NASA and IBM release an open-source lunar foundation model trained on 17 years of orbiter data

NASA and IBM Research, working with several academic institutions, have released the NASA-IBM Lunar Foundation Model. They describe it as one of the first open-source foundation models for lunar science. A foundation model is pretrained on large amounts of unlabeled data and can then be adapted to specific tasks with a few labeled examples. The team sees that as especially useful for lunar research, where observation data is plentiful but labels are scarce. The team trained the model from scratch on SomBench, which they describe as the largest co-registered multimodal lunar corpus to date. It contains nearly 2 million tile bundles drawn from 17 years of orbiter observations. According to The Decoder, the model performs particularly well at predicting ice deposits at the poles and at detecting craters. Both tasks matter for planning future lunar missions and for understanding where water might be found. "NASA has spent decades building an extraordinary scientific record of the Moon, but collecting data is only part of the job," said Kevin Murphy, NASA's chief science data officer, adding that the data also has to be easier for scientists to use. Because the model is open source, researchers outside the two organizations can adapt it to their own lunar analysis tasks without building a model from scratch.