USRA Contributes Expertise to Open-Source AI Model for Lunar Research

The Universities Space Research Association (USRA) has contributed its expertise in planetary science to the development of an open-source artificial intelligence model designed for lunar research.

The NASA-IBM Lunar Foundation Model, developed through a collaboration led by NASA and IBM Research, is pre-trained from scratch using SomBench, a multimodal dataset containing nearly two million co-registered data bundles spanning 11 modalities and two spatial scales.

USRA's Dr. Rachel Slank served as a planetary science subject-matter expert on the project team, helping to connect lunar science priorities with decisions about model development and evaluation.