Neural General Circulation Models for Weather and Climate

arXiv:2311.07222v3 Announce Type: replace-cross
Abstract: General circulation models (GCMs) are the foundation of weather and climate prediction. GCMs are physics-based simulators which combine a numerical solver for large-scale dynamics with tuned representations for small-scale processes such as cloud formation. Recently, machine learning (ML) models trained on reanalysis data achieved comparable or better skill than GCMs for deterministic weather forecasting. However, these models have not demonstrated improved ensemble forecasts, or shown sufficient stability for long-term weather and climate simulations. Here we …

abstract arxiv climate cloud cs.lg data dynamics foundation general machine machine learning numerical physics physics.ao-ph physics.comp-ph prediction processes scale small solver type weather