NASA’s Marshall Space Flight Center and computing giant IBM plan to use artificial intelligence (AI) tech to improve climate change research, according to an announcement IBM posted on Feb. 1.
Under the new partnership, NASA and IBM will create AI foundation models to analyze petabytes of text and remote-sensing data to make it easier to build AI applications tailored to specific climate change questions and tasks.
“We hope these models will make information and knowledge more accessible to everyone and encourage people to build applications that make it easier to use our datasets to make discoveries and decisions based on the latest science,” said Rahul Ramachandran, a senior research scientist at NASA’s Marshall Space Flight Center.
Foundational AI models can ingest massive amounts of raw data and find their underlying structure without explicit instruction. NASA is currently sitting on 70 petabytes of earth science data – a number expected to quadruple this year and into 2024 with future mission launches.
Under this collaboration, IBM and NASA will build two foundation models. The first model will be trained on reams of earth science journals to thematically organize the literature and make it easier to search and discover new knowledge. The second will be trained on the U.S. Geological Survey and NASA’s popular dataset, Harmonized Landsat Sentinel-2, which is a record of land-use changes captured by Earth-orbiting satellites.
The collaboration will also result in downstream applications, including detecting natural hazards and tracking changes to vegetation and wildlife habitats for natural resource management.
“Building these foundation models cannot be tackled by small teams. You need teams across different organizations to bring their different perspectives, resources, and skill sets,” Ramachandran said.
In addition, Ramachandran explained that the foundation models could multiply the usefulness of NASA data. The partnership with IBM is also a part of a broader push by NASA to make data, code, and AI models available to everyone through its Open-Source Science Initiative.