IBM and NASA unveil AI model to find ice and craters on the Moon
In Pakistan, IBM and NASA on September 10 unveiled the open AI model Lunar Foundation Model for analyzing multi-year lunar observation data. The tool is intended to help scientists study the lunar surface and support plans for a long-term human presence on Earth’s satellite, Dawn reports.
Data from four NASA missions
The model was trained on more than 30 data layers collected by nine instruments during four NASA missions, including the Lunar Reconnaissance Orbiter. The Lunar Foundation Model has joined the Prithvi family of open foundation models, which IBM and NASA also use for geospatial and weather-related tasks.
The AI model can help detect potential ice deposits in permanently shadowed areas of the Moon, map craters to select safe landing sites, and study volcanic features. Previously, such tasks required scientists to manually process maps and images or use lower-resolution machine-learning models.
More current news is available on the UA.News Telegram channel Telegram.
Resources for future missions
In tests, the model identified key features on the lunar surface up to 23% more accurately than widely used methods, NASA and IBM said. Lunar ice is of interest to space agencies because it indicates the presence of water and oxygen — resources considered necessary for a future Moon base and for producing rocket fuel for missions to Mars.
NASA’s Artemis program envisages returning astronauts to the Moon in 2028 to test technologies needed for a long-term presence on the satellite and future missions to Mars.
