100km). Tanker adds minimum fuel to bring HLS up to fuel required to land on Moon, deposit 100t payload, and return to LLO with 5% reserve, and remain on Moon surface for about 2 weeks (until moon is in desirable position for efficient TEI). Add fuel to HLS for return to LEO elliptical orbit. Please state amount of fuel transferred both before and after lunar landing. Dragon launched to meet HLS in elliptical orbit and return astronauts to Earth. Lifeboat Tanker remain in orbit until next mission, 6 -12 months. As stated before the main question is how large the Lifeboat Tanker has to be and how many Starship tanker flights required.

What Grok responded:
Minimum Lifeboat Tanker Fuel Capacity and Mission Refinements
Based on the updated mission profile with the 3,000 km × 200 km elliptical orbit (semi-major axis ≈7,971 km), 3 Raptor Vacuum engines (I_sp = 380 s, v_e ≈ 3.727 km/s), 50-layer MLI + active cooling/solar panels (dual-axis Sun-pointing) for 100 K fuel (CH₄ at 1 bar, O₂ at 6 bar), dry masses (HLS: 135 t including full crew PE shielding + support; LT: 95 t including Orion-equivalent quarters PE shielding + return support/crew supplies), 100 t HLS payload (includes 2-week supplies), 5% HLS return reserve, 1% LT return reserve, and 1.5% boil-off uplift on LLO transfers, the minimum LT fuel capacity is 1,558 metric tons.
This enables the single LT to handle outbound to LLO (Δv = 3.30 km/s total), transfers to HLS, and return to elliptical (Δv = 3.30 km/s total with reserve), assuming full load before TLI from the elliptical perigee.
The HLS retains its 1,200 metric ton fuel capacity without derating at 100 K—the tanks support the subcooled densities (~440 kg/m³ CH₄, ~1,120 kg/m³ O₂) with no volume loss, and active cooling ensures stability during the 2-week surface stay and transits.

Key delta V values:
Raise from 200 km circular to elliptical: 0.656 km/s.
TLI (elliptical perigee to translunar): 2.477 km/s (v_inf ≈ 0.83 km/s at Moon).
LOI to 100 km polar LLO: 0.82 km/s.
Outbound total: 3.30 km/s.
Landing (LLO to South Pole): 1.88 km/s.
Ascent (surface to LLO): 1.88 km/s.
TEI: 0.82 km/s.
Propulsive insertion (to elliptical): 2.477 km/s.
Return total: 3.30 km/s.

Propellant transfers in LLO:
246 metric tons pre landing.
205 tons post accent.

Tanker Flights Overview

Initial Fill at 200 km Circular: Vehicles launch with max allowable propellant (~200-300 t each, including payload for HLS). Tankers top off to full (1,558 t LT + 1,200 t HLS = 2,758 t total) → 19 flights (150 t delivery/flight; last partial).
Top-Off at Elliptical (Pre-TLI): Raise consumes 499 t total (232 t HLS + 267 t LT). Direct delivery to elliptical requires 1 flight (ST delivers 499 t net; max capacity ~971 t per reusable round-trip ST, assuming 100 t dry/1,200 t capacity—well within limits). 5 ST flights, 4 to fill the first one.

Diagram looks pretty much the same as previous. Mostly just text changes to reflect the 1,560 t capacity of Lifeboat Tanker and HEEO staging orbit.

This does reduce the tanker flights by 1 vs previous 900km circular orbit, 24 vs 25 flights, and reduced size of Lifeboat Tanker.

Greg, if you would like to verify the delta V figures it would be appreciated.

[InterestedEngineer]

If there's one thing that LLMs are good at it's formatting text.  So please stop pasting Grok's wall of text, it's practically unreadable.

Here's an example from chatGPT on how to format the above so it's human readable and you can actually follow the math.

ChatGPT link there so you can emulate the prompts:   https://chatgpt.com/share/68f10b1d-eb64-8013-8697-01e02014e774


Summary (keep-orig assumptions)

* Orbit staging: 200 km circular → raise to 3000×200 km elliptical (Oberth at perigee used for TLI).
* Engines: 3×Vac Raptors, Isp = 380 s (vₑ ≈ 3.7265 km/s).
* Temperatures / tankting: fuel at 100 K, CH₄ @1 bar, O₂ @6 bar, 50-layer MLI, active cooling.
* Masses (Grok): HLS dry = 135 t (plus 100 t payload), LifeboatTanker (LT) dry = 95 t.
* Reserves: HLS return reserve 5%, LT return reserve 1%.
* Key Δv (Grok): outbound total = 3.30 km/s; landing = 1.88 km/s; ascent = 1.88 km/s; LOI/TEI legs ≈0.82/2.477 km/s as listed.
* Grok final headline: LT fuel capacity ≈ 1,558 t; HLS fuel capacity ≈ 1,200 t.
* Prop transfers (Grok): 246 t pre-landing, 205 t post-ascent.

Essential equations (use direct LaTeX image links)

Rocket equation: 


Mass ratio: 


Propellant mass: 


Quick sample checks (minimal work to verify numbers)

Constants: 


1) For Δv = 3.30 km/s: 
 
Dry 95 t → 
 


2) For landing+ascent Δv = 1.88+1.88 = 3.76 km/s: 
 
Dry+payload = 235 t → 
 


Interpretation: single-stage surface round trip needs ≈410 t prop (order of magnitude matches 1,200 t tank).

Short logical notes

1. LT 1,558 t derives from system requirement (topping HLS, own Δv, reserves, losses). Plausible scale. 
2. Verify per-burn sequencing (Oberth perigee burn first, etc.). 
3. Tanker flights: Grok assumes ~150 t net delivery/flight → 19–24 flights total.

Deliverables (paste to NSF post)

Lifeboat Tanker (LT) dry 95 t, HLS dry 135 t + 100 t payload. 
Isp=380 s (vₑ≈3726.53 m/s). 
Key Δv: outbound 3.30 km/s; land 1.88 km/s; ascent 1.88 km/s. 
Grok result: LT fuel ≈ 1,558 t; HLS fuel ≈ 1,200 t. 
Prop transfers LLO: 246 t pre-landing, 205 t post-ascent.

Equations: 
 
 
Sample (Δv=3.30 km/s): → 95 t dry →  
Sample (land+ascent 3.76 km/s): → 235 t dry+payload →

One-line conclusion: 
Grok’s LT ≈1,558 t and HLS ≈1,200 t are order-of-magnitude consistent with single-stage rocket-eq checks when accounting for HLS surface round-trip Δv (≈3.76 km/s) and reserves; verify per-burn sequencing and Starship net delivery per tanker flight to confirm 19–25 flight count.

[crandles57]

The inner belt starts at around 5,000 km, so there's plenty of margin here.

Hmm confusing?

https://en.wikipedia.org/wiki/Van_Allen_radiation_belt

Earth's two main belts extend from an altitude of about 640 to 58,000 km (400 to 36,040 mi)[3] above the surface, in which region radiation levels vary.
...
The inner Van Allen Belt extends typically from an altitude of 0.2 to 2 Earth radii (L values of 1.2 to 3) or 1,000 km (620 mi) to 12,000 km (7,500 mi) above the Earth.[4][23]

Polaris Dawn reached 1400Km and that was ok, but they didn't stay that high long.

So what is the efficient way to do Roy's plan without too much radiation exposure? Maybe using something like 1000 * 125 km orbit for final fuelling and then Dragon dock for astronaut transfer?

Mission sequence is now:
1. launch HLS, Lifeboat tanker, cargo Starship and crewed Dragon into 200km LEO.
2. Astronauts perform EVA and assemble solar panels, radiator, and MLI shielding on HLS and Lifeboat Tanker.
3. Lifeboat tanker and HLS are fully fueled by 22 Starship Tankers. Assuming 150t fuel delivered per flight.
4. Lifeboat tanker and HLS fly to 900km circular orbit.
5. 3 more Starship tankers fly to 900km orbit and top off HLS and Lifeboat tanker.
6. Crew arrive via Dragon and board HLS.
7. HLD and Lifeboat tanker fly to LLO at 100km altitude. Polar orbit.
8. Lifeboat Tanker adds 247 tons fuel to HLS.
9. HLS performs Moon landing remains for about 2 weeks and unloads 100t cargo.
10. HLS launches to LLO.
11. Lifeboat tanker adds 253 tons fuel to HLS.
12. Lifeboat tanker and HLS return to 900km LEO
13. Astronauts transfer to Dragon for EDL to Earth.

Lifeboat tanker and HLS remain in orbit for future missions. When required they will return to 200km altitude for fuel and cargo for next mission.

Re Number 5 above: I don't think you send 3 tankers to 1000*125 km for final fuelling. I think it is more like one depot filled by 2 tankers in 150*150 km orbit then send the depot to 1000*125 km to do one final fuelling. Maybe with 1000*125 km orbit we get away with a smaller tank and only need one tank filling the depot before going to 1000*125 for final fuelling?

Is fuelling and astronaut transfer in 1000*125 km orbit a lot more difficult than in circular orbits? Is 125km too low a perigee?

[Roy_H]

Re Number 5 above: I don't think you send 3 tankers to 1000*125 km for final fuelling. I think it is more like one depot filled by 2 tankers in 150*150 km orbit then send the depot to 1000*125 km to do one final fuelling. Maybe with 1000*125 km orbit we get away with a smaller tank and only need one tank filling the depot before going to 1000*125 for final fuelling?

Is fuelling and astronaut transfer in 1000*125 km orbit a lot more difficult than in circular orbits? Is 125km too low a perigee?

Yes, it is definitely better to add fuel to one ST to deliver fuel to the HEEO via multiple flights. Did this in my latest proposal. I can't answer the question about the viability of 125km perigee. I chose a more conservative 200km because I was concerned about leaving the HLS and Lifeboat Tanker in orbit for long periods of time, waiting for the next mission, which could be 6 to 12 months. How much would the orbit decay in that time? If 125km is acceptable, then better. I was originally concerned about matching elliptical orbits, but several people here have assured me that is not a problem.

[InterestedEngineer]

Re Number 5 above: I don't think you send 3 tankers to 1000*125 km for final fuelling. I think it is more like one depot filled by 2 tankers in 150*150 km orbit then send the depot to 1000*125 km to do one final fuelling. Maybe with 1000*125 km orbit we get away with a smaller tank and only need one tank filling the depot before going to 1000*125 for final fuelling?

Is fuelling and astronaut transfer in 1000*125 km orbit a lot more difficult than in circular orbits? Is 125km too low a perigee?

Yes, it is definitely better to add fuel to one ST to deliver fuel to the HEEO via multiple flights. Did this in my latest proposal. I can't answer the question about the viability of 125km perigee. I chose a more conservative 200km because I was concerned about leaving the HLS and Lifeboat Tanker in orbit for long periods of time, waiting for the next mission, which could be 6 to 12 months. How much would the orbit decay in that time? If 125km is acceptable, then better. I was originally concerned about matching elliptical orbits, but several people here have assured me that is not a problem.

you can leave them long term in 200km.  The deltaV to get from 200km to 125km is so little that you might as well do that just before the final burn to the moon.

[Roy_H]

you can leave them long term in 200km.  The deltaV to get from 200km to 125km is so little that you might as well do that just before the final burn to the moon.

If 125km circular is acceptable, then I would do all the low level fueling etc. at 125km, raise to a 3000km x 125km HEEO, top off fuel, and gain additional benefit. I wonder if this would be enough to have one less fueling flight? On return it could be to a 3000km x 200km to be left there until next mission and when preparing for next mission, drop the HLS and Lifeboat Tanker to 125km circular. Rinse and repeat.

[crandles57]

Re Number 5 above: I don't think you send 3 tankers to 1000*125 km for final fuelling. I think it is more like one depot filled by 2 tankers in 150*150 km orbit then send the depot to 1000*125 km to do one final fuelling. Maybe with 1000*125 km orbit we get away with a smaller tank and only need one tank filling the depot before going to 1000*125 for final fuelling?

Is fuelling and astronaut transfer in 1000*125 km orbit a lot more difficult than in circular orbits? Is 125km too low a perigee?

Yes, it is definitely better to add fuel to one ST to deliver fuel to the HEEO via multiple flights. Did this in my latest proposal. I can't answer the question about the viability of 125km perigee. I chose a more conservative 200km because I was concerned about leaving the HLS and Lifeboat Tanker in orbit for long periods of time, waiting for the next mission, which could be 6 to 12 months. How much would the orbit decay in that time? If 125km is acceptable, then better. I was originally concerned about matching elliptical orbits, but several people here have assured me that is not a problem.

