NASA and IBM Release AI Model for Lunar Exploration
The open-source foundation model helps scientists map water ice and terrain for future Moon missions.
A digital visualization of the lunar surface with glowing overlays highlighting geological features and ice deposits.
Photo: Kronos News
NASA and IBM have released a new open-source lunar foundation model to accelerate space exploration [1][2]. The AI analyzes vast quantities of multi-instrument lunar data to identify geological features and potential water ice deposits [1]. This collaboration aims to support a sustained human presence on the Moon [2].
The model utilizes a dataset of two million tiles to automate mapping [3]. According to researchers, the system achieved a 22% reduction in error rates for ice mapping compared to previous methods [3]. This tool helps scientists navigate rugged terrains and volcanic features more efficiently [1].
Editorial notes
Transparency note
AI assisted drafting. Human edited and reviewed.
- AI assisted
- Yes
- Human review
- Yes
- Last updated
Risk assessment
Reviewed for sourcing quality and editorial consistency.
Sources
- 1.↗
manilatimes.net
https://www.manilatimes.net/2026/09/19/business/science-technology/ai-model-unlocks-lunar-secrets/2428138
- 2.↗
newsroom.ibm.com
https://newsroom.ibm.com/2026-09-10-ibm-and-nasa-release-open-source-ai-model-to-support-lunar-exploration
- 3.↗
storagereview.com
https://www.storagereview.com/news/nasa-ibm-lunar-foundation-model-goes-open-source-with-a-2m-tile-dataset-and-22-lower-ice-mapping-error
Related stories
View all
About the author
Kronos News Desk covers news and editorial analysis for Kronos News.