NEWS · MODELS · #1486
NASA and IBM release open-source Lunar Foundation Model trained on 17 years of LRO data
NASA and IBM Research, with academic partners, published the open-source NASA–IBM Lunar Foundation Model, a multimodal foundation model trained from scratch on SomBench — a co-registered corpus of nearly 2 million lunar tile bundles spanning 11 modalities and multiple missions including 17 years of LRO data. The pretrained model improves tasks such as polar ice prediction (up to ~22% error reduction) and coarse-scale crater detection (~19% improvement versus SwinV2-B), and is intended to let researchers adapt lunar observations to downstream tasks with far fewer labels.
KEY POINTS
- NASA and IBM Research, with academic partners, published the open-source NASA–IBM Lunar Foundation Model, a multimodal foundation model trained from scratch on SomBench — a co-registered corpus of nearly 2 million lunar tile bundles spanning 11 modalities and multiple missions including 17 years of LRO data.
- The pretrained model improves tasks such as polar ice prediction (up to ~22% error reduction) and coarse-scale crater detection (~19% improvement versus SwinV2-B), and is intended to let researchers adapt lunar observations to downstream tasks with far fewer labels.
- It makes decades of heterogeneous lunar observations directly usable for machine learning, lowering the label burden for key science and resource-mapping tasks such as ice detection and crater mapping.
WHY IT MATTERS
It makes decades of heterogeneous lunar observations directly usable for machine learning, lowering the label burden for key science and resource-mapping tasks such as ice detection and crater mapping.