Yes 125km perigee would be too low for a long period of time between missions. I was hopeful it would be ok for an orbit or two or three prior to TLI. After mission return to something more like 630km circular for astronaut transfer? (suggested just below lowest value of 640km I have seen for lower limit of Van Allen Belts)

Mission sequence would be more like:
1. Launch HLS, Lifeboat tanker, cargo Starship and crewed Dragon into 200km LEO.
2. Assembly astronauts perform EVA and assemble solar panels, radiator, and MLI shielding on HLS and NRHO Lifeboat Depot. Astronauts return on dragon after assembly work to avoid being around during refuelling.
3. Launch 2 LEO depots to 140km circular orbit.
4. Launch 19? tankers to same 140 km circular orbit to nearly fill depots. (150tons*21launches=3150 which is < 1585 tons * 2 depots. Nearly full as don't want a part full tanker hanging around or returning part full)
(3 and 4 can happen while 2 is completed.)
5. Boost depots to 200km circular orbit and fill 'NRHO lifeboat depot' retain just sufficient fuel in LEO depots to return to 140km circular orbit. The surplus fuel goes to cargo and HLS ship
6. NRHO lifeboat depot adjusts orbit to 1000*125 km orbit (possibly gets a refill?) and does TLI to NRHO (boil off is lower here)
7. One depot returns to 140km circular orbit.
8. Launch x? tankers to the 140 km circular orbit to refuel the LEO depot there.
9. Adjust orbits of cargo ship and HLS ship and LEO depot to 1000*125 km orbit
10. Add fuel to cargo ship and HLS ship from the LEO depot
11. Launch mission astronauts to transfer to HLS ship in 1000 * 125 km orbit
12. TLI of cargo ship and HLS ship to NRHO
13. Add fuel to cargo ship and HLS ship from NRHO lifeboat depot retaining sufficient for return to LEO.
14. Land cargo and then HLS ship on moon.
15. Unload cargo and complete mission objectives on moon.
16. Launch from moon to NRHO
17. Refuel returning ship.
18. Return to ~630km*630km orbit
19. Dragon launches to 630*630 km orbit to return astronauts to Earth

NRHO lifeboat depot stays there and is possibly of some use for future missions? Ion drive to maintain this orbit without using chemical fuels?

One LEO depot is in 1000*125 and this is unstable for long period so slowly and efficiently change to something more like 500*200 km orbit if it will be a long time before reuse. If needed quickly it can go more directly to 140km circular orbit. Depot in 200*200 km orbit is probably fine there until needed.

Next missions would have first refuel in 630*630 km orbits before adjusting to 1000*125 for final refill astronaut transfer and TLI.

So how many things have I got wrong with that mission sequence?

What is x and/or number of fuel launches? Is one 'NRHO lifeboat depot' sufficient to provide fuel for two ships (in this case a lunar cargo ship and a HLS ship)? Alternately, could we aim to do better e.g. try to support 5 lunar landing ships with 2 NRHO depot ships?

[crandles57]

you can leave them long term in 200km.  The deltaV to get from 200km to 125km is so little that you might as well do that just before the final burn to the moon.

If 125km circular is acceptable, then I would do all the low level fueling etc. at 125km, raise to a 3000km x 125km HEEO, top off fuel, and gain additional benefit. I wonder if this would be enough to have one less fueling flight? On return it could be to a 3000km x 200km to be left there until next mission and when preparing for next mission, drop the HLS and Lifeboat Tanker to 125km circular. Rinse and repeat.

I am doubting 125km circular is high enough for a LEO depot to do ~10 proximity docking and fuel transfer operations particularly if there might be a delay to some of the refuelling launches. I suggested 140*140km for tanker fuelling depot operations, but others likely have a much better idea of what is sensible. I am thinking 10 refuelling operations might be over 5 days if all launches are from one pad. Perhaps you can reduce that to 2 or 3 days by using more pads perhaps in different locations? It is still a lot more orbits than 2 or 3 orbits in 1000*125 km for a refuel and an astronaut transfer prior to TLI at perigee.

[Roy_H]

6. NRHO lifeboat depot adjusts orbit to 1000*125 km orbit (possibly gets a refill?) and does TLI to NRHO (boil off is lower here)

If you don't top off fuel in the elliptical orbit, there is no advantage in going there at all. It would be more fuel efficient to simply do TLI from 125km circular.

[crandles57]

6. NRHO lifeboat depot adjusts orbit to 1000*125 km orbit (possibly gets a refill?) and does TLI to NRHO (boil off is lower here)

If you don't top off fuel in the elliptical orbit, there is no advantage in going there at all. It would be more fuel efficient to simply do TLI from 125km circular.

I had it in 200 * 200 km and wanted oberth effect of TLI at the higher speed of at perigee of 1000*125 km but yes if you don't need the refuel in 1000*125 then go directly in most efficient manner from 200*200 (or in later missions from 630*630km).

(Grok tells me better to go directly from 630 * 630 km to NRHO rather than via 1000*125 but I am not sure I totally trust it.

The direct path requires 3.85 km/s total (3.02 km/s Earth-side + 0.83 km/s insertion).
The indirect path requires 4.20 km/s total (3.37 km/s Earth-side + 0.83 km/s insertion)

https://x.com/i/grok/share/S9VqzcwP8VMV04PCsAcoYbnpO )

[Roy_H]

I tried to pick conservative values for perigee and apogee. I believe the values I chose produce a compelling mission with the Lifeboat Tanker being close to the same size as the HLS, the LT (Lifeboat Tanker) is basically an HLS with moon landing thrusters, legs, cargo area and half the crew quarters removed and replaced with larger fuel tanks. Entirely buildable and launchable.  Clearly higher apogee and lower perigee would yield additional benefits. Small changes like 150km vs 200 are negligible, I wondered how much I could lower the 3000km by going to 150km and the answer was 2915km.

I believe the only major issue that needs to be resolved is 3000km dangerously high into the Van Allan Belt?

It occurred to me that since I have specified that the HLS have a much higher radiation shielding than Dragon, that astronauts, and NASA, should be comfortable with 3000km altitude. If it is an issue for Dragon, then the astronauts could board the HLS in the 200km circular orbit before it is raised to the HEEO for fuel top off. Coming back would be trickier as the intention is to leave the HLS and LT in HEEO until next mission. Could Dragon dock in the HEEO orbit and astronauts board and undock while in the lower portion of the orbit, and immediately retro-thrust to lower orbit?

Another issue is that I suggested a Dragon trip and astronauts would be required to equip HLS and LT with solar panels, radiator, and MLI (Multi Layer Insulation). I expect this will be done robotically. Has anyone designed 'space bots'? I envisage small bots equipped with Draco thrusters, cameras, and arms either teleoperated or more likely trained to assemble these parts. They could be included in the Starship cargo and there would be no need for the Dragon visit.

Edit:
Well, I probably screwed up big time trying to use https://oltaris.nasa.gov as I guessed at most of the parameters. However I submitted two almost identical projects one for a circular orbit of 500km and the other for 3000km circular. The 3000km had mGy and mSv values 2 to 3 orders of magnitude higher at 3k vs 500 so I take it that 3000km is a dangerous altitude.

I'm now wondering if leaving HLS in this HEEO for many months could be a bad thing as equipment gets higher radiation dose. So now I am thinking of adding a tanker flight to meet HLS and LT on return to add sufficient fuel to go to a lower parking orbit. This would also solve the issue of Dragon not having to go to high orbit for astronaut return. What would be a desirable long term parking orbit?

[Twark_Main]

The West took a very "maximalist" approach to assembly robots, utilizing significant industrial prowess. See Canadarm1/2/3, CanadaHand, etc. The Soviets took a more low-tech approach, see for example the Strela crane system that was used during the assembly of Mir and the Russian segment of the ISS.

https://en.wikipedia.org/wiki/Strela_(crane)

However usually in space it's simpler to design a specialized end effector and then simply bolt it to the ship. Now we call it a "deployment mechanism" and not a robot.    Even if this also requires adding protective doors or panels for launch, this is usually what's done.


Going from HEEO to a low circular orbit is free if your spacecraft can withstand a little heating. Aerobraking doesn't produce nearly as much peak heating as reentry, so even HLS or other Starships without heat shields can do it. On most satellites, it's the fragility of the solar panels that limits the amount of aerobraking achievable on each perigee pass.

[crandles57]

I submitted two almost identical projects one for a circular orbit of 500km and the other for 3000km circular. The 3000km had mGy and mSv values 2 to 3 orders of magnitude higher at 3k vs 500 so I take it that 3000km is a dangerous altitude.

I'm now wondering if leaving HLS in this HEEO for many months could be a bad thing as equipment gets higher radiation dose. So now I am thinking of adding a tanker flight to meet HLS and LT on return to add sufficient fuel to go to a lower parking orbit. This would also solve the issue of Dragon not having to go to high orbit for astronaut return. What would be a desirable long term parking orbit?

Yes I think 3000km is high enough you don't want crew spending too much time there. Polaris Dawn went to apogee of 1400km but didn't stay at that apogee for many orbits. While that was ok adding that radiation dose to a full trip through VAB to moon and back might be too much. So while going up to 1000 or even 1200 km may be ok above that seems likely to be an issue. At these 1000-3000 km altitudes, the higher the the radiation levels and also higher apogee means longer time each orbit at the higher altitudes. Your HLS ship might offer more protection and allow it to go higher before the TLI but the crew have to arrive on dragon. So you might have a choice between having radiation dose risk at higher altitude transfers or refuelling with crew present risk if you transfer crew earlier. Maybe after lots of successful refuellings, the fuel refuelling risk becomes preferable?

You might need a dragon boost trunk to reach 3000km apogee but that is ok as it has already been demonstrated on CRS-33 in August 2025 and maybe the extra performance offered allows you to add extra radiation protection to dragon?

How much would the cargo mass have to be reduced to keep final fuelling in a 1200 * 150km orbit? Or do we need to consider 3 landing ships supported by 2 NRHO ships (a NRHO depot and our NRHO lifeboat/depot?). Either makes it more expensive per Kg mass to surface, but which works out better?

I am calling it a lifeboat/depot rather than lifeboat/tanker because I assume it needs to have some boil off minimisation equipment and also ability to both receive and supply propellants. I assume NRHO to help reduce boiloff caused by being close to moon for a while time during mission.

.

I doubt we will see a 4 arm Optimus variant fitted with a jetpack soon ... but maybe one day

Dracos? Surely too powerful? Cold gas thrusters in a 'jetpack' seem more like it to me.

[Roy_H]

Maybe after lots of successful refuellings, the fuel refuelling risk becomes preferable?

How much would the cargo mass have to be reduced to keep final fuelling in a 1200 * 150km orbit? Or do we need to consider 3 landing ships supported by 2 NRHO ships (a NRHO depot and our NRHO lifeboat/depot?). Either makes it more expensive per Kg mass to surface, but which works out better?

I am calling it a lifeboat/depot rather than lifeboat/tanker because I assume it needs to have some boil off minimisation equipment and also ability to both receive and supply propellants. I assume NRHO to help reduce boiloff caused by being close to moon for a while time during mission.

Dracos? Surely too powerful? Cold gas thrusters in a 'jetpack' seem more like it to me.

Since I am suggesting 27 fuelings per moon mission, and it will be several missions before astronauts are aboard, I think the risk of a fueling mishap will be very low. There will be lots of experience with it.

Well, I suppose a Depot might be a better description, I just have this earth bound mind set that Depots don't move around like tanker trucks do. All variants will have to transfer fuel either way, and I think it would be a good idea to include HLS in that. There might be an emergency situation where crew needs to transfer to Lifeboat and moving some fuel back to the Lifeboat could be desirable.

From what I understand SpaceX is already planning on MLI and solar panel active cooling for both HLS and NHRO tanker, so yes, boil off mitigation is already addressed.

Yeah, you are right, Dracos would be too powerful.

Twark_Main, No I do not think Aerobraking is an option as the ships will have solar panels and MLI wrapping.

I'm still trying to think of what would be the most desirable parking orbit, high enough not to worry about decay for a year, and in order to not waste energy, it should still be elliptical with perigee of 200km, so maybe 600km x 200km? This would keep it out of drag area most of the time and make it easy for Dragon to dock. Do you agree?

[Twark_Main]

Twark_Main, No I do not think Aerobraking is an option as the ships will have solar panels and MLI wrapping.

These are both "bog standard" features on regular satellites, and regular satellites were the first vehicles to demonstrate aerobraking.

I'm still trying to think of what would be the most desirable parking orbit, high enough not to worry about decay for a year, and in order to not waste energy, it should still be elliptical with perigee of 200km, so maybe 600km x 200km? This would keep it out of drag area most of the time and make it easy for Dragon to dock. Do you agree?

To reduce the orbits decay from drag, the best way is to increase the perigee altitude. So you might go to a perigee of 300 or 350 km instead of 200 km.

[crandles57]

Twark_Main, No I do not think Aerobraking is an option as the ships will have solar panels and MLI wrapping.

I'm still trying to think of what would be the most desirable parking orbit, high enough not to worry about decay for a year, and in order to not waste energy, it should still be elliptical with perigee of 200km, so maybe 600km x 200km? This would keep it out of drag area most of the time and make it easy for Dragon to dock. Do you agree?

600*200 does sound sensible to me but that might not mean much. Might even get away with 700*200 or 800*200. What concerns me is how you get there. You want one rapid transit through VA belts.

Perhaps solar panels can be rolled up or folded and the MLI made robust enough that you could do some light aerobraking without much heating by doing several passes through high atmosphere slowly lowering apogee on each pass but this means several passes through VA belts which is not at all what we want for crew.

Do you do TEI burn to put you in a 200,000*75km earth orbit. Then do retro burn at latest time possible to complete before reaching 100km to put you in something like 50,000*70 km orbit? Use positive lift to adjust perigee up to 90km+ then use negative lift to keep you at 90km altitude for longer in order to scrub off more speed than just a quick trip down to 90km? Leave atmosphere in something like 2000*90km orbit and on way up to apogee propulsively adjust to 600*200 km orbit.

I really have no idea if that is the sort of profile you want or if it is possible. How should it be done?

[Roy_H]

What concerns me is how you get there. You want one rapid transit through VA belts.

