An Artificial Intelligence Framework for Lunar Missions from Ohio State Researchers: LUMINA

Developed by Gökçe İnal, a PhD student in civil, environmental and geodetic engineering at Ohio State University, the AI framework called LUMINA aims to make it easier for scientists to evaluate potential lunar landing sites, detect hazards and search for geological features. The research findings were presented at the 58th Annual Meeting of the American Astronomical Society's Division for Planetary Sciences.

The LUMINA model has shown strong results in making complex lunar observations and generating meaningful mission interpretations for candidate landing sites. Through these capabilities, mission planners aim to find areas rich in water ice and other resources.

Built upon the previously developed foundational model named LLaVA-LE, which describes lunar terrain and answers scientific questions, LUMINA can conduct multi-step analyses and explain the evidence behind its recommendations. Co-author Prof. Dr. Alper Yılmaz states that the model could be adapted to other planetary surfaces such as Mars and asteroids in the future.