Preprints
https://doi.org/10.5194/egusphere-2023-350
https://doi.org/10.5194/egusphere-2023-350
17 Apr 2023
 | 17 Apr 2023

Machine Learning for numerical weather and climate modelling: a review

Catherine Odelia de Burgh-Day and Tennessee Leeuwenburg

Abstract. Machine learning (ML) is increasing in popularity in the field of weather and climate modelling. Applications range from improved solvers and preconditioners, to parametrisation scheme emulation and replacement, and recently even to full ML-based weather and climate prediction models. While ML has been used in this space for more than 25 years, it is only in the last 10 or so years that progress has accelerated to the point that ML applications are becoming competitive with numerical knowledge-based alternatives. In this review, we provide a roughly chronological summary of the application of ML to aspects of weather and climate modelling from early publications through to the latest progress at the time of writing. We also provide an overview of key ML concepts and terms. Our aim is to provide a primer for researchers and model developers to rapidly familiarize and update themselves with the world of ML in the context of weather and climate models.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.

Journal article(s) based on this preprint

14 Nov 2023
| Review and perspective paper
| Highlight paper
Machine learning for numerical weather and climate modelling: a review
Catherine O. de Burgh-Day and Tennessee Leeuwenburg
Geosci. Model Dev., 16, 6433–6477, https://doi.org/10.5194/gmd-16-6433-2023,https://doi.org/10.5194/gmd-16-6433-2023, 2023
Short summary Executive editor
Catherine Odelia de Burgh-Day and Tennessee Leeuwenburg

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2023-350', Anonymous Referee #1, 17 May 2023
    • AC1: 'Reply on RC1', Catherine de Burgh-Day, 08 Jun 2023
  • RC2: 'Comment on egusphere-2023-350', Anonymous Referee #2, 09 Jun 2023
    • RC3: 'a quick addition', Anonymous Referee #2, 09 Jun 2023
    • AC2: 'Reply on RC2', Catherine de Burgh-Day, 23 Jun 2023

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2023-350', Anonymous Referee #1, 17 May 2023
    • AC1: 'Reply on RC1', Catherine de Burgh-Day, 08 Jun 2023
  • RC2: 'Comment on egusphere-2023-350', Anonymous Referee #2, 09 Jun 2023
    • RC3: 'a quick addition', Anonymous Referee #2, 09 Jun 2023
    • AC2: 'Reply on RC2', Catherine de Burgh-Day, 23 Jun 2023

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision | EF: Editorial file upload
AR by Catherine de Burgh-Day on behalf of the Authors (21 Jul 2023)  Author's response   Author's tracked changes   Manuscript 
ED: Referee Nomination & Report Request started (25 Jul 2023) by Paul Ullrich
RR by Anonymous Referee #2 (29 Jul 2023)
RR by Anonymous Referee #1 (31 Aug 2023)
ED: Publish as is (12 Sep 2023) by Paul Ullrich
ED: Publish as is (12 Sep 2023) by David Ham (Executive editor)
AR by Catherine de Burgh-Day on behalf of the Authors (21 Sep 2023)

Journal article(s) based on this preprint

14 Nov 2023
| Review and perspective paper
| Highlight paper
Machine learning for numerical weather and climate modelling: a review
Catherine O. de Burgh-Day and Tennessee Leeuwenburg
Geosci. Model Dev., 16, 6433–6477, https://doi.org/10.5194/gmd-16-6433-2023,https://doi.org/10.5194/gmd-16-6433-2023, 2023
Short summary Executive editor
Catherine Odelia de Burgh-Day and Tennessee Leeuwenburg
Catherine Odelia de Burgh-Day and Tennessee Leeuwenburg

Viewed

Total article views: 2,158 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
1,131 995 32 2,158 17 12
  • HTML: 1,131
  • PDF: 995
  • XML: 32
  • Total: 2,158
  • BibTeX: 17
  • EndNote: 12
Views and downloads (calculated since 17 Apr 2023)
Cumulative views and downloads (calculated since 17 Apr 2023)

Viewed (geographical distribution)

Total article views: 2,127 (including HTML, PDF, and XML) Thereof 2,127 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 03 Sep 2024
Download

The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.

Machine Learning is a rapidly expanding technique in the field of weather and climate modelling. This paper takes stock of the state of the field at the present time, and will be invaluable to participants across the field and beyond who wish to understand the impact of Machine Learning on the field, its limitations, and current scope.
Short summary
Machine learning (ML) is an increasingly popular tool in the field of weather and climate modelling. It has been used to improve many components of these models, and even the entire model. While ML has been used in this space for a long time, it is only recently that ML approaches have become competitive with more traditional approaches. In this review, we have summarized the use of ML in weather and climate modelling over time, and have also provided an overview of key ML concepts and terms.