No, I do not think that is doable. To keep fuel requirements low, has to go to the 3k x 200 orbit first. Then a tanker visits and supplies enough fuel to go to a lower orbit like my proposed 600 x 200. Hopefully just 2 or 3 orbits to refuel and burn to a lower orbit.

Can't wait for multiple passes for aerobraking as the astronauts must be in radiated area for shortest possible time and the plan is to get to 600 x 200   500km circular for Dragon to visit.

Turns out we can be sloppy. Upon arriving back at 3k x 200 orbit, a single Starship Tanker can deliver more than enough fuel for both HLS and Lifeboat Tanker to go to a 500km circular orbit unload astronauts, loiter for 1 year and still have excess fuel to lower themselves to a 200km x 200km orbit for the next mission.

[InterestedEngineer]

Twark_Main, No I do not think Aerobraking is an option as the ships will have solar panels and MLI wrapping.

https://www.universetoday.com/articles/foldable-solar-sails-could-help-with-aerobraking-and-atmospheric-reentry

[Roy_H]

Twark_Main, No I do not think Aerobraking is an option as the ships will have solar panels and MLI wrapping.

https://www.universetoday.com/articles/foldable-solar-sails-could-help-with-aerobraking-and-atmospheric-reentry

Interesting application. But this example shows designed for high strength aerobraking and release as stresses get too high.

I originally took Twark_Main's proposal to be high stress to  aerobrake in one or two orbits. The alternative given the fragility of solar panes and MLI would be a large number of passes with gentle braking. But this would have astronauts being subjected to Van Alan Belt radiation much longer than necessary.

Fuel is cheap. SpaceX has applied to drill 5 gas wells on their own property at Starbase. They are building a factory to remove Oxygen and Nitrogen from the air. They are planning on a large solar field to power all this. High capital expense, yes, but after all this is accomplished fuel will be very low cost. Starship Tankers will be re-used, so only launch costs and hopefully minimal refurbishment.

[Roy_H]

Latest plan now revised to eliminate time astronauts in Dragon have to spend in Van Alan Belt.

As before initial flight preparation takes place at 200km circular orbit.
No Dragon flight required to outfit HLS and LT (Lifeboat Tanker) with solar panels, radiators, and MLI as this can be done robotically.
Change is that astronauts board HLS at this orbit so Dragon doesn't have to spend time in Van Allan Belt. The HLS is equipped with much higher radiation shielding than Dragon.
HLS and Lifeboat Tanker fly to 3000km x 200km HEEO. There they get topped off via additional Starship Tanker flight.
HLS and Lifeboat Tanker fly to Moon as before and return to HEEO.
One more Starship Tanker flies to HEEO and adds as much fuel as it can carry. This turns our to be comfortably more than required to descend to 500km circular orbit, remain there for a year or more and still have fuel to descend to 200km circular orbit for next mission.
In both cases launching to the Moon and returning, it is desirable to spend as little time in the HEEO orbit as possible even though high shielding makes it safe. So hopefully fuel top-off can be accomplished in 2 or 3 orbits.
Astronauts transfer to Dragon in 500km circular orbit and perform EDL.
New updated mission profile diagram attached.

[Roy_H]

Asked Grok to produce a graph showing radiation levels at various altitudes. Should have done this long ago. So 3,000km turns out to be beyond the middle of the inner Van Allan Belt. Note scale distortion on upper end as I was only concerned with up to 3,000km.

[crandles57]

Can MLI be applied before launch? Why is depot white as opposed to grey steel of lander and tanker?

https://ntrs.nasa.gov/api/citations/20250008727/downloads/IAC%2025%20B3%201%20v3.pdf

[Twark_Main]

Asked Grok to produce a graph showing radiation levels

How can we be sure this isn't wholly hallucinated?

Can Grok produce a source?

[crandles57]

Asked Grok to produce a graph showing radiation levels at various altitudes. Should have done this long ago. So 3,000km turns out to be beyond the middle of the inner Van Allan Belt. Note scale distortion on upper end as I was only concerned with up to 3,000km.

Some Grok comments

Inner Belt (1,000-6,000 km): Sharp peak around 3,000-4,000 km, where dose rates can reach 10-20 rad/hour or higher. This is the most hazardous for prolonged exposure due to penetrating protons.
Slot Region (6,000-13,000 km): Lower radiation (~0.1-1 rad/hour), acting as a "gap" between belts.
Outer Belt (13,000-20,000+ km): Broader peak around 15,000-17,000 km, with dose rates ~5-10 rad/hour at max. Levels taper off more gradually.
Beyond 30,000 km: Negligible belt radiation; reverts to background GCR levels.
Variability: During solar storms, levels can increase by factors of 10-100. Shielding (e.g., 25 g/cm²) can reduce inner belt peaks to ~5 rad/hour.
Human Relevance: Quick transits (e.g., Apollo missions) result in low total doses (~0.1-1 rad total), but satellites or long stays require heavy shielding.

refs used include
https://pubmed.ncbi.nlm.nih.gov/12056428/

The flux of energetic protons in the maximum intensity zone of the inner Van Allen belt is by about four orders of magnitude higher, their energy and penetration power, of course, lower. A shield of 25 g/cm2 would reduce the dose rate from 20 rad/hour under 2 g/cm2 to 5 rad/hour.

also
https://spacemedicineassociation.org/download/history/ (1959 PDF)
image attached

.

Anyway:
3,000*200km means passing through the inner belt peak twice each orbit. For long RPOD operations it looks like it might be better to go to something like 7,000*4,000km orbit. The extra delta-v cost of doing this might not be worth it if RPOD operations don't take long and you have sufficient shielding.

[Roy_H]

Anyway:
3,000*200km means passing through the inner belt peak twice each orbit. For long RPOD operations it looks like it might be better to go to something like 7,000*4,000km orbit. The extra delta-v cost of doing this might not be worth it if RPOD operations don't take long and you have sufficient shielding.

No, I believe we have arrived at the sweet spot. The higher orbit just means more fuel tankers and I just don't think the radiation issue is that important.

This mission profile uses almost the same equipment that SpaceX is building for Artemis as they are planning on adding a tanker to refuel at Gateway. The only changes I have added are the lifeboat part of the tanker and the 50 tons of PE radiation shielding on the HLS and 10 tons of PE shielding on the Lifeboat Tanker. In my searches about NASA for MLI, I think I read that this was planned for HLS, so I assumed it is planned for the tanker as well. In any case the addition of 50 tons of PE may seem extravagant as the existing plan is to build a radiation shelter where the astronauts can huddle during the worst parts of the mission. But I figured that if it could be accommodated in the mass budget, what the hell, why not give the astronauts the freedom to go about their work at all times and live in an environment where their total exposure will be less. This makes the several orbits in the HEEO through the Van Allan Belt of minimal concern.

Another thing that I only realized lately is that I have assumed that the astronauts and payload to moon's surface would all be in one ship. Now I understand that the Artemis plan is for HLS to carry astronauts and a separate cargo version of HLS to deliver 1 ton payload. Splitting up these functions would allow a somewhat lower HEEO orbit, but not enough to make any difference in terms of radiation exposure. So the mission as I have described would be much cheaper than sending two different ships to the moon.

So how realistic is a goal of say only 1 orbit, about 2.5 hours, in HEEO to re-fuel? The Starship Tanker could be timed to arrive at the HEEO orbit at the same time, or even before the HLS does. The Lifeboat Tanker could stay for a 2nd orbit. It would just arrive at LLO a few hours later.

I want to thank all those who have contributed to this interesting thread, even those from the original thread where I got some ideas from. I believe we have arrived at a very desirable and doable plan for supporting a moon base. What are the chances of SpaceX actually reading this thread and giving it serious consideration?

[Roy_H]

I think all this could be done under the existing Artemis contract.
The initial HLS could be scrapped as intended in the demo mission.
The second one used to fulfill Artemis III contract, as it does not require the 100t payload and the detour to NRHO would consume less fuel than saved by no payload.
This would allow the HLS and LT to return to LEO as planned and the HLS could be re-supplied, refurbished if necessary in LEO and sent back to NHRO for Artemis IV.

My whole point is that the modifications and additional costs such as adding the lifeboat part to the tanker could be done within the existing Artemis contract budget by eliminating the building of a 3rd HLS and fulfill all the Artemis contract goals.

[crandles57]

New updated mission profile diagram attached.

I think you want to launch HEEO depot, 4 tankers, refuel HEEO depot, send HEEO depot and lifeboat depot to the 3000*200 orbit and refuel the lifeboat tanker (and maybe send lifeboat depot onwards to get it out of the way) before launching astronauts in dragon. This is to save time in VAB for astronauts by the fuel depot being there ready and waiting to refuel them as fast as possible.

It would be cheaper and easier to apply MLI and solar panels to body of lunar ships if this can survive launch.

~150 km circular orbit might be better for tanker to depot fuelling than 200km.

It is just confusing not using the depot terminology that others are using.

[Roy_H]

Not much change here. Just thought I would consolidate some things spread out over several posts and correct an error in calculation. Yes, I depend too much on Grok, just have to make sure my questions are worded properly. Turns out the Lifeboat Depot can be a little smaller, and I included the option of a larger Lifeboat Depot (LD) to reduce time astronauts spend in Van Allan Belt.

Mission Objectives:

1, Most fuel efficient - no detour to NHRO, minimum fuel for Lunar landing and accent.

2. Deliver 100 tons payload to Lunar surface.

3. Provide radiation protection for astronauts to NASA recommendation.

4. Make all hardware re-useable, hardware is expensive, fuel is cheap.

5. Provide lifeboat alternative if prop transfer at LLO fails. HLS and Depot tanker can dock nose-to-nose. Failing that EVA transfer could be possible.

Depot tanker has Orion sized crew quarters in nose as lifeboat for emergency. HLS and lifeboats have PE radiation shielding (for entire living area, not just shelter) to minimum NASA guideline. I don't know enough about space craft construction, but I assume crew quarters have double hull. I envision this to be 14 cm apart and filled with Poly Ethelene This would also provide extra protection to small debris that might punch through the outer hull. I have allotted 50 tons PE on HLS and 10 tons on Lifeboat Depot, LD.

HLS and LD each have 3 gimbaled vac Raptors, no sea level Raptors. I do not know the dry mass, so these calculations are based on a dry mass for HLS of 120 tons + 50 tons PE for a total of 170 tons. The LD is 95 tons + 10 tons for crew quarters and 10 tones for PE. I believe these estimates to be very conservative.

Edit: Another assumption. Fuel is kept at 95°K to 100°K, CH4 at 1 Bar, O2 at 6 Bar. Both liquid under this condition.

Initial HLS launch includes 100 ton payload. Subsequent missions would have HLS payload delivered by Starship in 200km circular orbit.

Two variations on LD, the minimal one would have 1,240 ton capacity for fuel and require a fuel too-op for HLS and LD on return to HEEO. A larger 1,535 ton version would allow returning ships to avoid HEEO and go directly to a 500km circular orbit.

Mission Profile:

1. launch HLS, Lifeboat Depot, and cargo Starship to 200km LEO.

2. Robotics are used to remove supplies from Starship and assemble solar panels, radiator, and MLI shielding on HLS and Lifeboat Depot.

3. LD and HLS are fully fueled by 20 Starship Tankers. Assuming 150t fuel delivered per flight. 16 flights for filling at 200km LEO and an ST with 3 more ST flights adding fuel to it would fly to HEEO to top off HLS and LD. The larger Depot option would require 2 more flights for LEO fills and 1 more for HEEO fill.

4. Top up ST flies to 3,000km x 200km HEEO and waits for LD and HLS.

5. Dragon delivers astronauts to HLS. Dragon performs EDL to Earth.

6. LD flies to HEEO and spends two obits there being topped up by the waiting ST. They would mate at Apogee spend the portion through Perigee loading the fuel, and undock at Apogee.

7. LD performs TLI to LLO at 100km altitude. Polar orbit.

8. HLS flies to HEEO and performs same fuel top up orbit. The value in this sequence is to minimize time astronauts spend in Van Allan Belt, and be assured that LD is successfully on the way.

9. HLS performs TLI to LLO at 100km altitude. Polar orbit.

10. LD adds 62 tons fuel to HLS in LLO.

11. HLS performs Moon landing remains for about 2 weeks and unloads 100t cargo.

12. HLS returns to LLO and receives 205 tons fuel to HEEO or 363 tons fuel for return to 500km LEO.
 
13. LD and HLS return to HEEO.

14. One more Starship Tanker meets HLS and LD adding fuel to enable them to go to 500km circular orbit and later to 200km circular.

15. HLS and LD descend to 500km circular orbit.

16. Astronauts transfer to Dragon for EDL to Earth.

17. Lifeboat Depot and HLS remain in orbit for future missions. When required they will return to 200km altitude for fuel and cargo for next mission.

[crandles57]

Found this re SpaceX's suggestion for Final Tanking Orbit 'FTO'.

https://danielmarin.naukas.com/files/2024/12/Technical-Annex.pdf

Medium-Earth Orbit/High-Earth Orbit/Final Tanking Orbit. 
Missions beyond LEO will also require space station operations in medium-Earth orbit (“MEO”) to high-Earth orbit (“HEO”).  For example, crewed lunar missions will include a secondary propellant transfer in MEO/HEO, the Final Tanking Orbit (“FTO”).  Operations in MEO/HEO will occur in an elliptical orbit of 281 km x 34,534 km and an altitude tolerance of +116,000/-24,000 km apogee and +/- 100 km perigee, with inclination between 28 and 33 degrees (+/- 2 degrees). 

