The Rise of Data-Driven Weather Forecasting: A First Statistical Assessment of Machine Learning–Based Weather Forecasts in an Operational-Like Context

Zied Ben Bouallègue, Mariana Clare, Linus Magnusson, Estíbaliz Gascón, Michael Maier‐Gerber, Martin Janoušek, Mark John Rodwell, Florian Pinault et al.

Bulletin of the American Meteorological Society 2024 article cited by 211

importance 6/10 partially solved Meteorological Phenomena and Simulations weather forecasting stage: research

Traditional numerical weather prediction is so computationally costly that improvements via higher resolution or larger ensembles are hindered.

Accurate, cheaper forecasts improve weather warnings that protect lives, property, and economies.

Machine learning models trained on ERA5 reanalysis generate forecasts at much lower computational cost; this study provides a first statistical comparison of ML versus NWP forecasts in an operational-like context.

Abstract states ML forecasts are 'highly competitive in terms of accuracy' at much lower computational cost; no specific benchmark numbers in abstract.

Provides first operational-like statistical evidence that ML forecasts can rival NWP at far lower cost.

Venue Bulletin of the American Meteorological Society
Published 2024
Work type article
Authors Zied Ben Bouallègue, Mariana Clare, Linus Magnusson, Estíbaliz Gascón, Michael Maier‐Gerber, Martin Janoušek, Mark John Rodwell, Florian Pinault et al.
Citations 211 (OpenAlex, at import time)
References 37
Model or method not stated in source
Organization not stated in source
Primary source https://doi.org/10.1175/bams-d-23-0162.1
Open access bronze
Keywords machine learning, weather forecasting, numerical weather prediction, ERA5, forecast verification
6 / 10

significant — thousands to millions affected

Abstract states NWP computational cost greatly hinders resolution and ensemble improvements and that ML forecasts are highly competitive at much lower cost; first operational-like comparison, significant but no human-impact scale given.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

# Paper Year Citations Importance
1 Learning skillful medium-range global weather forecasting
Rémi Lam, Álvaro Sánchez‐González, Matthew Willson, Peter Wirnsberger,...
2023 1,416
8
2 Accurate medium-range global weather forecasting with 3D neural networks
Kaifeng Bi, Lingxi Xie, Hengheng Zhang, Xin Chen, Xiaotao Gu, Qi Chuan...
2023 1,631
8
3 FuXi: a cascade machine learning forecasting system for 15-day global weather forecast
Lei Chen, Xiaohui Zhong, Feng Zhang, Yuan Cheng, Yinghui Xu, Qi Yuan,...
2023 355
8
4 Skilful nowcasting of extreme precipitation with NowcastNet
Yuchen Zhang, Mingsheng Long, Kaiyuan Chen, Lanxiang Xing, Ronghua Jin...
2023 451
8
5 Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects
Natei Ermias Benti, Mesfin Diro Chaka, Addisu Gezahegn Semie
2023 378
8