Nasa and IBM Unveil AI-Powered Lunar Mapping Tool

Nasa has partnered with IBM to develop an open-source artificial intelligence model that can help scientists map the Moon's surface and search for water. The Nasa-IBM Lunar Foundation Model was trained on over 30 layers of data collected by nine instruments across four Nasa missions, including the Lunar Reconnaissance Orbiter (LRO).

The model can identify potential ice deposits in permanently shadowed regions, map craters, and study volcanic formations with up to 23% greater accuracy than widely used methods. This could be crucial for future lunar exploration, as scientists prepare for a new era of missions.

Craters on the Moon's surface hold valuable information about its geological history, while detailed crater maps can help planners identify safer locations for landings and infrastructure. The search for lunar ice is also a key application of the model, as it could provide drinking supplies and oxygen for astronauts, as well as rocket fuel for future missions.

The Nasa-IBM Lunar Foundation Model is open-source, meaning researchers around the world can access and build on it. IBM Research's Juan Bernabe-Moreno said that the model can help the science community explore the lunar landscape and aid the next generation of astronauts in navigating the Moon's surface.