So it seems SpaceX isn't considering less than 181*10000 km as the FTO.

[Roy_H]

So it seems SpaceX isn't considering less than 181*10000 km as the FTO.

No, I wouldn't take that as a limit. It is good to see that they are considering taking the HLS back to Earth orbit for re-use instead of leaving it in NHRO and re-suppling there. If they go through the same optimizing process I did, they will come to the same conclusion.

Namely don't take any more fuel to Moon's surface then you have to. Have a depot in LLO to re-fuel for home trip.
It's just foolish to take the fuel required to return to any orbit around Earth, in this case their MEO to the moon surface and back to LLO.

Once you have made that decision, going to the 200km x 3,000km orbit I recommend results in the accompanying Depot to be about the same size as HLS. If you choose a higher orbit such as they have the accompanying tanker gets smaller, until at their 34,534km orbit, it is not needed at all. But it becomes much more difficult and costly to re-supply and re-fuel in that high orbit. You want to do as much of that in 200km circular as possible. Choosing a lower HEEO such as 200km x 2,000km results in a larger accompanying Depot, with no advantage until you choose an orbit below the Van Allan Belt at which point as my earlier attempts show, require either a monster Depot or two Depots. What I have arrived at is the sweet spot. I think they will too.

[crandles57]

So it seems SpaceX isn't considering less than 181*10000 km as the FTO.

No, I wouldn't take that as a limit. It is good to see that they are considering taking the HLS back to Earth orbit for re-use instead of leaving it in NHRO and re-suppling there. If they go through the same optimizing process I did, they will come to the same conclusion.

Namely don't take any more fuel to Moon's surface then you have to. Have a depot in LLO to re-fuel for home trip.
It's just foolish to take the fuel required to return to any orbit around Earth, in this case their MEO to the moon surface and back to LLO.

Once you have made that decision, going to the 200km x 3,000km orbit I recommend results in the accompanying Depot to be about the same size as HLS. If you choose a higher orbit such as they have the accompanying tanker gets smaller, until at their 34,534km orbit, it is not needed at all. But it becomes much more difficult and costly to re-supply and re-fuel in that high orbit. You want to do as much of that in 200km circular as possible. Choosing a lower HEEO such as 200km x 2,000km results in a larger accompanying Depot, with no advantage until you choose an orbit below the Van Allan Belt at which point as my earlier attempts show, require either a monster Depot or two Depots. What I have arrived at is the sweet spot. I think they will too.

Isn't the problem with LLO that you get lots of reflected radiation off the moon and a small sunshade is unlikely to cope unless it completely surrounds vehicle so boil off is a big problem? Hence suggested use of NRHO to get the prop store further from the moon?

200*3000 km means you pass slowly through the inner VAB peak at about 2000km. Using 200*10000 means you pass more quickly through those high risk altitudes. The orbit also takes longer which gives you more time to complete RPOD for astronaut transfer allowing fewer orbits and hence passes through inner belt peak before TLI.

[Robotbeat]

Note SpaceX will doubtless want margin for initial crewed missions and to avoid an additional tanking event before bringing crew home.
I agree in the long term it makes sense as an optimization. But in the near term, tanker launches are relatively cheap.

[Roy_H]

Isn't the problem with LLO that you get lots of reflected radiation off the moon and a small sunshade is unlikely to cope unless it completely surrounds vehicle so boil off is a big problem? Hence suggested use of NRHO to get the prop store further from the moon?

200*3000 km means you pass slowly through the inner VAB peak at about 2000km. Using 200*10000 means you pass more quickly through those high risk altitudes. The orbit also takes longer which gives you more time to complete RPOD for astronaut transfer allowing fewer orbits and hence passes through inner belt peak before TLI.

The sun shade does completely surround the cylindrical part of the rocket in both cases. There is the addition of the solar cells and active cooling. Assuming that the landing spot chosen, the solar cells will not be in shadow and the expectation is zero boil off for both HLS and LD. Since boil off is not a problem the slight savings going to NHRO is irrelevant.

I agree on the statement about the higher HEEO where the HLS passes quickly through Van Allan Belt. However, the 3,000km orbit only goes into the lower belt whereas the higher orbit goes through both belts. Astronauts have to go through the VABs to get to the moon and back so we are arguing about increased amount. How many orbits will the HLS spend in the higher 34,500km elliptical orbit? In my plan, I think it can be down to 4, 2 going and 2 returning.

However, I grant that it is a fair argument. In my plan I have added a significant amount of radiation shielding, and we don't know how much SpaceX is planning on. If the shielding is minimal, then I agree the higher orbit will be better for the astronauts at the expense of more difficult fuel transfer to that higher orbit. Unfortunately they don't go into details, but I would expect that fueling could be done in a single orbit and then the HLS could go to an LEO circular such as my 500km choice. This would result in much lower time in the Van Allan Belts.

I am very pleased that SpaceX is considering an option to bring the HLS back to LEO for re-use no matter how it is done.

[Roy_H]

Note SpaceX will doubtless want margin for initial crewed missions and to avoid an additional tanking event before bringing crew home.
I agree in the long term it makes sense as an optimization. But in the near term, tanker launches are relatively cheap.

I am not sure I understand your argument. Any mission that includes bringing the HLS back to Earth orbit will require re-fueling. How is this "margin" to be accomplished? The standard fuel margin is 5% and that has been accounted for in my proposal.

[Roy_H]

I did another quick estimate of fuel requirements for another variation and will qualify this as a rough estimate as I did not give Grok all the finer details. However. in this one I specified that HLS would be fully fueled in a 800km circular orbit (below Van Alan Belt), and LD fully fueled in 4000km x 200km orbit (no astronauts so no radiation problem). As before HLS has two fuel transfers in LLO, before and after moon landing. This time the HLS returns directly to 500km circular orbit and LD returns to 4000km x 200km for additional fuel to return to 500km circular. This requires the LD to be about 1350 ton capacity. I did not ask for how many ST flights required.

This plan retained my requirement of 50 tons PE shielding and 100 ton payload to Moon surface. It has the benefit that HLS does not have to spend any extra orbits in Van Allan Belt. Astronauts would board the HLS at 200km orbit as before from Dragon. I think it is best to plan on Dragon performing EDL and being re-launched to pick up crew on return. That way the Dragon can be launched to match whatever orbit timing and inclination the HLS returns to at 500km.

[crandles57]

The orbital period for a satellite in a 200 x 10000 km altitude Earth orbit is approximately 3.4 hours.
The orbital period for a satellite in a 200 x 3000 km altitude Earth orbit is approximately 1.84 hours.

Are those periods correct?

I am not sure 3.4 hours is enough for elliptical orbit insertion burn, POD for docking, hatch opening, astronaut transfer, hatch closing, detach dragon, and TLI burn at perigee. However, 1.84 hour period seems likely to involve a few orbits?

>"How is this "margin" to be accomplished?"
If you fully refuel in 200*10000 then you need less from there to moon than if you are in 200*3000 km orbit. Yes it does take more tanker launches to get fully fuelled in 200*10000 orbit than in 200*3000 km orbit. Maybe this is a price worth paying early on for extra fuel safety margin and reduced radiation dose for astronauts during transfer time (or in refuelling time if the astronauts are transferred at lower altitude) is also a factor in favour? Probably also reduces refuelling time and launches for way back down if not eliminating it?

>"However, the 3,000km orbit only goes into the lower belt whereas the higher orbit goes through both belts"
200*10000 doesn't go though the higher belt but I accept that 200*~30k km does go through both.

[Roy_H]

I am not sure 3.4 hours is enough for elliptical orbit insertion burn, POD for docking, hatch opening, astronaut transfer, hatch closing, detach dragon, and TLI burn at perigee. However, 1.84 hour period seems likely to involve a few orbits?

>"How is this "margin" to be accomplished?"
If you fully refuel in 200*10000 then you need less from there to moon than if you are in 200*3000 km orbit.

Your link makes no mention of a 200*10000 km orbit, only 281km * 34,534km. Also it only mentions refueling, no mention of astronauts transferring from Dragon. That orbit is 10 hours and 8 minutes. Lots of time to refuel, so I would expect one orbit going up and one coming back. HLS has lots of lift capacity to include extra shielding. You do not want to send Dragon through the Van Alan Belt if it can be avoided. Also the inner belt is far more dangerous than the outer belt.

I agree that there are many trade-off scenarios and the one suggested in your link makes me believe that orbit is only for refueling, not astronaut transfer, and probably does not require refueling in LLO. Too many unknowns.

[crandles57]

Your link makes no mention of a 200*10000 km orbit, only 281km * 34,534km. Also it only mentions refueling, no mention of astronauts transferring from Dragon. That orbit is 10 hours and 8 minutes. Lots of time to refuel, so I would expect one orbit going up and one coming back. HLS has lots of lift capacity to include extra shielding. You do not want to send Dragon through the Van Alan Belt if it can be avoided. Also the inner belt is far more dangerous than the outer belt.

I agree that there are many trade-off scenarios and the one suggested in your link makes me believe that orbit is only for refueling, not astronaut transfer, and probably does not require refueling in LLO. Too many unknowns.

Found the document shown at
https://danielmarin.naukas.com/files/2024/12/Technical-Annex.pdf

Medium-Earth Orbit/High-Earth Orbit/Final Tanking Orbit. 
Missions beyond LEO will also require space station operations in medium-Earth orbit (“MEO”) to high-Earth orbit (“HEO”).  For example, crewed lunar missions will include a secondary propellant transfer in MEO/HEO, the Final Tanking Orbit (“FTO”).  Operations in MEO/HEO will occur in an elliptical orbit of 281 km x 34,534 km and an altitude tolerance of +116,000/-24,000 km apogee and +/- 100 km perigee, with inclination between 28 and 33 degrees (+/- 2 degrees). 

34534-24000=10534 but I rounded this down to 10000km apogee. So it sort of does mention it, admittedly only as an extreme of the range.

I think you are trying to do more mass than they are. This possibly makes your lower elliptical refuelling orbit seem strange but perhaps it is explained because they are building in more fuel safety margin and less mass for first few attempts to avoid refuelling in LLO and on return journey?

[Roy_H]

34534-24000=10534 but I rounded this down to 10000km apogee. So it sort of does mention it, admittedly only as an extreme of the range.

I think you are trying to do more mass than they are. This possibly makes your lower elliptical refuelling orbit seem strange but perhaps it is explained because they are building in more fuel safety margin and less mass for first few attempts to avoid refueling in LLO and on return journey?

Absolutely true. I have taken the highest possible mass (worst case condition) quite deliberately as anything less will require less fuel, and I expect they are not. But all I think this shows is that they are considering refueling in some high orbit (huge range possible) and we cannot make many conclusions on what mass, or how much fuel.

I suspect that my latest variation will require more fuel, but I should probably go to the effort to find out. I do find it interesting that SpaceX does consider at least one extra pass through the Van Allan Belts acceptable as a price to bring HLS back to LEO. Although initial mission will be crewless, follow on will be crewed.

[Twark_Main]

So what's the cost per seat (and per ton) again?

[DanClemmensen]

I suspect that my latest variation will require more fuel, but I should probably go to the effort to find out. I do find it interesting that SpaceX does consider at least one extra pass through the Van Allan Belts acceptable as a price to bring HLS back to LEO. Although initial mission will be crewless, follow on will be crewed.

I'm sorry, but I do not recall seeing any mission of this type described by SpaceX. We have a lot of speculation here on our forums which include such a mission, but the NASA HLS contract NextSTEP appendix H, Option A, and the extension to Option B) do not require a return of an HLS to LEO. If you have it, please provide a reference to a SpaceX proposal to return HLS to LEO.

[Roy_H]

I guess I need to clarify that this is not an official SpaceX plan, only a possibility.
Ok, again according to Grok.
LD has to be only 705 ton fuel capacity.
LD gets filled at 200km orbit, 5 ST flights.
LD burns to 10,000km x 200km orbit and gets topped off with 4 more ST flights (one gets partially filled from 3 more at 200km orbit then it flies to 10,000km x 200 km orbit to top off LD).
LD performs TLI to LLO
HLS is filled at 200km orbit, 8 ST flights.
Dragon meets HLS and astronauts transfer. Dragon performs EDL.
HLS flies to 800km circular orbit (below Van Allan Belt)
One more ST flight to top off HLS.
HLS performs TLI to LLO and gets fuel from LD to perform lunar landing payload drop off and return to LLO.
HLS gets more fuel from LD.
HLS returns to 500km circular Earth orbit.
LD returns to 5,000km x 200km HEEO
one more ST flight to LD adds fuel to return to 500km circular and later to 200km circular.
Dragon flies to HLS to return astronauts to Earth.

So this plan actually reduces the number of ST flights to 19 while the astronauts only have to pass through the Van Alan Belts once each direction.

One more Starship flight to 200km orbit is required outside of this basic flight plan. To deliver up to 100 ton payload or on initial flight to deliver add-ons to HLS and LD, namely MLI and active cooling solar panels and radiators. Of course this only has to be done once and the initial payload will be less than 100t leaving room for add-ons.

One less ST flight to 200km orbit is required on initial mission as HLS and LD arrive with residuals in their tanks.

