GenCast: Diffusion-based ensemble forecasting for medium-range weather
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913337576521728 |
|---|---|
| author | Price, Ilan Sanchez-Gonzalez, Alvaro Alet, Ferran Andersson, Tom R. El-Kadi, Andrew Masters, Dominic Ewalds, Timo Stott, Jacklynn Mohamed, Shakir Battaglia, Peter Lam, Remi Willson, Matthew |
| author_facet | Price, Ilan Sanchez-Gonzalez, Alvaro Alet, Ferran Andersson, Tom R. El-Kadi, Andrew Masters, Dominic Ewalds, Timo Stott, Jacklynn Mohamed, Shakir Battaglia, Peter Lam, Remi Willson, Matthew |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_15796 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | GenCast: Diffusion-based ensemble forecasting for medium-range weather Price, Ilan Sanchez-Gonzalez, Alvaro Alet, Ferran Andersson, Tom R. El-Kadi, Andrew Masters, Dominic Ewalds, Timo Stott, Jacklynn Mohamed, Shakir Battaglia, Peter Lam, Remi Willson, Matthew Machine Learning Atmospheric and Oceanic Physics 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. |
| title | GenCast: Diffusion-based ensemble forecasting for medium-range weather |
| topic | Machine Learning Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2312.15796 |