NASA and IBM Unveil Lunar Mapping AI System

NASA and IBM have released an open-source AI system called the Lunar Foundation Model to help map the Moon's surface. This model is designed to identify water ice, craters, and other geological features on the Moon.

The model is trained on over two million co-registered data points from three lunar missions: NASA's Lunar Reconnaissance Orbiter, the Gravity Recovery and Interior Laboratory mission, and Japan's SELENE/Kaguya spacecraft. This dataset allows the AI to ingest high-resolution imagery, topography, gravity measurements, and thermal readings simultaneously.

The model outperforms a leading Microsoft-trained vision baseline on ice mapping and crater detection, reducing error by 22-23% in one benchmark test. It also passed a real-world test when it correctly identified a new crater created by a SpaceX rocket stage impact on the Moon.