[Roy_H]

I suspect that my latest variation will require more fuel, but I should probably go to the effort to find out. I do find it interesting that SpaceX does consider at least one extra pass through the Van Allan Belts acceptable as a price to bring HLS back to LEO. Although initial mission will be crewless, follow on will be crewed.

I'm sorry, but I do not recall seeing any mission of this type described by SpaceX. We have a lot of speculation here on our forums which include such a mission, but the NASA HLS contract NextSTEP appendix H, Option A, and the extension to Option B) do not require a return of an HLS to LEO. If you have it, please provide a reference to a SpaceX proposal to return HLS to LEO.

I'm sorry if I implied that this was in planning stages. This is just my speculation based on SpaceX requesting permission to fly HLS to Medium Earth Orbit for re-fueling.

[DanClemmensen]

I suspect that my latest variation will require more fuel, but I should probably go to the effort to find out. I do find it interesting that SpaceX does consider at least one extra pass through the Van Allan Belts acceptable as a price to bring HLS back to LEO. Although initial mission will be crewless, follow on will be crewed.

I'm sorry, but I do not recall seeing any mission of this type described by SpaceX. We have a lot of speculation here on our forums which include such a mission, but the NASA HLS contract NextSTEP appendix H, Option A, and the extension to Option B) do not require a return of an HLS to LEO. If you have it, please provide a reference to a SpaceX proposal to return HLS to LEO.

I'm sorry if I implied that this was in planning stages. This is just my speculation based on SpaceX requesting permission to fly HLS to Medium Earth Orbit for re-fueling.

OK, but please try to be more precise in your wording. I know that I am probably guilty of this same problem of miss-attributing stuff, but I try to avoid it. In this case you specifically asserted that "SpaceX does consider at least one extra pass through the Van Allan Belts acceptable".  In this era of AI, it is particularly important to avoid making unsupported assertions that  may be propagated.

[Roy_H]

Here I go again, only this time I have included a spread sheet showing all calculations. It is written with Libre Office a free word processing program. https://www.libreoffice.org  It does allow export to an older version of Excel. You are encouraged to download the spreadsheet, and I hope some of you will point out any errors as I am not a rocket engineer and am in way over my head. It is set up so you can put in your own variables.

As before I have chosen HLS dry weight to be 180 metric tons so as to include 50 tons of PE radiation shielding. Also the Lifeboat Depot has 10 tons for lifeboat part and 10 tons for shielding.

This scenario has HLS go to 700km orbit for fuel top off and does not spend any orbits in the Van Alan Belts. However the Lifeboat Depot does spend a few orbits in a very high HEEO for it's fuel top up passing through the Van Alan Belts. Of course, no crew aboard.

Again I have chosen to have HLS and Lifeboat Depot covered with Multi Layer Insulation and have solar panels and radiators for active cooling of fuel. This allows zero fuel boil off.

The Starship Tanker that provides the Lifeboat Depot top off in HEEO returns over many orbits with aerobraking apogee about 75km to conserve fuel. It ends by circularizing at 200km orbit before EDL. I didn't attempt to calculate how much fuel would be saved, but allotted 20% of fuel to attain HEEO for return. I expect this is far more than necessary and possibly one tanker trip could be saved.

Mission Sequence:
1.  Lifeboat Depot and HLS launch to 200km LEO.
2.  A Starship loaded with materials and equipment to outfit HLS and LD with MLI and solar panels joins them.
     These modifications are performed robotically in orbit. Starship returns to Earth.
3.  A total of 12 Starship Tanker flights fill LD and HLS (6 tankers each).
      Since LD and HLS have zero boil off, little time constraint.
4.  One ST files to 200km and is filled with 5 more ST flights adding 150 tons each flight.
5.  LD flies to 120,000km x 200km HEEO.
6.  The partially filled ST flies to HEEO and tops up the LD. ST aerobrakes back to 200km circular, then EDL.
7.  Dragon flies crew to HLS in 200km LEO.
8.  HLS flies to 700km circular orbit. This is well below the Van Alan Belts.
9.  One more ST flies to HLS to top up fuel tanks.
10. LD flies to LLO.
11. HLS flies to LLO.
12. HLS gets 257 tons fuel transfer from LD.
13. HLS performs landing on Moon, stays for mission period typically 1 or 2 weeks, and unloads payload.
14. HLS returns to LLO.
15. HLS gets 377 tons fuel transfer from LD.
16. Both HLS and LD return to 500km circular LEO.
17. Dragon launches to meet HLS to remove crew. (This instead of leaving Dragon in orbit avoids
      problems of Dragon raising itself from 200km to 500km and possibly a different angle orbit if RAAN
      issue appears.
18.  Dragon performs EDL with crew, and HLS and LD remain in orbit for future missions.

I know the biggest objection to this scenario is the 23 ST flights to carry fuel for HLS and LD, but with re-use the cost of this is relatively low (compared to SLS/Orion or any other method that involves disposing of rocket hardware). The fueling trips can be spread out without penalty so as few as 2 ST's could do the job (but 3 would be much better).

[Roy_H]

Stripping everything down to bare minimum, zero radiation shielding, zero payload, gives a flag and footprints mission requiring only 16 Starship tanker trips.

[crandles57]

700 km circular orbit is well below VA belts as you said and dragon can, I think, get there and still land (Polaris dawn went to 1400km not sure about perigee possibly only 190km which is average of near 800km)

Therefore can fully fuel in 700*700 before launching crew so as to reduce crew risk of being present during fuelling.
(Maybe 900*500 or 1000*200 is better to avoid the inefficiency of circularising?)

.

Other issues:

You have another fuelling in LLO of 257 tonnes when the crew are present. Avoiding this would be nice and there seem to be some possibilities:
I see 6 tankers to HLS in 200*200 and one in 700*700 which at 150 tonnes a tanker makes 1050 tonnes (180 tonne dry mass will presumably arrive in orbit nearly empty). However I thought v3 ships could carry 1600t sub cooled or nearly 1500 tonnes (1493t?) at boiling point. So why not add more fuel in LEO and avoid the need for refuelling in LLO if you can? It also reduces the expensive refuelling in 200*120000km.

Using 2 HLS ships would be less design and testing work.

Being able to avoid the refuelling with crew present in LLO by just having the crew transfer to the second HLS would be a less risky approach. Testing out the docking for this in LEO should also be part of the plan.

Why bring both ships back to LEO? Yes it is nice to be able to reuse them, but they will soon be an obsolete design and it might be nicer if you can to land one again on the moon as a starter of a base/crew habitat after the crew have departed for Earth? Not sure if you can do that with sufficient margin, maybe trim 50 tonne shielding so it can make it?

95000 ton dry mass for a tanker sounds far too low for a vehicle that has to do Earth entry and landing, I thought it would be 130 tonnes or even slightly more.
 
I suspect you want an ordinary depot for taking fuel to 200*120000km orbit. This won't have TPS or header tank and will never land but can still be reused for future refuelling campaigns. If you cut out providing fuel pre landing in LLO maybe it doesn't have to be so high?

I have seen nothing to suggest that depot and HLS's MLI will be added in orbit? Not sure why you continue to propose that rather than just adding on the ground before launch? Not sure how solar panels are going to be done however maybe fold sensitive parts inside with sufficiently robust outside covers and mechanism to unfold when in space? 

[DanClemmensen]

700 km circular orbit is well below VA belts as you said and dragon can, I think, get there and still land (Polaris dawn went to 1400km not sure about perigee possibly only 190km which is average of near 800km)

Therefore can fully fuel in 700*700 before launching crew so as to reduce crew risk of being present during fuelling.
(Maybe 900*500 or 1000*200 is better to avoid the inefficiency of circularising?)

The Dragon boost trunk exists and is already proven. If used with Crew Dragon, it should provide at least some additional orbital altitude.

[Roy_H]

700 km circular orbit is well below VA belts as you said and dragon can, I think, get there and still land (Polaris dawn went to 1400km not sure about perigee possibly only 190km which is average of near 800km)

Therefore can fully fuel in 700*700 before launching crew so as to reduce crew risk of being present during fueling.
(Maybe 900*500 or 1000*200 is better to avoid the inefficiency of circularizing?)

.I agree that Dragon transfer crew can easily be done at 700km. I guess I just have an attitude that fuel transfer with astronauts aboard is not a big deal. There will be at least 50 and maybe 100 fuel transfers performed before any are done with crew present.

There is little to zero advantage of Oberth effect for very small differences between apogee and perigee. Entering into Van Alan Belt is not worth it. Compare to the average of the ellipse, average of 1000*200 is 600, so slightly worse than 700 circular.

Other issues:

You have another fuelling in LLO of 257 tonnes when the crew are present. Avoiding this would be nice and there seem to be some possibilities:
I see 6 tankers to HLS in 200*200 and one in 700*700 which at 150 tonnes a tanker makes 1050 tonnes (180 tonne dry mass will presumably arrive in orbit nearly empty). However I thought v3 ships could carry 1600t sub cooled or nearly 1500 tonnes (1493t?) at boiling point. So why not add more fuel in LEO and avoid the need for refuelling in LLO if you can? It also reduces the expensive refuelling in 200*120000km.

If HLS turns out to be able to carry more than 1200 tons fuel then, yes it could be taken advantage of. In my spreadsheet, you can change the fuel capacity of any of the versions. The reason for 1 tanker to 700km is to top off the HLS. No matter how you cut it, this is an advantage vs not doing any top-off. Just having more at 200km will avoid top off at 700km but will ultimately cost more in total fuel use. You can play with the spread sheet and make the HLS fuel tank any arbitrary size and put zero in for top-off.

Using 2 HLS ships would be less design and testing work.

Being able to avoid the refuelling with crew present in LLO by just having the crew transfer to the second HLS would be a less risky approach. Testing out the docking for this in LEO should also be part of the plan.

I'm not quite sure what you are getting at. As Dan has suggested the Depot could be simply a second HLS, but now you are talking about bringing 3 ships to LLO, one HLS just for crew to transfer to while the other is being refueled?

I think you are overly concerned about avoiding fuel transfer at LLO, but I do not see it as possible and still return to LEO. So you think bringing a second HLS to LLO for the single purpose of allowing the crew to transfer there for fueling is worth the expense. Do you think the risk of docking the two HLS's together is significantly less than the risk of HLS docking with the Depot for fuel transfer? Or do you think the risk is not the docking operation, but the actual transfer of fuel? Do you leave the second HLS in orbit around the moon for future use? Not enough fuel to bring it back.

Why bring both ships back to LEO? Yes it is nice to be able to reuse them, but they will soon be an obsolete design and it might be nicer if you can to land one again on the moon as a starter of a base/crew habitat after the crew have departed for Earth? Not sure if you can do that with sufficient margin, maybe trim 50 tonne shielding so it can make it?

An interesting option. As Dan suggests the Depot can be a second HLS, I believe it would have enough fuel to land on the moon, instead of returning to LEO. Why remove the radiation shielding? If the intent is to leave it on the Moon surface for future inhabitation, the radiation shielding is highly desirable. The radiation issue does not go away being on the moon's surface. On second though, no, I have shown the Lifeboat Tanker to be significantly less mass than the HLS, so taking that into account there would not be enough fuel left.

95000 ton dry mass for a tanker sounds far too low for a vehicle that has to do Earth entry and landing, I thought it would be 130 tonnes or even slightly more.

Oops, if you are right recalc has to be done. I did a recalculation using 115 tons and it made no difference to number of total tanker trips. I have made a lot of guesses because I do not know what the mass of either HLS or ST would be.

I suspect you want an ordinary depot for taking fuel to 200*120000km orbit. This won't have TPS or header tank and will never land but can still be reused for future refuelling campaigns. If you cut out providing fuel pre landing in LLO maybe it doesn't have to be so high?

No, I chose the standard ST because it can aerobrake on return. This is a huge advantage.

Cut out fuel pre landing from LLO? How? By removing radiation shielding and payload? Or maybe having significantly larger fuel tanks? Again you are doing cartwheels to avoid fuel transfer with crew aboard. SpaceX launches astronauts to ISS on Dragon and fuels the Falcon 9 while crew are in the Dragon. At first proposal, NASA was horrified at that idea, but ultimately they accepted it, and now it is routine.

I have seen nothing to suggest that depot and HLS's MLI will be added in orbit? Not sure why you continue to propose that rather than just adding on the ground before launch? Not sure how solar panels are going to be done however maybe fold sensitive parts inside with sufficiently robust outside covers and mechanism to unfold when in space?

Admittedly this is just my idea, after all this is just a proposal, I am not claiming that this is SpaceX's plan. However the MLI is up to 50 layers of thin mylar coated with silver or aluminum  and alternate other material thin sheets complete with spacers between each layer. Same system as used on the James Web Telescope. I do not believe this would survive launching. If the MLI has to be added in space, then it makes sense to add the solar panels and radiators there too. It would complicate the design of the LD and HLS significantly to carry them up internally and then extend them.

I don't want to get into trouble claiming that this is already being studied, but I think I read somewhere that NASA has looked at this for the HLS. But I can't remember where, my memory is not perfect, and have no link.

[DanClemmensen]

I'm not quite sure what you are getting at. As Dan has suggested the Depot could be simply a second HLS, but now you are talking about bringing 3 ships to LLO, one HLS just for crew to transfer to while the other is being refueled?

