NASA and IBM Launch Open AI Model to Map Moon Surface

Science11 sourcesSep 11, 2026

ConsensusFactual rigor 50/100

The Story

NASA has launched the NASA-IBM Lunar Foundation Model, one of the first open-source AI models built specifically for lunar science, in collaboration with IBM Research and several academic institutions.

The model, trained primarily on data from NASA's Lunar Reconnaissance Orbiter (LRO), is hosted publicly on Hugging Face, with its complete codebase available on GitHub for testing and experimentation. IBM announced the open-source release of the model on Thursday. The tool aims to help scientists analyze decades' worth of lunar data to generate actionable insights in preparation for mankind's return to the moon.

It can help astronauts navigate the moon more safely, track down potential resources such as ice deposits, and identify certain geological features that may present hazards. NASA's Artemis Program intends to land a crewed mission on the lunar surface, with plans to return humans to the Moon in 2028. The last time humans were on the Moon was in December 1972 as part of the Apollo 17 mission.

What they agree on

NASA and IBM Research have launched the NASA-IBM Lunar Foundation Model, an open-source AI model for lunar science.
The AI model is designed to help researchers analyze the moon's surface, map ice, craters, and volcanoes.
The model was primarily trained on data from NASA's Lunar Reconnaissance Orbiter (LRO).
The complete codebase for the model is publicly available on GitHub, and the model is hosted on Hugging Face.
The tool aims to assist in preparing for future crewed missions to the Moon, including NASA's Artemis Program, which plans to return humans to the Moon in 2028.

Where they split

Phys.org and Space.com focus on the technical details of the AI model, including its open-source nature and training data.
Fast Company emphasizes the model's potential role in helping humans return to the Moon by 2028 and its practical applications for astronauts.
Reuters, The Straits Times, and Channel News Asia provide brief, direct announcements of the launch of the AI model.
Some independent outlets, like IJR (Independent Journal Review) and Live Science, highlight the model's ability to outperform prior lunar analysis tools and map the moon in more detail.