GenCast: Diffusion-based ensemble forecasting for medium-range weather
arXiv:2312.15796
Abstract
Weather forecasts are fundamentally uncertain, so predicting the range of probable weather scenarios is crucial for important decisions, from warning the public about hazardous weather, to planning renewable energy use. Here, we introduce GenCast, a probabilistic weather model with greater skill and speed than the top operational medium-range weather forecast in the world, the European Centre for Medium-Range Forecasts (ECMWF)'s ensemble forecast, ENS. Unlike traditional approaches, which are based on numerical weather prediction (NWP), GenCast is a machine learning weather prediction (MLWP) method, trained on decades of reanalysis data. GenCast generates an ensemble of stochastic 15-day global forecasts, at 12-hour steps and 0.25 degree latitude-longitude resolution, for over 80 surface and atmospheric variables, in 8 minutes. It has greater skill than ENS on 97.4% of 1320 targets we evaluated, and better predicts extreme weather, tropical cyclones, and wind power production. This work helps open the next chapter in operational weather forecasting, where critical weather-dependent decisions are made with greater accuracy and efficiency.
Main text 11 pages, Appendices 76 pages
Cited by in corpus (12)
- Validating Deep Learning Weather Forecast Models on Recent High-Impact Extreme Events
- Generative Learning of the Solution of Parametric Partial Differential Equations Using Guided Diffusion Models and Virtual Observations
- Samudra: An AI Global Ocean Emulator for Climate
- Development of an offline and online hybrid model for the Integrated Forecasting System
- Generative ensemble deep learning severe weather prediction from a deterministic convection-allowing model
- Leveraging data-driven weather models for improving numerical weather prediction skill through large-scale spectral nudging
- Predicting Change, Not States: An Alternate Framework for Neural PDE Surrogates
- Stochastic Latent Transformer: Efficient Modelling of Stochastically Forced Zonal Jets
- Beyond Ensemble Averages: Leveraging Climate Model Ensembles for Subseasonal Forecasting
- Improving ensemble extreme precipitation forecasts using generative artificial intelligence
- Uncertainties of Satellite-based Essential Climate Variables from Deep Learning
- Projecting U.S. coastal storm surge risks and impacts with deep learning