I think you are overly concerned about avoiding fuel transfer at LLO, but I do not see it as possible and still return to LEO. So you think bringing a second HLS to LLO for the single purpose of allowing the crew to transfer there for fueling is worth the expense. Do you think the risk of docking the two HLS's together is significantly less than the risk of HLS docking with the Depot for fuel transfer? Or do you think the risk is not the docking operation, but the actual transfer of fuel? Do you leave the second HLS in orbit around the moon for future use? Not enough fuel to bring it back.

There are two potential failure modes here: 1) the refill operation results in an explosion or other severe damage, with risk to the crew; or 2) refill simply fails for any other reason. my completely unsupported guess is that the first scenario has very low probability, so I would leave the crew in the HLS and try to refill, thus avoiding the need to transfer the crew. Crew only needs to transfer if refill fails.

Plans that bring the other two ships back to LEO are really only there to answer the criticism that those perfectly good ships are expended. If they are cheap and/or obsolete, then expend them. However, the HLS backup ship and the Depot can be used for multiple missions by just refilling and they probably do not become obsolete for these roles. You can also use this mission's backup as the next mission's primary and use a new more modern ship for the backup, thus refreshing them.

[crandles57]

Using 2 HLS ships would be less design and testing work.

Being able to avoid the refuelling with crew present in LLO by just having the crew transfer to the second HLS would be a less risky approach. Testing out the docking for this in LEO should also be part of the plan.

I'm not quite sure what you are getting at. As Dan has suggested the Depot could be simply a second HLS, but now you are talking about bringing 3 ships to LLO, one HLS just for crew to transfer to while the other is being refueled?

I think you are overly concerned about avoiding fuel transfer at LLO, but I do not see it as possible and still return to LEO. So you think bringing a second HLS to LLO for the single purpose of allowing the crew to transfer there for fueling is worth the expense. Do you think the risk of docking the two HLS's together is significantly less than the risk of HLS docking with the Depot for fuel transfer? Or do you think the risk is not the docking operation, but the actual transfer of fuel? Do you leave the second HLS in orbit around the moon for future use? Not enough fuel to bring it back.

I think NASA will be reluctant to accept a plan now that involves crew present during refuelling. I agree that after 100 refuelling, NASA as well as enthusiasts may be much more relaxed about it. So I am suggesting that SpaceX may well be more inclined to currently pitch a plan to NASA that does not involve crew being present during refuelling.

Sending a 3rd ship so they are not present during refuelling is too costly for too little risk reduction. So I am trying to get a simpler option without refuelling being needed above LEO considered.

The 2 HLS ship version involves 1 going to moon and back to LO while the other goes to LO first then receives crew and returns to LEO.

In more detailed, it goes something like:

2 HLS try out nose to nose docking in LEO
Both HLS refuelled to ~1493 tonne boiling point fuel in LEO
Possible additional fuelling in 200*1000km ? for HLS to carry crew to Moon if needed (likely methinks)
Possible additional fuelling in 200*10000 for other HLS called HST (Human Space Transport, as never lands)  (less likely to be necessary?)
HST does TLI and into LO
Dragon takes crew to HLS, maybe boost trunk adds a little speed before undock on way down to perigee where TLI burn is done. (If dragon can boost ISS then boosting HLS seems doable?)

HLS now needs to do TLI and into LO, lunar landing, lunar mission, lunar ascent, and nose to nose dock with HST for crew transfer. As this was already tested, this is hopefully low risk, certainly lower risk than a refuelling in NASA current likely views.

The HST does TEI and propulsive entry to LEO.
Second dragon takes crew back to Earth

Ideally HLS in LO can either stay there for future use? Alternately if it has enough fuel, land on moon to provide a habitat with life support functions on moon, if there is insufficient on this trip maybe it can be done later with some spare fuel on a future trip.

I don't know if this is possible. can you provide spreadsheet in excel format, particularly if that might be able to help me.

If we want a lower risk profile then perhaps SpaceX could/should also propose sending 3 HLS ships to provide redundancy and return 2 of them to LEO and optionally re-land the remaining one on the moon?

[crandles57]

Admittedly this is just my idea, after all this is just a proposal, I am not claiming that this is SpaceX's plan. However the MLI is up to 50 layers of thin mylar coated with silver or aluminum  and alternate other material thin sheets complete with spacers between each layer. Same system as used on the James Web Telescope. I do not believe this would survive launching. If the MLI has to be added in space, then it makes sense to add the solar panels and radiators there too. It would complicate the design of the LD and HLS significantly to carry them up internally and then extend them.

I don't want to get into trouble claiming that this is already being studied, but I think I read somewhere that NASA has looked at this for the HLS. But I can't remember where, my memory is not perfect, and have no link.

I assumed MLI was many layers of thin "foils". I agree this would not survive launch if exposed to winds rushing past during launch ascent. However, I also assume this then has a white coloured aero-protecting layer that is more robust and can survive launch and protects the foils. I have no idea what this outer aero-protecting material would be and would like to know in respect of whether it could survive some light aerobraking or even more intense aerobraking.

[crandles57]

If HLS turns out to be able to carry more than 1200 tons fuel then, yes it could be taken advantage of.

We had this at a presentation



So I think we know it is in the region of 1600 tonnes though that is lift off mass when propellants are subcooled. For caution, someone on the forum converted this to 1493 tonnes at boiling point, I think.

If we can fit in nearly 300 tonnes extra at final tanking orbit, would we still have 257 tonnes more at lunar orbit? I assume probably not, the extra mass uses more fuel to get there but if it turns out to be close then maybe we can shave a little mass off the radiation protection in order to help. 50 tonnes sounds excessive and I am wondering if 20 tonnes or so might be able to provide adequate protection.

[spacenut]

If they could upgrade crew Dragon for a lunar mission, Falcon Heavy expendable could probably get Dragon all the way to the halo orbit.  No need for SLS/Orion.  Then lunar Starship could take it from there.  Still depends on Starship being in full operational mode. 

[Roy_H]

I don't know if this is possible. can you provide spreadsheet in excel format, particularly if that might be able to help me.

[Roy_H]

If we can fit in nearly 300 tonnes extra at final tanking orbit, would we still have 257 tonnes more at lunar orbit? I assume probably not, the extra mass uses more fuel to get there but if it turns out to be close then maybe we can shave a little mass off the radiation protection in order to help. 50 tonnes sounds excessive and I am wondering if 20 tonnes or so might be able to provide adequate protection.

Yes, the 50 ton PE shielding is for the entire crew area. A smaller crew shelter (sleeping area) would be much lighter but then is used only when solar storm or transiting Van Alan Belts.

This would allow the HLS to land on the Moon and return to LLO, but would still have to be re-fueled to return to LEO. I see little advantage, but certainly possible.

[crandles57]

180t HLS ship plus 100t payload might just about get to orbit but with no more than ~5t fuel on board. From what I can make out, I think your spreadsheet assumes it arrives with 150t fuel.

If we can fit in nearly 300 tonnes extra at final tanking orbit, would we still have 257 tonnes more at lunar orbit? I assume probably not, the extra mass uses more fuel to get there but if it turns out to be close then maybe we can shave a little mass off the radiation protection in order to help. 50 tonnes sounds excessive and I am wondering if 20 tonnes or so might be able to provide adequate protection.

Yes, the 50 ton PE shielding is for the entire crew area. A smaller crew shelter (sleeping area) would be much lighter but then is used only when solar storm or transiting Van Alan Belts.

This would allow the HLS to land on the Moon and return to LLO, but would still have to be re-fueled to return to LEO. I see little advantage, but certainly possible.

Re "see little advantage", did you read

https://arstechnica.com/space/2025/11/what-would-a-simplified-starship-plan-for-the-moon-actually-look-like/

I am not the only one saying refuelling with crew on board is likely to be seen as a big issue. Maybe this will change but for now I think this plan with no refuelling after astronauts launch should be one of a range of plans that should be pitched to NASA.

It may well not be the best plan but if crewed refuelling are a good reason for NASA to reject plans then I think this should be there as one of the options to avoid that.

[xvel]

What?

[spacenut]

The grid fins are on the booster.  Why would they say that?  The tiles were accounted for I thought.  Without reuse, it is back to the same as F9/FH and now New Glenn, all of which expend the second stage.  Also, a fuel depot made from a tanker wouldn't have fins or tiles, but probably white paint and maybe solar powered refrigeration equipment. 

[geza]

The grid fins are on the booster.  Why would they say that?  The tiles were accounted for I thought.  Without reuse, it is back to the same as F9/FH and now New Glenn, all of which expend the second stage.  Also, a fuel depot made from a tanker wouldn't have fins or tiles, but probably white paint and maybe solar powered refrigeration equipment. 

It is probably a typoo. Eric Berger knows the subject well. He meant the 4 flaps on the 2nd stage, I am sure.

[Roy_H]

Re "see little advantage", did you read

https://arstechnica.com/space/2025/11/what-would-a-simplified-starship-plan-for-the-moon-actually-look-like/

I am not the only one saying refuelling with crew on board is likely to be seen as a big issue.

From the article:
"There is one relatively straightforward way to cut down on the number of “tanker” launches. For early Artemis missions, SpaceX could use expendable “tanker” Starships rather than landing and reusing them. It is not clear how much this would boost the capacity of Starship, but it likely would be considerable."

Eric Berger seems to think that it takes as much fuel to land a Starship Tanker as it does to launch it to orbit. Or that the 11 tons saved by not having flaps and heat shield is a significant savings. I do not think he understands much about how rockets work. However I am glad to see that someone else is considering the idea that SpaceX can bring astronauts back to LEO via HLS.

It never ceases to amaze me on how people cry over large number of Tanker launches but think nothing of expending space ships as a preferable alternative.

[Roy_H]

I suspect you want an ordinary depot for taking fuel to 200*120000km orbit. This won't have TPS or header tank and will never land but can still be reused for future refuelling campaigns.

I intend to add to my spread sheet calculations showing how much fuel is used to return an ST via aero braking vs a Depot via propulsion to 200km circular. I did ask Grok about this and am posting it's reply:

"Aerobraking Campaign at 75 km Perigee: Orbits and Duration

Switching to a 75 km perigee strikes a good balance—aggressive drag for faster decay while staying within Starship's thermal and structural tolerances (peak heating ~0.5–1 MW/m² per pass, cumulative manageable over fewer cycles). Based on numerical simulation using the standard perigee drag approximation (exponential atmosphere model with NRLMSISE-00-inspired average density ρ ≈ 3.5 × 10^{-5} kg/m³ at 75 km, scale height H ≈ 6.5 km), here's the breakdown for your 120,000 km × 75 km initial HEEO:

Total orbits (passes): ~80
Total duration: ~19–20 days

Key Simulation Details

Assumptions: Constant perigee altitude (maintained via ~0.2–0.3 km/s total apogee corrections for variability); average solar/geomagnetic conditions; Starship β ≈ 2,300 kg/m²; drag modeled as impulsive tangential velocity loss at perigee using the King-Hele integral for exponential atmosphere.

Decay profile:
Initial period: ~4.8 days (slow passes, minimal drag).
Mid-campaign (after ~40 orbits): Apogee ~40,000 km, period ~1.5 days, Δv_drag/pass ~25–35 m/s.
Late phase (last ~20 orbits): Apogee <5,000 km, period <90 min, faster decay but still controlled.

ΔV_drag total: ~2.2 km/s (dissipated passively; equivalent to the energy saved vs. propulsive deorbit).

Phase    Cumulative  Approx.        Apogee              Notes
              Orbits        Days            Altitude (km)

Early        1–20         0–6            120,000            Low drag (~15 m/s/pass);
                                               → 80,000            long waits for phasing if needed.

Mid          21–50       6–12           80,000              Peak efficiency (~30 m/s/pass);
                                               → 20,000            monitor solar activity.

Late         51–80      12–20          20,000              Accelerating decay;
                                               → 200                 increase correction frequency (every 2–3 passes)."

What is not included in the above quote is the previous estimate of 20 tons maximum fuel used.
(tried to use Table function, but couldn't figure out how)

[Roy_H]

I'm not quite sure what you are getting at. As Dan has suggested the Depot could be simply a second HLS, but now you are talking about bringing 3 ships to LLO, one HLS just for crew to transfer to while the other is being refueled?

There are two potential failure modes here: 1) the refill operation results in an explosion or other severe damage, with risk to the crew; or 2) refill simply fails for any other reason. my completely unsupported guess is that the first scenario has very low probability, so I would leave the crew in the HLS and try to refill, thus avoiding the need to transfer the crew. Crew only needs to transfer if refill fails.

Plans that bring the other two ships back to LEO are really only there to answer the criticism that those perfectly good ships are expended. If they are cheap and/or obsolete, then expend them. However, the HLS backup ship and the Depot can be used for multiple missions by just refilling and they probably do not become obsolete for these roles. You can also use this mission's backup as the next mission's primary and use a new more modern ship for the backup, thus refreshing them.

I was thinking on how to prove reliability to in space fuel transfers in a productive way. NASA seems content to allow astronauts to fly to lunar surface on HLS after proving it can land and take off again only once.

As I described before, a stripped down version of HLS and LD would require only 16 tanker flights. SpaceX is already being paid to demonstrate HLS landing on the moon, but for little more than the cost of extra fuel could do this robotically without crew, say 3 times. This would increase the number of fueling operations to 48, could be done in the same time span allotted between Artemis III and Artemis IV and have the benefit of inspecting ships in LEO visually for damage via micro meteorites or other causes. More flights might show up other problems. Sensors inside could monitor total radiation received. 3 moon landings would give more experience on tilt variance. Also the ST that experiences 80 orbits aerobraking is an important part to gain experience in. It would also have to track potential impact with known debris each time while passing through LEO and make corrective changes in path to avoid them, much as ISS and Starlink satellites do now.

