Rahul Ramachandran (ST11) gave an invited keynote address on “Building Earth Science Foundation Models to Better Understand our Planet” at the IBM AI Forum. His talk presented a vision for building foundation AI models to both augment NASA’s data lifecycle and to accelerate scientific discovery. Foundation models (FM) are AI models pretrained on comprehensive datasets using self-supervised learning. These models can then be used for many different downstream tasks. The datasets need to be sequential in nature, and that removes the need for having large labeled datasets.