AI-generated illustration; not a photograph of the reported event.
- calendar_today October 28, 2026
Next-Gen AI to Enhance Space Exploration
Preparing for space missions has always required intensive scientific preparation and data analysis. As global space agencies strive to establish outposts on the moon, artificial intelligence could play a central role in making mission planning more efficient and comprehensive.
Introducing LUMINA: An AI Framework for Lunar Missions
At The Ohio State University, PhD candidate Gokce Inal from the Department of Civil, Environmental and Geodetic Engineering has developed an advanced artificial intelligence framework known as LUMINA. This system is designed to support scientists by evaluating potential lunar landing sites, identifying hazards for future crews, and highlighting regions that may have valuable geologic features.
Bridging AI and Planetary Science
Inal describes AI tools as becoming essential for space exploration, helping human experts to sift through millions of images and datasets generated by future missions. "This work is meant to serve as a bridge between those two worlds, AI and planetary science," Inal explained. The complexity of landing on the moon has increased over the decades, but preliminary results from LUMINA indicate that the AI can make complex lunar observations and provide insightful commentary about candidate landing sites.
Key Capabilities of the LUMINA Framework
LUMINA builds on a previous lunar vision-language foundation called LLaVA-LE, which could describe terrain and answer scientific questions. By enabling multistep analyses and the evaluation of potential lunar landing sites, LUMINA also provides explanations for its recommendations. Rather than operating as an autonomous decision-maker, LUMINA is positioned as a decision-support tool, working collaboratively with mission planners to arrive at informed conclusions. Inal said, "We’re moving toward an active scientific assistant that can work through a problem alongside the experts."
Expanding Beyond the Moon
The model's applications stretch beyond the lunar surface. According to Alper Yilmaz, professor and co-author on the research, LUMINA could also be useful for mapping other planetary bodies such as Mars or asteroids. "There aren’t many GPT-like map models being developed for space exploration, so our effort is aimed at making one generalizable to other surfaces," Yilmaz noted.
Future Applications and Testing
As new, high-resolution lunar data is produced, the research team plans to further test LUMINA and assess its support for mission planning activities. The system has the potential to narrow down landing sites rich in resources like water ice by efficiently navigating complex datasets—a task that could otherwise resemble "looking for a needle in a haystack," said Yilmaz.
Supporting Artemis and Beyond
Inal highlighted that NASA's Artemis program provides valuable opportunities for this research. Advanced lunar data from such programs could improve LUMINA and help future space mission planning become more precise. "As new lunar data becomes available, their results can improve systems like ours and better support future mission planning," said Inal.
Ongoing Development and Outlook
The LUMINA AI framework was presented at the 58th Annual Meeting of the Division for Planetary Sciences of the American Astronomical Society. As development continues, researchers remain optimistic about AI's role in advancing planetary science and the practical aspects of future space missions, ensuring that crews land in the safest and most scientifically valuable locations possible.
Source: news.osu.edu.
