NASA plans to return astronauts to the lunar surface in 2028 for the first time since Apollo 17 in 1972. To support this goal and the subsequent establishment of a permanent human presence, researchers at The Ohio State University have introduced a novel artificial intelligence framework called LUMINA to evaluate safe landing sites and resources.
Researchers Present LUMINA Framework at Astronomical Society Meeting
The Ohio State University research team detailed the LUMINA framework at the 58th Annual Meeting of the Division for Planetary Sciences of the American Astronomical Society. LUMINA is an agentic AI framework designed to help mission planners evaluate safe lunar landing sites. The model focuses on key resources such as water ice and evaluates potential scientific value across candidate locations.
Unlike systems that rely exclusively on orbital images, LUMINA incorporates multiple layers of lunar surface data. The model evaluates topography, terrain hazards, geology, surface properties, and scientific value while cross-referencing candidate sites against one another. Gokce Inal, a PhD candidate in Civil Environmental and Geodetic Engineering at The Ohio State University and lead author of the study, noted the growing utility of these systems.
AI systems are going to become critical tools for space exploration that will help humans analyze the millions of images and datasets that future missions will require,
Inal said. This work is meant to serve as a bridge between those two worlds, AI and planetary science.
Building on the LLaVA-LE Model Released on arXiv and GitHub
The LUMINA framework builds directly upon previous work by the same research group. That predecessor, the Large Language-and-Vision Assistant for Lunar Exploration, demonstrated an ability to analyze and describe orbital images of the lunar surface.
The LLaVA-LE model is currently available on arXiv, was presented at the CVPR2026 AI4Space Workshop in June 2026, and can be found on GitHub. Researchers plan to expand the application of these AI models beyond the Moon to other planetary bodies, specifically targeting Mars.
Supporting NASA Architecture and In-Situ Resource Utilization
NASA’s long-term strategy involves sending humans to Mars through the continuously evolving Moon to Mars Architecture. This strategic framework develops vital technologies for living and working on the Moon, including power systems, transportation, habitation and life support, robotics and construction, communications, and in-situ resource utilization.
In-situ resource utilization plays a central role by allowing crews to use local resources for survival. This approach targets water ice for drinking, bathing, and fuel, oxygen generation via electrolysis, and lunar regolith for construction and growing plants. The strategy aims to reduce or eliminate resupply missions from Earth.
NASA’s Artemis program creates important opportunities for our research,
Inal said. As new lunar data becomes available, their results can improve systems like ours and better support future mission planning.
Worth a look