48 ST refuelings and 6 for LLO transfers, plus another 22 before astronauts board would bring the total to 66. Would that be enough to make NASA comfortable with fuel transfer while astronauts are aboard? Which is the higher risk, refueling or landing on the Moon?

The whole point of the Lifeboat Depot is if fuel transfer fails at LLO, the crew can transfer to the LD and return to LEO.

I disagree with your assessment that re-engineering HLS to strip out unneeded parts of HLS to create the LD is a big effort. It results in significant mass savings which would have to be made up with more fuel somehow. Tesla almost never goes 2 weeks without some small improvement in their cars. The assembly line is designed to support continuous modification. This is a large part of Elon's ethos, every Starship built is modified based on learnings from previous versions.

[crandles57]

I disagree with your assessment that re-engineering HLS to strip out unneeded parts of HLS to create the LD is a big effort. It results in significant mass savings which would have to be made up with more fuel somehow. Tesla almost never goes 2 weeks without some small improvement in their cars. The assembly line is designed to support continuous modification. This is a large part of Elon's ethos, every Starship built is modified based on learnings from previous versions.

I think this depends what you are talking about. Simply not adding parts like waist thrusters so the LD cannot land on moon quite possibly makes it quicker to build. There will be some extra development time because of different mass distribution but that might be minor.

If you are moving domes forward to carry more fuel and reduce astronaut space, I would guess that is quite a bit more effort and more likely to delay Artemis III. If you are talking about after Artemis III then there is more time to do more development and more things become possible. So we may be talking different timeframes: I am thinking that if Orion is fully built and tested out then there will be stronger argument to use Orion. There seems a narrow window currently to say an all SpaceX starship/dragon approach is simpler and faster as it only requires starship development to be completed whereas SLS/Orion/HLS requires both  starship and Orion development to be completed. So if it is a race reduce what you need done.

So if you want to drop Orion in favour of Starship only, it seems sensible to make the argument now to quickly drop Orion. A consequence being that we are looking for a quick simple safe early moon landing rather than how to do it later.

Regarding development work: If you can never land on moon in the LD then perhaps you don't have to do as much work as having a mock up of the smaller space to check everything is possible. However further test tanks for the larger tanks are likely to be necessary to check they work ok with all the stresses. Maybe that can be done in parallel with all the other work but even if so it only adds unwanted complications if trying to race Chinese to the moon. 

[Roy_H]

If you are moving domes forward to carry more fuel and reduce astronaut space, ...

If you look at the spreadsheet values pictured, you will note that the fuel capacity of the LD is exactly the same as the HLS at 1,200 tons. This is really coincidence more than planning. The way Starships are built, ring by ring, I find it difficult to believe it is a major job to leave a ring or two out. At this rate the LD would actually be shorter than the HLS. Even if it was the same size, just removing the landing thrusters, side air lock, elevator components would result in significant mass (and cost) savings. SpaceX doesn't seem to have a problem extending fuel tank sizes as demonstrated by later versions of Starship.

[crandles57]

If you are moving domes forward to carry more fuel and reduce astronaut space, ...

If you look at the spreadsheet values pictured, you will note that the fuel capacity of the LD is exactly the same as the HLS at 1,200 tons. This is really coincidence more than planning. The way Starships are built, ring by ring, I find it difficult to believe it is a major job to leave a ring or two out. At this rate the LD would actually be shorter than the HLS. Even if it was the same size, just removing the landing thrusters, side air lock, elevator components would result in significant mass (and cost) savings. SpaceX doesn't seem to have a problem extending fuel tank sizes as demonstrated by later versions of Starship.

About that 1200 tons for HLS and LD:

I think we are pretty sure HLS for Artemis III will have 1600 tons fuel at launch. We are less sure about the dry mass but suggestions seem around 130+ tons for a tanker arriving with 150 tons of fuel so the mass fraction is 280/1350. With 1200 ton fuel you can only do  ~280*1200/1350 tons of payload + dry mass yet you have 180 ton dry mass ship (presumably including your 50 ton radiation shielding) and 100 ton payload. You would have to trim that payload to get to orbit with 0 fuel left.

I am also slightly dubious of 130 ton tanker minus TPS, header tanks & fins + 15 ton life support and human occupancy payload + 50 ton radiation shielding + MYI and boil off minimisation + waist thrusters - a couple? of rings is as little as 180 tons.

These are minor nits on the numbers you used which can be fixed by reducing the 100 ton payload which has always seemed nice but excessive to me.

A shorter stubbier HLS makes a lot of sense for lunar landing and ascent. The longer length needed for launch to Earth orbit is wasteful once it has been launched. One way to navigate that is to have the HLS as a 3rd stage but then the problem is when is that substantial development work going to be done? The simpler solution is to accept the standard v3 starship size with 1493 ton boiling point fuel capacity.

Maybe your numbers make more sense than I realise?

[Vultur]

I don't see any reason to have 50 tons of radiation shielding. These aren't multi year missions.

[Roy_H]

I don't see any reason to have 50 tons of radiation shielding. These aren't multi year missions.

From my first posts on page 1: Look at page 32 for table from NASA of recommended radiation shielding for various conditions on this link: https://www.nasa.gov/wp-content/uploads/2020/10/2022-01-05_nasa-std-3001_vol.1_rev._b_final_draft_with_signature_010522.pdf

It gives recommended thickness in water, but PE is marginally more effective. So 15cm of water thickness recommended for beyond earth orbit and < 6 months is equivalent to 14cm of PE. Now I did a very rough calculation for all of crew quarters on HLS, but much less would be required if only for sleeping area as a radiation shelter to be used during radiation storms or transiting Van Alan Belts.

Yes, fewer ST flights for fueling would be required if less shielding is used.

[Roy_H]

About that 1200 tons for HLS and LD:

All of my values for dry mass are just my guess, I have no official source to draw on. Part of the reason I provided the spreadsheet set up so it is easy to put your own values in. It should be noted that the 1,200 tons shown is not at sub-cooled temperature. I have targeted 95°K to 100°k for fuel temperature as both fuels can be the same temperature in liquid form if the CH4 is at 1 bar and the O2 at 6 bar. This is desirable because the tanks share the same bulkhead. This means the HLS and LD tanks would have to be larger than the original 1,200 ton rating at sub cooled temperatures due to fuel expansion.

To the argument that it may not be possible to include 100 tons payload in HLS on initial launch to orbit, I agree this is marginal. However I do not expect the first Moon landing to have a large payload, and subsequent flights will have payload added to the HLS via Starship at 200km LEO.

[Twark_Main]

I don't see any reason to have 50 tons of radiation shielding. These aren't multi year missions.

From my first posts on page 1: Look at page 32 for table from NASA of recommended radiation shielding for various conditions on this link: https://www.nasa.gov/wp-content/uploads/2020/10/2022-01-05_nasa-std-3001_vol.1_rev._b_final_draft_with_signature_010522.pdf

It gives recommended thickness in water, but PE is marginally more effective. So 15cm of water thickness recommended for beyond earth orbit and < 6 months is equivalent to 14cm of PE. Now I did a very rough calculation for all of crew quarters on HLS, but much less would be required if only for sleeping area as a radiation shelter to be used during radiation storms or transiting Van Alan Belts.

Yes, fewer ST flights for fueling would be required if less shielding is used.

This says more about how unrealistic NASA requirements are, or how unrealistic it is to shield the entire habitable volume. 

The correct engineering trade-off should be that taking 1 kg of radiation shielding mass and allocating it differently would give the same number of statistical years of life (based on the overall systems risk analysis) as deleting 1 kg of radiation shielding.

[math needed]

[Roy_H]

I don't see any reason to have 50 tons of radiation shielding. These aren't multi year missions.

From my first posts on page 1: Look at page 32 for table from NASA of recommended radiation shielding for various conditions on this link: https://www.nasa.gov/wp-content/uploads/2020/10/2022-01-05_nasa-std-3001_vol.1_rev._b_final_draft_with_signature_010522.pdf

It gives recommended thickness in water, but PE is marginally more effective. So 15cm of water thickness recommended for beyond earth orbit and < 6 months is equivalent to 14cm of PE. Now I did a very rough calculation for all of crew quarters on HLS, but much less would be required if only for sleeping area as a radiation shelter to be used during radiation storms or transiting Van Alan Belts.

Yes, fewer ST flights for fueling would be required if less shielding is used.

This says more about how unrealistic NASA requirements are, or how unrealistic it is to shield the entire habitable volume. 

The correct engineering trade-off should be that taking 1 kg of radiation shielding mass and allocating it differently would give the same number of statistical years of life (based on the overall systems risk analysis) as deleting 1 kg of radiation shielding.

[math needed]

If I interpret your statement correctly, you are recommending shielding that would be 50% effective, that is half way between levels we get on Earth to the level of no shielding in space. I suspect that is more shielding than you think, and a lot more than NASA's recommendations.

In terms of how unrealistic, it is simply how many dollars you want to spend for crew protection. Cost of a few more ST flights plus the cost of the PE shielding. What I have shown is that it does not cost so much in mass that the mission cannot be performed. I have no objection if the astronauts feel it is excessive and they want less shielding. If you were flying, how much shielding would you want?

[Twark_Main]

I don't see any reason to have 50 tons of radiation shielding. These aren't multi year missions.

From my first posts on page 1: Look at page 32 for table from NASA of recommended radiation shielding for various conditions on this link: https://www.nasa.gov/wp-content/uploads/2020/10/2022-01-05_nasa-std-3001_vol.1_rev._b_final_draft_with_signature_010522.pdf

It gives recommended thickness in water, but PE is marginally more effective. So 15cm of water thickness recommended for beyond earth orbit and < 6 months is equivalent to 14cm of PE. Now I did a very rough calculation for all of crew quarters on HLS, but much less would be required if only for sleeping area as a radiation shelter to be used during radiation storms or transiting Van Alan Belts.

Yes, fewer ST flights for fueling would be required if less shielding is used.

This says more about how unrealistic NASA requirements are, or how unrealistic it is to shield the entire habitable volume. 

The correct engineering trade-off should be that taking 1 kg of radiation shielding mass and allocating it differently would give the same number of statistical years of life (based on the overall systems risk analysis) as deleting 1 kg of radiation shielding.

[math needed]

If I interpret your statement correctly, you are recommending shielding that would be 50% effective, that is half way between levels we get on Earth to the level of no shielding in space.

You are not interpreting me correctly. In fact I struggle to see how my words were misinterpreted like that.

What I actually said was that if you take 1 kg away from the radiation shield, and that 1 kg is allocated to other systems in the ideal (risk-minimizing) way, then it should give you the same number of years of statistical life as you gained by that 1 kg of shielding. In other words, the two numbers should be identical.

Otherwise the risk in the system is unbalanced, and you could reduce the total risk by reducing the radiation shield mass and re-allocating that mass to other systems.

If you were flying, how much shielding would you want?

I would want the thing I actually wrote, not the misunderstanding. 

[meekGee]

I don't see any reason to have 50 tons of radiation shielding. These aren't multi year missions.

From my first posts on page 1: Look at page 32 for table from NASA of recommended radiation shielding for various conditions on this link: https://www.nasa.gov/wp-content/uploads/2020/10/2022-01-05_nasa-std-3001_vol.1_rev._b_final_draft_with_signature_010522.pdf

It gives recommended thickness in water, but PE is marginally more effective. So 15cm of water thickness recommended for beyond earth orbit and &lt; 6 months is equivalent to 14cm of PE. Now I did a very rough calculation for all of crew quarters on HLS, but much less would be required if only for sleeping area as a radiation shelter to be used during radiation storms or transiting Van Alan Belts.

Yes, fewer ST flights for fueling would be required if less shielding is used.

This says more about how unrealistic NASA requirements are, or how unrealistic it is to shield the entire habitable volume. 

The correct engineering trade-off should be that taking 1 kg of radiation shielding mass and allocating it differently would give the same number of statistical years of life (based on the overall systems risk analysis) as deleting 1 kg of radiation shielding.

[math needed]

If I interpret your statement correctly, you are recommending shielding that would be 50% effective, that is half way between levels we get on Earth to the level of no shielding in space.

You are not interpreting me correctly. In fact I struggle to see how my words were misinterpreted like that.

What I actually said was that if you take 1 kg away from the radiation shield, and that 1 kg is allocated to other systems in the ideal (risk-minimizing) way, then it should give you the same number of years of statistical life as you gained by that 1 kg of shielding. In other words, the two numbers should be identical.

Otherwise the risk in the system is unbalanced, and you could reduce the total risk by reducing the radiation shield mass and re-allocating that mass to other systems.

If you were flying, how much shielding would you want?

I would want the thing I actually wrote, not the misunderstanding. 

How do you compare long term chronic risk (e.g. radiation) to short term acute risk (life support or landing legs)?

How do you compare risknof death and risk of severe injury?   Risk now vs. risk later?

One number does not capture all aspects of harm, and the probabilities themselves are uncertain, so trade-offs are not simple one-variable arithmetic.

[Twark_Main]

I don't see any reason to have 50 tons of radiation shielding. These aren't multi year missions.

