NASA and IBM Release Open-Source Lunar Foundation Model and Mapping Dataset
NASA and IBM have released an open-source AI model trained on a large collection of lunar observations, alongside a dataset built from nine instruments across four missions, to help scientists analyze the Moon at scale.
The NASA-IBM Lunar Foundation Model is described as the first AI model to integrate observations captured in a range of modalities, or data formats, and at different viewing angles and spatial scales, according to an account published by The Register and reported by Slashdot on September 13, 2026.
"The NASA-IBM Lunar Foundation Model gives scientists a foundation to explore the Moon at scale, connecting observations across instruments, revealing patterns that are difficult to see in isolation, and providing an open platform the global research community can build on," said Juan Bernabe-Moreno, IBM's director of research for Europe.
According to NASA and IBM, researchers can use the model to analyze geographic features instead of sifting through maps and images by hand or relying on low-resolution machine learning models. The two organizations said they hope the tool will help researchers find previously unidentified lunar ice deposits, analyze volcanic features known as Irregular Mare Patches, and identify and classify craters.
Lunar ice is of interest because it indicates the presence of water and oxygen, resources that may be useful for future crewed missions. It is found in permanently shadowed regions, which are among the most difficult areas of the Moon to observe. The NASA-IBM model combines multimodal and multi-resolution observations to better predict where ice may be present on the lunar surface.
Alongside the model, IBM and NASA scientists compiled an open-source lunar dataset from more than 30 spatially aligned layers, drawing on data from nine instruments across four missions. The dataset combines tens of thousands of images and maps showing various geophysical properties of the lunar surface.