The HClimRep project aims to answer precisely such questions. By building one of the first AI foundation models for climate research that integrates data from the atmosphere, the ocean, and sea ice, researchers are developing one of the most precise weather and climate models in the world. Trained extensively on Europe’s first exascale computer, this deep learning model, with several billion parameters, will be able to perform complex “what-if” experiments as well as a wide range of oceanic and atmospheric modeling tasks.