Probabilistic weather forecasting with machine learning

被引:12
作者
Price, Ilan [1 ]
Sanchez-Gonzalez, Alvaro [1 ]
Alet, Ferran [1 ]
Andersson, Tom R. [1 ]
El-Kadi, Andrew [1 ]
Masters, Dominic [1 ]
Ewalds, Timo [1 ]
Stott, Jacklynn [1 ]
Mohamed, Shakir [1 ]
Battaglia, Peter [1 ]
Lam, Remi [1 ]
Willson, Matthew [1 ]
机构
[1] Google DeepMind, London, England
关键词
TEMPESTEXTREMES; PREDICTION; FRAMEWORK; TRACKING;
D O I
10.1038/s41586-024-08252-9
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
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. Traditionally, weather forecasts have been based on numerical weather prediction (NWP)1, which relies on physics-based simulations of the atmosphere. Recent advances in machine learning (ML)-based weather prediction (MLWP) have produced ML-based models with less forecast error than single NWP simulations2,3. However, these advances have focused primarily on single, deterministic forecasts that fail to represent uncertainty and estimate risk. Overall, MLWP has remained less accurate and reliable than state-of-the-art NWP ensemble forecasts. Here we introduce GenCast, a probabilistic weather model with greater skill and speed than the top operational medium-range weather forecast in the world, ENS, the ensemble forecast of the European Centre for Medium-Range Weather Forecasts4. GenCast is an ML weather prediction method, trained on decades of reanalysis data. GenCast generates an ensemble of stochastic 15-day global forecasts, at 12-h steps and 0.25 degrees latitude-longitude resolution, for more than 80 surface and atmospheric variables, in 8 min. It has greater skill than ENS on 97.2% of 1,320 targets we evaluated and better predicts extreme weather, tropical cyclone tracks and wind power production. This work helps open the next chapter in operational weather forecasting, in which crucial weather-dependent decisions are made more accurately and efficiently.
引用
收藏
页码:84 / 90
页数:21
相关论文
共 50 条
[21]   Machine learning techniques for flood forecasting [J].
Hadi, Fayrouz Abd Alkareem ;
Sidek, Lariyah Mohd ;
Salih, Gasim Hayder Ahmed ;
Basri, Hidayah ;
Sammen, Saad Sh. ;
Dom, Norlida Mohd ;
Ali, Zaharifudin Muhamad ;
Ahmed, Ali Najah .
JOURNAL OF HYDROINFORMATICS, 2024, 26 (04) :779-799
[22]   Enhanced EEG Forecasting: A Probabilistic Deep Learning Approach [J].
Pankka, Hanna ;
Lehtinen, Jaakko ;
Ilmoniemi, Risto J. ;
Roine, Timo .
NEURAL COMPUTATION, 2025, 37 (04) :793-814
[23]   Learning to Forecast: The Probabilistic Time Series Forecasting Challenge [J].
Bracher, Johannes ;
Koster, Nils ;
Krueger, Fabian ;
Lerch, Sebastian .
AMERICAN STATISTICIAN, 2024, 78 (01) :115-127
[24]   Load Forecasting with Machine Learning and Deep Learning Methods [J].
Cordeiro-Costas, Moises ;
Villanueva, Daniel ;
Eguia-Oller, Pablo ;
Martinez-Comesana, Miguel ;
Ramos, Sergio .
APPLIED SCIENCES-BASEL, 2023, 13 (13)
[25]   Probabilistic Geomagnetic Storm Forecasting via Deep Learning [J].
Tasistro-Hart, Adrian ;
Grayver, Alexander ;
Kuvshinov, Alexey .
JOURNAL OF GEOPHYSICAL RESEARCH-SPACE PHYSICS, 2021, 126 (01)
[26]   Improving Model Chain Approaches for Probabilistic Solar Energy Forecasting through Post-processing and Machine Learning [J].
Horat, Nina ;
Klerings, Sina ;
Lerch, Sebastian .
ADVANCES IN ATMOSPHERIC SCIENCES, 2025, 42 (02) :297-312
[27]   The potential of machine learning for weather index insurance [J].
Cesarini, Luigi ;
Figueiredo, Rui ;
Monteleone, Beatrice ;
Martina, Mario L., V .
NATURAL HAZARDS AND EARTH SYSTEM SCIENCES, 2021, 21 (08) :2379-2405
[28]   Automated Weather Event Analysis with Machine Learning [J].
Hasan, Nasimul ;
Uddin, Md Taufeeq ;
Chowdhury, Nihad Karim .
2016 INTERNATIONAL CONFERENCE ON INNOVATIONS IN SCIENCE, ENGINEERING AND TECHNOLOGY (ICISET 2016), 2016,
[29]   Forecasting Solar Irradiance with Weather Classification and Chaotic Gravitational Search Algorithm Based Wavelet Kernel Extreme Learning Machine [J].
Pani, Alok Kumar ;
Nayak, Niranjan .
INTERNATIONAL JOURNAL OF RENEWABLE ENERGY RESEARCH, 2019, 9 (04) :1650-1659
[30]   Probabilistic models and machine learning in structural bioinformatics [J].
Hamelryck, Thomas .
STATISTICAL METHODS IN MEDICAL RESEARCH, 2009, 18 (05) :505-526