From my first posts on page 1: Look at page 32 for table from NASA of recommended radiation shielding for various conditions on this link: https://www.nasa.gov/wp-content/uploads/2020/10/2022-01-05_nasa-std-3001_vol.1_rev._b_final_draft_with_signature_010522.pdf

It gives recommended thickness in water, but PE is marginally more effective. So 15cm of water thickness recommended for beyond earth orbit and &lt; 6 months is equivalent to 14cm of PE. Now I did a very rough calculation for all of crew quarters on HLS, but much less would be required if only for sleeping area as a radiation shelter to be used during radiation storms or transiting Van Alan Belts.

Yes, fewer ST flights for fueling would be required if less shielding is used.

This says more about how unrealistic NASA requirements are, or how unrealistic it is to shield the entire habitable volume. 

The correct engineering trade-off should be that taking 1 kg of radiation shielding mass and allocating it differently would give the same number of statistical years of life (based on the overall systems risk analysis) as deleting 1 kg of radiation shielding.

[math needed]

If I interpret your statement correctly, you are recommending shielding that would be 50% effective, that is half way between levels we get on Earth to the level of no shielding in space.

You are not interpreting me correctly. In fact I struggle to see how my words were misinterpreted like that.

What I actually said was that if you take 1 kg away from the radiation shield, and that 1 kg is allocated to other systems in the ideal (risk-minimizing) way, then it should give you the same number of years of statistical life as you gained by that 1 kg of shielding. In other words, the two numbers should be identical.

Otherwise the risk in the system is unbalanced, and you could reduce the total risk by reducing the radiation shield mass and re-allocating that mass to other systems.

If you were flying, how much shielding would you want?

I would want the thing I actually wrote, not the misunderstanding. 

How do you compare long term chronic risk (e.g. radiation) to short term acute risk (life support or landing legs)?

How do you compare risknof death and risk of severe injury?   Risk now vs. risk later?

If you prefer, use discounted (now vs later) or disability adjusted (death vs injury) numbers. We already know how to do that.

But do some math, instead of squinting and saying that X or Y amount of radiation shielding sounds about right, which certainly fails to "capture all aspects of harm."

One number does not capture all aspects of harm, and the probabilities themselves are uncertain, so trade-offs are not simple one-variable arithmetic.

What, exactly, is your proposed alternative?   

Is "winging it" (zero variable arithmetic) somehow any better?  If not, then you should be directing all this ire at Roy instead of me.... 

[Roy_H]

If I interpret your statement correctly, you are recommending shielding that would be 50% effective, that is half way between levels we get on Earth to the level of no shielding in space.

You are not interpreting me correctly. In fact I struggle to see how my words were misinterpreted like that.

What I actually said was that if you take 1 kg away from the radiation shield, and that 1 kg is allocated to other systems in the ideal (risk-minimizing) way, then it should give you the same number of years of statistical life as you gained by that 1 kg of shielding. In other words, the two numbers should be identical.

Otherwise the risk in the system is unbalanced, and you could reduce the total risk by reducing the radiation shield mass and re-allocating that mass to other systems.

Thank you for pointing out that I completely mis-understand you. However, maybe I am a little dense and still do not have a clear idea of your statement. I am aware that there are other elements that provide shielding, the ss skin, electrical equipment, supplies including clothing, space suits, drinking water, food etc. and if these items are placed on outer walls, they provide some protection to astronauts inside. However I doubt there is a 1:1 shielding value.

I do not want to get into an argument about exactly how much shielding is required/desired and the composition of the shielding. That is engineering details far beyond my very rough estimates. I only wanted to point out that 50t of shielding is possible and the mission would still be successful.

[Twark_Main]

If I interpret your statement correctly, you are recommending shielding that would be 50% effective, that is half way between levels we get on Earth to the level of no shielding in space.

You are not interpreting me correctly. In fact I struggle to see how my words were misinterpreted like that.

What I actually said was that if you take 1 kg away from the radiation shield, and that 1 kg is allocated to other systems in the ideal (risk-minimizing) way, then it should give you the same number of years of statistical life as you gained by that 1 kg of shielding. In other words, the two numbers should be identical.

Otherwise the risk in the system is unbalanced, and you could reduce the total risk by reducing the radiation shield mass and re-allocating that mass to other systems.
[/​quote]

Thank you for pointing out that I completely mis-understand you. However, maybe I am a little dense and still do not have a clear idea of your statement. I am aware that there are other elements that provide shielding, the ss skin, electrical equipment, supplies including clothing, space suits, drinking water, food etc. and if these items are placed on outer walls, they provide some protection to astronauts inside. However I doubt there is a 1:1 shielding value.

I mean that there are lots of things that can "eat mass" to improve survival: better MMOD shielding, more emergency rations, oxygen, CO2 scrubbers, medical supplies, etc.

All of these things improve survivability if you just throw more mass at them, but you have to have a "cutoff" where you decide the extra mass isn't worth it to increase safety any more.

So you have a priority list where you say "if I had an extra 500 kg I would put X into medical kit, Y into better seat shock absorption" etc.

What I'm saying is, these things should all be balanced.  Let the system "find its own level," and the radiation shield mass should compete on a level playing field with all that other risk reduction hardware.

Or, put another way, "if you can replace a ton of radiation shield with other stuff and I'm less likely to die overall, then I want that instead."

[Roy_H]

What I'm saying is, these things should all be balanced.  Let the system "find its own level," and the radiation shield mass should compete on a level playing field with all that other risk reduction hardware.

Of course, I didn't mean to suggest that anything else should be sacrificed in order to have extra shielding. I added it to the dry mass of the ship, which I expected to already include these things. I expect my "excess shielding" adds 2% to 3% of the cost of a Moon mission. Please consider it as an optional extra.

I absolutely agree with you, it should be a balanced approach.

[Twark_Main]

What I'm saying is, these things should all be balanced.  Let the system "find its own level," and the radiation shield mass should compete on a level playing field with all that other risk reduction hardware.

Of course, I didn't mean to suggest that anything else should be sacrificed in order to have extra shielding. I added it to the dry mass of the ship, which I expected to already include these things. I expect my "excess shielding" adds 2% to 3% of the cost of a Moon mission. Please consider it as an optional extra.

I absolutely agree with you, it should be a balanced approach.

Yep, I took the "50 tons" number to be mostly a placeholder (and some mass growth margin), and it sounds like that's the right way to interpret it.


To put it technically, each hardware category gets truncated once the diminishing marginal risk mitigation per mass reaches the same value across the entire vehicle. Say it ends up being 4 minutes of statistical life per kilogram. So you truncate the MMOD shield mass when the last kilogram gained 4.001 minutes but the next kilogram "only" gains 3.998 minutes. Same for medical supplies, life support consumables, and of course the radiation shield.

Basically sort the "wish list" by minutes / kg, decide how many kilograms you have, and then just keep going down the sorted list adding items until you run out of kilograms. This procedure should result in the safest vehicle possible that still fits into the mass constraints.

Obviously we're not going to do all that in this thread, but in the "real world" that's how you'd solve this problem in (something approaching) an optimal way.

[Vultur]

If you were flying, how much shielding would you want?

I would much rather spend that mass on preventing things that could lead to short term death, like spare parts, extra life support consumables, etc. I wouldn't worry too much about radiation shielding for the whole habitable volume (vs a solar storm shelter).

Part of the issue is that risk vs risk tradeoffs depend on your assumptions about chronic radiation risk. NASA probably believes in the linear-no-threshold model; I don't, so I think a lot of the risk NASA assumes is being mitigated from chronic radiation doses is risk that doesn't actually exist in the first place.

And even that is more for really long missions. For an Artemis 3 style mission, I wouldn't really worry much about radiation at all. Apollo didn't very much.

[Twark_Main]

Part of the issue is that risk vs risk tradeoffs depend on your assumptions about chronic radiation risk. NASA probably believes in the linear-no-threshold model; I don't, so I think a lot of the risk NASA assumes is being mitigated from chronic radiation doses is risk that doesn't actually exist in the first place.

I don't want to get too far down the LNT rabbit hole, but it should be said that Vultur is hardly taking a pseudoscientific position here.





The pro-LNT arguments are... rather lacking. These are not the sorts of papers you write when you stand on firm scientific ground. 

https://pubmed.ncbi.nlm.nih.gov/39222266/

https://www.nrdc.org/bio/bemnet-alemayehu/hold-fast-linear-no-threshold-radiation-protection

Anyway let's not go into a huge tangent, but hopefully these links are helpful for people who want to dig deeper.

[Vultur]

The pro-LNT arguments are... rather lacking. These are not the sorts of papers you write when you stand on firm scientific ground. 

I think that's because it's more a conservative default assumption than something that's positively supported.

IE, it's almost certainly wrong as a factual model of what happens in the real world. OTOH, "all models are wrong, but some are useful".

If one is an agency required to set *some* limit, in the absence of sufficient data about low dose/long exposure time, it is arguable that linear no threshold is a useful/safe assumption. I think that may be a reasonable argument for general-population standards (but probably not for special cases like astronauts). But in that case, the model is being used for a specific purpose - setting a regulatory standard. It may be fine for that use, but shouldn't then be considered to necessarily represent the "real" risk for other purposes.

(The opposite extreme would be the assumption that increased risk is zero, or even that risk decreases [hormesis], below the lowest level where harm is well demonstrated.

Reality is probably somewhere in between.)

This is pretty normal for setting regulatory safety limits. Since the limits are being set well below "obvious acute nasty effects", there's a lot of arguable extrapolation involved. The establishment of a limit at X doesn't usually mean that some obvious bad effects happens at X+a tiny bit.

[Roy_H]

Anyway let's not go into a huge tangent, but hopefully these links are helpful for people who want to dig deeper.

So some low level of radiation is actually beneficial. The Apollo astronauts had very little radiation protection, and no health problems attributable to radiation exposure.

I think we need to do some studies, like exposing mice to various levels/types of radiation to establish some realistic levels of danger. Such studies have been done. Trying to put this into some rough perspective:

20mGy/day         lethal (long term exposure, rats)
0.137 mGy/day    actually beneficial (extended life in beagle dogs 15%)
1.37 mGy/day     NASA acceptable guide line.

From: https://pmc.ncbi.nlm.nih.gov/articles/PMC5347275
"The optimum lifespan increase appeared at 50 mGy/y. The threshold for harm (decreased lifespan) was 700 mGy/y for 50% mortality dogs and 1100 mGy/y for short-lived dogs."

[Twark_Main]

The pro-LNT arguments are... rather lacking. These are not the sorts of papers you write when you stand on firm scientific ground. 

I think that's because it's more a conservative default assumption than something that's positively supported.

IE, it's almost certainly wrong as a factual model of what happens in the real world. OTOH, "all models are wrong, but some are useful".

If one is an agency required to set *some* limit, in the absence of sufficient data about low dose/long exposure time, it is arguable that linear no threshold is a useful/safe assumption. I think that may be a reasonable argument for general-population standards (but probably not for special cases like astronauts). But in that case, the model is being used for a specific purpose - setting a regulatory standard. It may be fine for that use, but shouldn't then be considered to necessarily represent the "real" risk for other purposes.

(The opposite extreme would be the assumption that increased risk is zero, or even that risk decreases [hormesis], below the lowest level where harm is well demonstrated.

Reality is probably somewhere in between.)

This is pretty normal for setting regulatory safety limits. Since the limits are being set well below "obvious acute nasty effects", there's a lot of arguable extrapolation involved. The establishment of a limit at X doesn't usually mean that some obvious bad effects happens at X+a tiny bit.

Yep, and honestly I can sympathize. LNT is "bad science but good policy," because if there's an acceptable dose when who gets to profit off it?

The company that makes my drywall wants to "use it" so they can source more radioactive gypsum. The construction company wants to use more radioactive gravel on roads and housing development. Ditto for granite countertops, brick facades, etc. And of course the local coal power plant wants to not get penalized for radiation because it's "actually healthy."

By assuming LNT, every potential radiation exposure source gets "policed" on a level playing field. Nice and simple.

Anyway this is already too far down the rabbit hole as it is...

[Twark_Main]

Bringing this back around, while NASA currently uses LNT for cancer risk modeling, they are notably open to using non-LNT models once they have more data on low-dose radiation risks.


https://www.ncbi.nlm.nih.gov/books/NBK189539/

The estimation of human cancer and non-cancer effects at low doses (less than 100 millisievert [mSv]) is based on the epidemiological data from atomic bomb survivors together with selected data for occupational and medical exposures. There is a continued reliance on the assumption that, at these low doses, a given increment in dose produces a directly proportionate increase in the probability of the development of cancer or heritable effects that are attributable to the radiation. This relationship is described as the linear no-threshold (LNT) model. The ICRP, for example “considers that the adoption of the LNT model combined with a judged value of a dose and dose rate effectiveness factor (DDREF) provides a prudent basis for the practical purposes of radiological protection, i.e., the management of risks from low-dose radiation exposure” (ICRP, 2007, p. 51). This is an important position because the LNT hypothesis and some of the other assumptions behind the estimation of risks are based on models and projections and not on direct scientific observation.

https://ntrs.nasa.gov/api/citations/20250001731/downloads/nscr_usafsymposium_March2025.pdf

Uncertainties not yet quantified in risk projections
...
  - Alternatives to linear no-threshold at low dose (i.e. non-targeted effects)

So NASA, at least, is keeping their powder dry.