# NASA and IBM release open‑source lunar model built on 17 years of orbiter data

> The NASA‑IBM Lunar Foundation Model, now open on Hugging Face, uses nearly 2 million lunar image tiles to improve ice‑deposit and crater predictions.

Oossa · 2026-10-04 · https://oossa.com/en/nasa-and-ibm-release-open-source-lunar-model-built-on-17-years-of-orbiter-data

NASA and IBM Research have made a new lunar AI model publicly available. The NASA‑IBM Lunar Foundation Model is open‑source and can be downloaded from Hugging Face, with its code on GitHub. It was trained on 17 years of data from the Lunar Reconnaissance Orbiter and other missions, turning that archive into a tool that scientists can adapt with only a few labeled examples.

## What the model can do

The model works with high‑resolution (about 1 meter per pixel) and coarse (100 m per pixel) images at the same time. It also takes lighting angles and sun position as explicit inputs, which helps it separate real surface features from shadows. In tests, it cut error on polar‑ice predictions by up to 22 % compared with the best baseline model. For crater detection at coarse scales it was about 19 % more accurate, even though it used only half the labeled data.

## How it was built

Researchers assembled a data set called SomBench, the largest co‑registered multimodal lunar corpus to date. It contains nearly 2 million “tile bundles” from 11 different data types, covering more than 30 aligned layers from nine instruments across four missions. The model was trained from scratch using a technique called FlexiViT, which lets the same model handle different image patch sizes without retraining.

## The facts

- The model was trained on nearly 2 million tile bundles from 17 years of Lunar Reconnaissance Orbiter observations.
- About 1 million tiles are high‑resolution (≈1 m/pixel) NAC images; roughly 964,000 are multispectral Wide Angle Camera images at 100 m/pixel.
- Prediction error on polar ice deposits fell by up to 22 % compared with the SwinV2‑B baseline.
- Coarse‑scale crater detection accuracy improved by nearly 19 % while using only half the labeled data.
- The model and its datasets are released on Hugging Face; code is on GitHub and integrated into the TerraTorch toolkit.

## Why it matters

For planetary scientists, the open model provides a ready‑made AI that can spot ice and craters with fewer hand‑labeled examples, speeding up research on lunar resources. For anyone following future Moon missions, better ice maps could inform where to land or mine water for rocket fuel. However, the model is not a substitute for direct measurements; its geographic coordinates can still be off by dozens of degrees.

## Sources & references

1. [NASA and IBM's open source lunar model turns 17 years of orbiter data into a foundation for lunar science](https://the-decoder.com/nasa-and-ibms-open-source-lunar-model-turns-17-years-of-orbiter-data-into-a-foundation-for-lunar-science/) – The Decoder, 2026-10-04

Last updated: 2026-10-04