GoKawiilNASA and IBM release open-source AI model trained on lunar mission data
NASA and IBM Research have jointly released the NASA-IBM Lunar Foundation Model, an open-source AI system pretrained on SomBench, a dataset of nearly two million co-registered lunar data bundles across 11 modalities. The model fuses imagery, topography, mineralogy, radar, gravity and other planetary datasets to help scientists analyze the Moon's surface, with USRA scientist Rachel Slank contributing planetary science expertise during development.
GoKawiil's interpretation of the reporting above, not reported fact.
Lunar missions generate enormous, disparate datasets that are hard to interpret using traditional single-purpose tools, so a foundation model capable of combining multiple data types could speed up identification of resources like water ice ahead of future crewed missions. Making the model open-source also lets the broader research community build on it rather than relying on proprietary or siloed analysis pipelines.
- NASA and IBM Research jointly built an open-source AI model for lunar data analysis.
- The model was pretrained on SomBench, a dataset with nearly two million multimodal lunar data bundles.
- It shows improved prediction of lunar ice prospectivity compared to prior models like ConvNeXt.
Celestron NexStar 130SLT Telescope — If lunar science stories spark your curiosity about the Moon's surface, a telescope like the Celestron NexStar 130SLT lets you observe those craters and features firsthand. Its computerized mount makes it easy to locate and track the Moon and other celestial objects, bringing the science behind these AI-driven lunar maps to life in your own backyard.
See Celestron NexStar 130SLT Telescope on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.Source: newsroom.usra.edu, 2026-09-19
Published there as: “NASA-IBM Lunar Foundation open-Source Geospatial AI Model”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.