---
format: "aidr-story-markdown/v1"
id: "942585b4a6305d6d1dfce2b0d17870095eb1eeca9c89ed22a41899420b6be336"
canonical_url: "https://aidr.today/942585b4?lang=en"
title: "NASA and IBM Open Source First Lunar AI for Scientific Exploration"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-11T05:47:35.000Z"
category: "Research"
topics: ["open-source","multimodal","vision-language","nasa","ibm","huggingface"]
source_urls: ["https://huggingnews.com/ai/nasa-and-ibm-open-source-first-lunar-ai-for-scientific-exploration-9e48d9b1","https://x.com/NASAScience_/status/2098088421403095496","https://x.com/IBMNews/status/2098018859840082162","https://x.com/BrianRoemmele/status/2098259556799480280"]
summary: "A new machine learning model allows the global research community to map craters and volcanic features across the Moon's surface. Developed by NASA and IBM, the NASA-IBM Lunar Foundation Model was trained on 17 years of observations from the Lunar Reconnaissance Orbiter and other missions using a dataset of 2 million co-registered tile bundles called SomBench. This Vision Transformer encoder-decoder outperforms SwinV2-B baselines in crater detection by nearly 19% at 100 meter scale. The collaboration follows previous efforts to create the Prithvi Earth-observation and Surya heliophysics models to allow researchers to process petabytes of data without new hardware. This lunar system reduced root-mean-square error for polar ice prospectivity by up to 22% compared to previous benchmarks and is distributed via Hugging Face under an Apache 2.0 license. Fine-tuning code is available on GitHub for use with the TerraTorch toolkit."
---

# NASA and IBM Open Source First Lunar AI for Scientific Exploration

> [Open the canonical story](<https://aidr.today/942585b4?lang=en>)

**Published:** 2026-09-11T05:47:35.000Z
**Category:** Research
**Topics:** open\-source, multimodal, vision\-language, nasa, ibm, huggingface

## Summary

A new machine learning model allows the global research community to map craters and volcanic features across the Moon's surface\. Developed by NASA and IBM, the NASA\-IBM Lunar Foundation Model was trained on 17 years of observations from the Lunar Reconnaissance Orbiter and other missions using a dataset of 2 million co\-registered tile bundles called SomBench\. This Vision Transformer encoder\-decoder outperforms SwinV2\-B baselines in crater detection by nearly 19% at 100 meter scale\. The collaboration follows previous efforts to create the Prithvi Earth\-observation and Surya heliophysics models to allow researchers to process petabytes of data without new hardware\. This lunar system reduced root\-mean\-square error for polar ice prospectivity by up to 22% compared to previous benchmarks and is distributed via Hugging Face under an Apache 2\.0 license\. Fine\-tuning code is available on GitHub for use with the TerraTorch toolkit\.

## Sources

- [Story source](<https://huggingnews.com/ai/nasa-and-ibm-open-source-first-lunar-ai-for-scientific-exploration-9e48d9b1>)
- [Story source](<https://x.com/NASAScience_/status/2098088421403095496>)
- [Story source](<https://x.com/IBMNews/status/2098018859840082162>)
- [Supporting source](<https://x.com/BrianRoemmele/status/2098259556799480280>)