NASA, IBM Release Open-Source AI Model to Study the Moon

NASA and IBM have released an open-source artificial intelligence model built to help researchers study the moon, the two organizations announced Thursday, Sept. 10. The tool, called the NASA-IBM Lunar Foundation Model, is available for free on the AI platform Hugging Face.

NASA has gathered mountains of data over decades of lunar missions and studies. Data collected by the Lunar Reconnaissance Orbiter (LRO), a NASA lunar orbiter, alone exceeds that of all of NASA's other planetary missions combined. Analyzing all this information takes considerable time and effort from researchers, which is what the new model is meant to help with.

According to NASA, the model can assist researchers with tasks such as mapping craters, identifying young volcanic features, and modeling possible locations of water ice near the moon's poles. Kevin Murphy, NASA's chief science data officer and acting chief data and AI officer, said in the announcement that "NASA has spent decades building an extraordinary scientific record of the moon, but collecting data is only part of the job."

The lunar model is part of a series of science-focused AI models NASA has developed with IBM, following earlier models for Earth observation and for heliophysics, the study of the sun and its effects on the solar system. NASA and other space agencies and private companies have increasingly explored how AI models can help with analysis to increase scientific productivity, reduce costs and streamline workflows.

The new model was trained mostly on data from the LRO mission. Over 17 years, the orbiter has compiled a nearly complete mosaic of high-definition images detailing the moon's surface.