NASA and IBM open-source a lunar foundation model, weights on Hugging Face
TinfoilTricorn · x · 2026-09-12
NASA and IBM have released the NASA-IBM Lunar Foundation Model, one of the first open-source AI foundation models built for lunar science. Announced September 10, 2026, it distills 17 years of Lunar Reconnaissance Orbiter observations and complementary mission data into a reusable base adaptable for crater mapping, volcanic-feature analysis, and ice prospecting.
- Weights published on Hugging Face under Apache-2.0, fine-tuning code on GitHub
- Ships with a unified ML-ready dataset called SomBench
- Follows prior NASA-IBM collaborations: the Prithvi Earth-observation models and the Surya heliophysics model
- Framed as an open-science tool for the global research community
More from Research
- Continued pretraining vs RAG: an accuracy and performance comparison on Qwen 3.5 4B — funJS · 2026-09-12
- Researcher speculates spatial reasoning leap comes from Blender training data — yoavartzi · 2026-09-12
- tszzl pushes back on Fermi paper: 50-OOM lognormal abiogenesis prior under-justified — tszzl · 2026-09-12
- Continued pretraining vs RAG on Qwen 3.5 4B: a hands-on accuracy and performance comparison — funJS · 2026-09-12
- OpenAI launches GPT-Rosalind for biological reasoning in API and Codex — OpenAIDevs · 2026-09-12
- MIT quantum lab uses GPT-5.6 Sol and Codex to automate chip measurements — OpenAI · 2026-09-12