Articles | Volume 18, issue 17
https://doi.org/10.5194/gmd-18-5575-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Special issue:
https://doi.org/10.5194/gmd-18-5575-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Huge ensembles – Part 1: Design of ensemble weather forecasts using spherical Fourier neural operators
Ankur Mahesh
CORRESPONDING AUTHOR
Earth and Environmental Sciences Area, Lawrence Berkeley National Laboratory (LBNL), Berkeley, California, USA
Department of Earth and Planetary Science, University of California, Berkeley, USA
William D. Collins
Earth and Environmental Sciences Area, Lawrence Berkeley National Laboratory (LBNL), Berkeley, California, USA
Department of Earth and Planetary Science, University of California, Berkeley, USA
Boris Bonev
NVIDIA Corporation, Santa Clara, California, USA
Noah Brenowitz
NVIDIA Corporation, Santa Clara, California, USA
Yair Cohen
NVIDIA Corporation, Santa Clara, California, USA
Joshua Elms
Department of Earth and Atmospheric Sciences, Indiana University, Bloomington, Indiana, USA
Peter Harrington
National Energy Research Scientific Computing Center (NERSC), LBNL, Berkeley, California, USA
Karthik Kashinath
NVIDIA Corporation, Santa Clara, California, USA
Thorsten Kurth
NVIDIA Corporation, Santa Clara, California, USA
Joshua North
Earth and Environmental Sciences Area, Lawrence Berkeley National Laboratory (LBNL), Berkeley, California, USA
Travis O'Brien
Department of Earth and Atmospheric Sciences, Indiana University, Bloomington, Indiana, USA
Michael Pritchard
NVIDIA Corporation, Santa Clara, California, USA
Department of Earth System Science, University of California, Irvine, USA
David Pruitt
NVIDIA Corporation, Santa Clara, California, USA
Mark Risser
Earth and Environmental Sciences Area, Lawrence Berkeley National Laboratory (LBNL), Berkeley, California, USA
Shashank Subramanian
National Energy Research Scientific Computing Center (NERSC), LBNL, Berkeley, California, USA
Jared Willard
National Energy Research Scientific Computing Center (NERSC), LBNL, Berkeley, California, USA
Viewed
Since the preprint corresponding to this journal article was posted outside of Copernicus Publications, the preprint-related metrics are limited to HTML views.
Total article views: 8,686 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 02 Oct 2024)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 7,112 | 1,453 | 121 | 8,686 | 119 | 143 |
- HTML: 7,112
- PDF: 1,453
- XML: 121
- Total: 8,686
- BibTeX: 119
- EndNote: 143
Total article views: 6,459 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 04 Sep 2025)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 4,898 | 1,453 | 108 | 6,459 | 119 | 143 |
- HTML: 4,898
- PDF: 1,453
- XML: 108
- Total: 6,459
- BibTeX: 119
- EndNote: 143
Total article views: 2,227 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 02 Oct 2024)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 2,214 | 0 | 13 | 2,227 | 0 | 0 |
- HTML: 2,214
- PDF: 0
- XML: 13
- Total: 2,227
- BibTeX: 0
- EndNote: 0
Viewed (geographical distribution)
Since the preprint corresponding to this journal article was posted outside of Copernicus Publications, the preprint-related metrics are limited to HTML views.
Total article views: 8,686 (including HTML, PDF, and XML)
Thereof 8,411 with geography defined
and 275 with unknown origin.
Total article views: 6,459 (including HTML, PDF, and XML)
Thereof 6,205 with geography defined
and 254 with unknown origin.
Total article views: 2,227 (including HTML, PDF, and XML)
Thereof 2,206 with geography defined
and 21 with unknown origin.
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
Cited
11 citations as recorded by crossref.
- Bridging the weather and climate divide with artificial intelligence G. Camps-Valls et al. https://doi.org/10.1038/s41467-026-75787-y
- Huge ensembles – Part 2: Properties of a huge ensemble of hindcasts generated with spherical Fourier neural operators A. Mahesh et al. https://doi.org/10.5194/gmd-18-5605-2025
- AI-Boosted Rare Event Sampling to Characterize Extreme Weather A. Lancelin et al. https://doi.org/10.1103/b1gc-9c2q
- Kilometer-scale convection-allowing model emulation using generative diffusion modeling J. Pathak et al. https://doi.org/10.1126/sciadv.adv0423
- Samudra: An AI Global Ocean Emulator for Climate S. Dheeshjith et al. https://doi.org/10.1029/2024GL114318
- A Practical Probabilistic Benchmark for AI Weather Models N. Brenowitz et al. https://doi.org/10.1029/2024GL113656
- Investigation of local scour predictions beneath a submerged cylinder using Fourier neural operator variants H. Nazari et al. https://doi.org/10.1063/5.0321428
- Spread/error relationship and spatial error representation in precipitation nowcasting: comparison of STEPS and generative AI M. Bonte et al. https://doi.org/10.5194/wcd-7-1837-2026
- Snow-eater heat waves of the western United States A. Rhoades et al. https://doi.org/10.1126/sciadv.aeb3361
- Evaluation of AI-based seasonal weather ensembles as input for fluvial flood risk estimation: a case study over the Elbe basin J. Ashcroft et al. https://doi.org/10.5194/nhess-26-3129-2026
- Boosting weather forecast via generative superensemble C. Nai et al. https://doi.org/10.1038/s41612-025-01255-x
11 citations as recorded by crossref.
- Bridging the weather and climate divide with artificial intelligence G. Camps-Valls et al. https://doi.org/10.1038/s41467-026-75787-y
- Huge ensembles – Part 2: Properties of a huge ensemble of hindcasts generated with spherical Fourier neural operators A. Mahesh et al. https://doi.org/10.5194/gmd-18-5605-2025
- AI-Boosted Rare Event Sampling to Characterize Extreme Weather A. Lancelin et al. https://doi.org/10.1103/b1gc-9c2q
- Kilometer-scale convection-allowing model emulation using generative diffusion modeling J. Pathak et al. https://doi.org/10.1126/sciadv.adv0423
- Samudra: An AI Global Ocean Emulator for Climate S. Dheeshjith et al. https://doi.org/10.1029/2024GL114318
- A Practical Probabilistic Benchmark for AI Weather Models N. Brenowitz et al. https://doi.org/10.1029/2024GL113656
- Investigation of local scour predictions beneath a submerged cylinder using Fourier neural operator variants H. Nazari et al. https://doi.org/10.1063/5.0321428
- Spread/error relationship and spatial error representation in precipitation nowcasting: comparison of STEPS and generative AI M. Bonte et al. https://doi.org/10.5194/wcd-7-1837-2026
- Snow-eater heat waves of the western United States A. Rhoades et al. https://doi.org/10.1126/sciadv.aeb3361
- Evaluation of AI-based seasonal weather ensembles as input for fluvial flood risk estimation: a case study over the Elbe basin J. Ashcroft et al. https://doi.org/10.5194/nhess-26-3129-2026
- Boosting weather forecast via generative superensemble C. Nai et al. https://doi.org/10.1038/s41612-025-01255-x
Saved (final revised paper)
Latest update: 24 Sep 2026
Short summary
Simulating extreme weather events in a warming world is a challenging task for current weather and climate models. These models' computational cost poses a challenge in studying low-probability extreme weather. We use machine learning to construct a new probabilistic system. We give an in-depth explanation of how we constructed this system. We present a thorough pipeline to validate our method. Our method requires fewer computational resources than existing weather and climate models.
Simulating extreme weather events in a warming world is a challenging task for current weather...