Neural general circulation models for weather and climate

Dmitrii Kochkov (), Janni Yuval (), Ian Langmore, Peter Norgaard, Jamie Smith, Griffin Mooers, Milan Klöwer, James Lottes, Stephan Rasp, Peter Düben, Sam Hatfield, Peter Battaglia, Alvaro Sanchez-Gonzalez, Matthew Willson, Michael P. Brenner and Stephan Hoyer ()
Additional contact information
Dmitrii Kochkov: Google Research
Janni Yuval: Google Research
Ian Langmore: Google Research
Peter Norgaard: Google Research
Jamie Smith: Google Research
Griffin Mooers: Google Research
Milan Klöwer: Massachusetts Institute of Technology
James Lottes: Google Research
Stephan Rasp: Google Research
Peter Düben: European Centre for Medium-Range Weather Forecasts
Sam Hatfield: European Centre for Medium-Range Weather Forecasts
Peter Battaglia: Google DeepMind
Alvaro Sanchez-Gonzalez: Google DeepMind
Matthew Willson: Google DeepMind
Michael P. Brenner: Google Research
Stephan Hoyer: Google Research

Nature, 2024, vol. 632, issue 8027, 1060-1066

Abstract: Abstract General circulation models (GCMs) are the foundation of weather and climate prediction1,2. GCMs are physics-based simulators that combine a numerical solver for large-scale dynamics with tuned representations for small-scale processes such as cloud formation. Recently, machine-learning models trained on reanalysis data have achieved comparable or better skill than GCMs for deterministic weather forecasting3,4. However, these models have not demonstrated improved ensemble forecasts, or shown sufficient stability for long-term weather and climate simulations. Here we present a GCM that combines a differentiable solver for atmospheric dynamics with machine-learning components and show that it can generate forecasts of deterministic weather, ensemble weather and climate on par with the best machine-learning and physics-based methods. NeuralGCM is competitive with machine-learning models for one- to ten-day forecasts, and with the European Centre for Medium-Range Weather Forecasts ensemble prediction for one- to fifteen-day forecasts. With prescribed sea surface temperature, NeuralGCM can accurately track climate metrics for multiple decades, and climate forecasts with 140-kilometre resolution show emergent phenomena such as realistic frequency and trajectories of tropical cyclones. For both weather and climate, our approach offers orders of magnitude computational savings over conventional GCMs, although our model does not extrapolate to substantially different future climates. Our results show that end-to-end deep learning is compatible with tasks performed by conventional GCMs and can enhance the large-scale physical simulations that are essential for understanding and predicting the Earth system.

Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41586-024-07744-y Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nature:v:632:y:2024:i:8027:d:10.1038_s41586-024-07744-y

Ordering information: This journal article can be ordered from
https://www.nature.com/

DOI: 10.1038/s41586-024-07744-y

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

More articles in Nature from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().