Ohio State researchers present AI model to help choose lunar landing sites
The LUMINA framework weighs terrain hazards, water ice and scientific value to assess candidate sites on the Moon, according to Universe Today.
Researchers at The Ohio State University have presented an AI model meant to help mission planners pick safe landing sites on the Moon, according to Universe Today.
The model is called LUMINA, and the outlet describes it as an agentic AI framework. Universe Today reported that the team introduced it in a study presented at the 58th Annual Meeting of the Division for Planetary Sciences of the American Astronomical Society. The framework evaluates landing sites with a focus on key resources such as water ice, along with potential scientific value. It is also meant to help develop a strategy for a human outpost at those sites.
According to the outlet, LUMINA does not rely only on orbital images. It draws on lunar surface data including topography, terrain hazards, geology, surface properties and scientific value, and it compares candidate sites with each other. The researchers hope to apply it to other planetary bodies as well, specifically Mars.
“"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."”Gokce Inal, PhD candidate at The Ohio State University and lead author of the study
Inal added: "This work is meant to serve as a bridge between those two worlds, AI and planetary science."
LUMINA builds on the group's earlier model, the Large Language-and-Vision Assistant for Lunar Exploration (LLaVA-LE), which analyzes and describes orbital images of the lunar surface. Universe Today reported that LLaVA-LE is available on arXiv and GitHub and was presented at the CVPR2026 AI4Space Workshop in June 2026.
The work comes as NASA prepares for crewed lunar missions. According to Universe Today, the agency plans to return astronauts to the Moon in 2028, the first time since Apollo 17 in 1972, and aims to establish a permanent human presence there. That effort falls under NASA's Moon to Mars Architecture, a framework for developing technologies such as power systems, habitation and in-situ resource utilization. That last approach uses local resources like water ice for drinking, fuel and oxygen, with the aim of reducing the need for resupply from Earth.
"NASA's Artemis program creates important opportunities for our research," Inal said, adding that new lunar data could improve systems like LUMINA and better support future mission planning.
Much is still unclear. Universe Today says LUMINA shows a strong ability to identify promising sites, but the report gives no performance figures, no list of the sites it picked and no comparison with other methods. It does not say whether NASA or any mission team has used or reviewed the model, or whether the LUMINA study has been peer reviewed. The report also does not say when the presentation took place.
