Evaluating Machine‐Learning Weather Prediction for UK Windstorm Weather Warnings
Meteorological Applications · 2026-11 · 33 (6)
DOI: 10.1002/met.70261 ↗Kurz gefasst
Fachartikel in der Zeitschrift Meteorological Applications, online erschienen am 29.10.2026. Verfasst von James Hewitt und 9 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Environment Research Council, National Center for Atmospheric Research.
Abstract (Originalsprache)
Machine‐learning weather prediction (MLWP) has emerged as a powerful new forecasting tool, with the potential to complement or even replace numerical weather prediction (NWP) in early warning systems. MLWP models are computationally cheap once trained, offering more timely, accessible, and energy‐efficient forecasts than NWP. Yet their ability to capture weather extremes, particularly strong winds associated with extra‐tropical cyclones, remains insufficiently understood. This study provides the first comprehensive evaluation of MLWP performance for dynamically diverse UK windstorms, addressing a critical evidence gap before these models can be responsibly deployed in weather risk management. We evaluate eight state‐of‐the‐art MLWP models against reanalysis, NWP analysis, and an operational NWP ensemble for six contrasting UK cyclones from winter 2023/24. We find substantial inter‐storm and inter‐model variability in forecast skill at 24‐h lead time. Forecast accuracy is found to be linked to the underlying atmospheric dynamics and spatial scales of the wind‐producing features: wind maxima associated with mesoscale structures are systematically underestimated across all MLWP models. Significant variability is also found in the representation of mesoscale storm structure, and the highest‐resolution MLWP model (Aurora‐0.1) does not deliver uniform improvements across the cyclone set. In‐depth analysis of two mature Shapiro–Keyser cyclones reveals a consistent tendency for MLWP models to smooth sharp frontal gradients and misrepresent key mesoscale features, including bent‐back warm fronts and frontal‐fracture regions. These deficiencies are physically consistent with the underestimation of localised extreme winds. Overall, our findings highlight the current limitations of MLWP for underpinning UK wind warnings. While these models are not yet suitable to replace NWP for hazardous windstorm prediction entirely, their demonstrated skill in capturing storm tracks and synoptic‐scale evolution points to promising complementary roles in future national weather forecasting and resilience frameworks.
Förderung
- Natural Environment Research Council
- National Center for Atmospheric Research
Zitieren
APA
Hewitt, J., Volonté, A., Harvey, B., Cardoso, A. A., Hunt, K. M. R., Harvey, N. J., Martinez‐Alvarado, O., Gray, S. L., Dacre, H. F., & Jones, T. R. (2026). Evaluating Machine‐Learning Weather Prediction for UK Windstorm Weather Warnings. Meteorological Applications, 33(6). https://doi.org/10.1002/met.70261
Vancouver
Hewitt J, Volonté A, Harvey B, Cardoso AA, Hunt KMR, Harvey NJ, et al. Evaluating Machine‐Learning Weather Prediction for UK Windstorm Weather Warnings. Meteorological Applications. 2026;33(6). doi:10.1002/met.70261
BibTeX
@article{Hewitt2026,
author = {Hewitt, James and Volonté, Ambrogio and Harvey, Ben and Cardoso, Andressa Andrade and Hunt, Kieran M. R. and Harvey, Natalie J. and Martinez‐Alvarado, Oscar and Gray, Suzanne L. and Dacre, Helen F. and Jones, Todd R.},
title = {Evaluating Machine‐Learning Weather Prediction for UK Windstorm Weather Warnings},
journal = {Meteorological Applications},
year = {2026},
volume = {33},
number = {6},
doi = {10.1002/met.70261}
}
EUVIMED