ETH Zurich researchers use NASA data and supercomputing for AI climate forecasting

Researchers at ETH Zurich are working to revolutionize natural disaster forecasting by training artificial intelligence models on massive datasets. To facilitate this, approximately 100 petabytes of publicly available NASA climate and Earth observation data—comprising roughly six billion files—have been transferred to servers connected to ‘Alps’, one of the world’s most powerful supercomputers.

By integrating this data directly with high-performance computing, scientists aim to identify previously imperceptible patterns in weather and climate data. This capability could significantly improve the early detection of natural hazards, such as the devastating floods recently seen in Nepal. Thomas Schulthess, director of the Swiss National Supercomputing Centre, noted that having this data directly connected to the machine enables scientific possibilities that were previously unimaginable.