Journal article · 2024 · Open access

Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciarán

Andrew James Charlton-Perez, Helen Dacre, Simon Driscoll, Suzanne Louise Gray, Ben J. Harvey, Natalie J. Harvey, Kieran M. R. Hunt, Robert William Lee, Ranjini Swaminathan, Rémy Vandaele, Ambrogio Volonté

npj Climate and Atmospheric Science, 7(1) · Published 22 April 2024 · DOI 10.1038/s41612-024-00638-w

Free PDFView at the publisherCite this paper

In brief

“Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciarán” is a 2024 journal article by Andrew James Charlton-Perez and 10 co-authors, published in npj Climate and Atmospheric Science. OpenAlex counts 135 citations as of 15 November 2026, which puts it in the top 1% of works published in 2024 by citations. It is open access under a CC BY licence: the full text is free to read at npj Climate and Atmospheric Science.

Citations
135
Most cited in
2026 (65)
Field-weighted impact
19.56
References
39
Authors
11

Abstract

There has been huge recent interest in the potential of making operational weather forecasts using machine learning techniques. As they become a part of the weather forecasting toolbox, there is a pressing need to understand how well current machine learning models can simulate high-impact weather events. We compare short to medium-range forecasts of Storm Ciarán, a European windstorm that caused sixteen deaths and extensive damage in Northern Europe, made by machine learning and numerical weather prediction models. The four machine learning models considered (FourCastNet, Pangu-Weather, GraphCast and FourCastNet-v2) produce forecasts that accurately capture the synoptic-scale structure of the cyclone including the position of the cloud head, shape of the warm sector and location of the warm conveyor belt jet, and the large-scale dynamical drivers important for the rapid storm development such as the position of the storm relative to the upper-level jet exit. However, their ability to resolve the more detailed structures important for issuing weather warnings is more mixed. All of the machine learning models underestimate the peak amplitude of winds associated with the storm, only some machine learning models resolve the warm core seclusion and none of the machine learning models capture the sharp bent-back warm frontal gradient. Our study shows there is a great deal about the performance and properties of machine learning weather forecasts that can be derived from case studies of high-impact weather events such as Storm Ciarán.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Charlton-Perez, A. J., Dacre, H., Driscoll, S., Gray, S. L., Harvey, B. J., Harvey, N. J., Hunt, K. M. R., Lee, R. W., Swaminathan, R., Vandaele, R., & Volonté, A. (2024). Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciarán. npj Climate and Atmospheric Science, 7(1). https://doi.org/10.1038/s41612-024-00638-w

MLA 9

Charlton-Perez, Andrew James, et al. “Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciarán.” npj Climate and Atmospheric Science, vol. 7, no. 1, 2024. https://doi.org/10.1038/s41612-024-00638-w.

Chicago

Charlton-Perez, Andrew James, Helen Dacre, Simon Driscoll, Suzanne Louise Gray, Ben J. Harvey, Natalie J. Harvey, Kieran M. R. Hunt, et al. 2024. “Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciarán.” npj Climate and Atmospheric Science 7 (1). https://doi.org/10.1038/s41612-024-00638-w.

Harvard

Charlton-Perez, A. J. et al. (2024) ‘Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciarán’, npj Climate and Atmospheric Science, 7(1). doi:10.1038/s41612-024-00638-w.

IEEE

A. J. Charlton-Perez et al., “Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciarán,” npj Climate and Atmospheric Science, vol. 7, no. 1, 2024, doi: 10.1038/s41612-024-00638-w.

BibTeX

@article{charltonperez2024models,
  title     = {{Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciarán}},
  author    = {Charlton-Perez, Andrew James and Dacre, Helen and Driscoll, Simon and Gray, Suzanne Louise and Harvey, Ben J. and Harvey, Natalie J. and Hunt, Kieran M. R. and Lee, Robert William and Swaminathan, Ranjini and Vandaele, Rémy and Volonté, Ambrogio},
  journal   = {npj Climate and Atmospheric Science},
  year      = {2024},
  volume    = {7},
  number    = {1},
  doi       = {10.1038/s41612-024-00638-w},
  url       = {https://doi.org/10.1038/s41612-024-00638-w}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
20241515
20255555
20266565

Its field-weighted citation impact is 19.56: it has been cited 19.56 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Meteorological Phenomena and Simulations

  • numerical weather prediction
  • FourCastNet
  • Pangu-Weather
  • GraphCast
  • warm conveyor belt
  • high-impact weather

Work with this paper

Most-cited papers in Earth and Planetary Sciences

All highly cited Earth and Planetary Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Charlton-Perez, A. J., Dacre, H., Driscoll, S., Gray, S. L., Harvey, B. J., Harvey, N. J., Hunt, K. M. R., Lee, R. W., Swaminathan, R., Vandaele, R., & Volonté, A. (2024). Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciarán. npj Climate and Atmospheric Science, 7(1). https://doi.org/10.1038/s41612-024-00638-w

How many times has this paper been cited?

135 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at npj Climate and Atmospheric Science.

Who wrote this paper?

Andrew James Charlton-Perez, Helen Dacre, Simon Driscoll, Suzanne Louise Gray, Ben J. Harvey, Natalie J. Harvey, Kieran M. R. Hunt, Robert William Lee, Ranjini Swaminathan, Rémy Vandaele, Ambrogio Volonté.

What is the DOI of this paper?

10.1038/s41612-024-00638-w. The permanent link is https://doi.org/10.1038/s41612-024-00638-w.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.