ETH Zurich loads 100 PB of NASA climate data onto Alps supercomputer for AI forecasting

ETH Zurich researchers said they copied roughly 100 petabytes of publicly available NASA climate and Earth observation data, about 6 billion files, onto servers adjacent to the Alps supercomputer at the Swiss National Supercomputing Centre in Lugano, a process that took about a year. The setup is intended to train AI statistical models that can run a global multi-day weather forecast in about a minute, versus hours for traditional equation-based simulation, and to flag hazards such as landslides and glacier collapses from satellite patterns. ETH climate physicist Reto Knutti said the models are expensive to train but cheap to run, enabling more frequent iterations for early-warning systems.