IBM and NASA Release AI Foundation Model to Accelerate Lunar Research

International Business Machines Corp. (NYSE: IBM) and NASA on Thursday announced the release of an open-source artificial intelligence model intended to significantly accelerate the analysis of lunar data and support future exploration. The new tool is designed to help scientists identify key features and potential resources on the Moon's surface, a critical step for NASA's long-term plans for a sustained human presence.

Model Details and Capabilities

The NASA-IBM Lunar Foundation Model is a publicly available tool trained on more than 30 layers of data gathered by nine different instruments across four separate NASA missions, including the Lunar Reconnaissance Orbiter. It is the latest addition to the Prithvi family of open foundation models developed by the two organizations, which also cover geospatial and weather applications.

According to the joint announcement, the AI can automate tasks that previously required scientists to manually analyze maps and images. Its primary functions include:

• Identifying potential ice deposits in the Moon’s permanently shadowed regions.
• Mapping craters to help select safe landing sites for future missions.
• Studying volcanic features across the lunar landscape.

Ad

Strategic Importance for Artemis

The model's release directly supports NASA’s Artemis program, which aims to return astronauts to the Moon in 2028 and establish a long-term base. The search for lunar ice is a high priority, as it indicates the presence of water and oxygen—resources essential for life support and for producing rocket fuel for potential future missions to Mars.

By streamlining data analysis, the AI model allows researchers to more efficiently locate these vital resources and assess geological features. In benchmark tests, the model identified key lunar features with up to 23% greater accuracy than widely used existing methods, according to IBM and NASA.

For IBM, the collaboration serves as a high-profile demonstration of its AI capabilities in a highly specialized scientific field. The project underscores the growing application of foundation models beyond commercial use cases and into complex government and research initiatives.