Articles | Volume 17, issue 21
https://doi.org/10.5194/gmd-17-7915-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-17-7915-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Model evaluation paper
| 
07 Nov 2024
Model evaluation paper |
| 07 Nov 2024
| 07 Nov 2024
Do data-driven models beat numerical models in forecasting weather extremes? A comparison of IFS HRES, Pangu-Weather, and GraphCast
Leonardo Olivetti
CORRESPONDING AUTHOR
Department of Earth Sciences, Uppsala University, 75236 Uppsala, Sweden
Swedish Centre for Impacts of Climate Extremes (climes), Uppsala University, 75236 Uppsala, Sweden
Centre of Natural Hazards and Disaster Science (CNDS), Uppsala University, 75236 Uppsala, Sweden
Gabriele Messori
Department of Earth Sciences, Uppsala University, 75236 Uppsala, Sweden
Swedish Centre for Impacts of Climate Extremes (climes), Uppsala University, 75236 Uppsala, Sweden
Department of Meteorology and Bolin Centre for Climate Research, Stockholm University, 10691 Stockholm, Sweden
Viewed
Total article views: 13,181 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 10 Apr 2024)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 8,994 | 3,691 | 496 | 13,181 | 274 | 365 |
- HTML: 8,994
- PDF: 3,691
- XML: 496
- Total: 13,181
- BibTeX: 274
- EndNote: 365
Total article views: 8,109 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 07 Nov 2024)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 6,246 | 1,488 | 375 | 8,109 | 138 | 190 |
- HTML: 6,246
- PDF: 1,488
- XML: 375
- Total: 8,109
- BibTeX: 138
- EndNote: 190
Total article views: 5,072 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 10 Apr 2024)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 2,748 | 2,203 | 121 | 5,072 | 136 | 175 |
- HTML: 2,748
- PDF: 2,203
- XML: 121
- Total: 5,072
- BibTeX: 136
- EndNote: 175
Viewed (geographical distribution)
Total article views: 13,181 (including HTML, PDF, and XML)
Thereof 12,776 with geography defined
and 405 with unknown origin.
Total article views: 8,109 (including HTML, PDF, and XML)
Thereof 7,753 with geography defined
and 356 with unknown origin.
Total article views: 5,072 (including HTML, PDF, and XML)
Thereof 5,023 with geography defined
and 49 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
31 citations as recorded by crossref.
- Binned spectral power loss for improved prediction of chaotic systems D. Chakraborty et al. https://doi.org/10.1016/j.jcp.2026.114866
- Assessing the real-world economic value of weather forecasts for compounding extremes L. Olivetti et al. https://doi.org/10.1088/1748-9326/ae9327
- Skill assessment of AI-based weather model in heavy precipitation prediction over South Korea S. Hong et al. https://doi.org/10.1007/s00704-026-06536-w
- Increasing resolution and accuracy in sub-seasonal forecasting through 3D U-Net: the western US J. Ryu et al. https://doi.org/10.5194/gmd-19-27-2026
- Resolving the limits of MJO forecast skill: large-sample-based ensemble optimization in the IAP-CAS S2S model Y. Liu et al. https://doi.org/10.3389/fclim.2026.1828808
- Evaluating the Shanghai Typhoon Model against State-of-the-Art Machine-Learning Weather Prediction Models: A Case Study for Typhoon Danas (2025) Z. Niu et al. https://doi.org/10.1007/s00376-025-5464-8
- Can data-driven weather models accurately forecast atmospheric rivers? F. Lopez-Marti et al. https://doi.org/10.1088/1748-9326/ae1e8e
- Ensemble Experiments in an AI-NWP Coupled Framework: A Typhoon Case Y. Ge et al. https://doi.org/10.1007/s13351-025-5038-9
- Evaluating deep learning-integrated physics-based models for tropical cyclone track and intensity predictions Y. Zeng et al. https://doi.org/10.1063/5.0303579
- Forecast-based attribution of extratropical cyclones using AI weather models B. Jiménez-Esteve et al. https://doi.org/10.1088/2752-5295/ae714b
- Machine learning advances and data model coevolution in geoscience A. Eltijnai & M. Mohammed https://doi.org/10.1007/s44288-026-00524-3
- Explaining AI’s successes: A no miracles argument for quasi-representations D. Rowbottom & A. Curtis-Trudel https://doi.org/10.1007/s11229-026-05525-w
- The potential of AI global weather models for reference evapotranspiration forecasting: a comparison with numerical weather prediction models S. Zhao et al. https://doi.org/10.1016/j.jhydrol.2025.134363
- Toward Operational Heat-Stress Early Warnings in Southern South America: AI-Based UTCI Forecasting S. Collazo et al. https://doi.org/10.1007/s41748-026-01194-4
- Impact of AIFS and GFS Initialization on WRF Operational Forecasts During High-Impact Storms in Spain (2025) R. Arasa Agudo et al. https://doi.org/10.3390/earth7030077
- Whose weather is it? A fairness framework for data-driven weather forecasting L. Olivetti & G. Messori https://doi.org/10.1088/1748-9326/ae21f5
- Effectiveness of machine learning and deep learning techniques for multi-horizon weather forecasting A. Sami et al. https://doi.org/10.1007/s00703-026-01183-2
- Data-driven forecasts of extreme weather in East Asia: feasibility of operational use S. Oh et al. https://doi.org/10.1016/j.wace.2026.100875
- Foundation Models of Ocean and Atmosphere in 2025: Milestones and Perspectives M. Krinitskiy https://doi.org/10.3103/S0027134925703084
- Fusion of multi-source precipitation records via coordinate-based generative models S. Sun et al. https://doi.org/10.1038/s41467-025-67987-9
- 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
- Evaluating the skill of AI and physics-based models for February 2020 North Atlantic storm hazards H. Afargan-Gerstman et al. https://doi.org/10.1038/s44304-026-00223-6
- Physics-based models outperform AI weather forecasts of record-breaking extremes Z. Zhang et al. https://doi.org/10.1126/sciadv.aec1433
- An extension of WeatherBench 2 to binary hydroclimatic forecasts T. Zhao et al. https://doi.org/10.5194/gmd-18-5781-2025
- A Hybrid Machine Learning–numerical Coupling Method for Regional Typhoon Forecasting Z. CHEN et al. https://doi.org/10.3724/j.1006-8775.2026.030
- A Modeling Effort for Medium-Range Weather Prediction over India with a Modified Pangu-Weather Architecture A. Choudhury et al. https://doi.org/10.1007/s13143-026-00458-3
- MoTiF: a self-supervised model for multi-source forecasting with application to tropical cyclones C. Dauvilliers & C. Monteleoni https://doi.org/10.1017/eds.2025.10014
- Comparative insights into short-term streamflow forecasting in navigating urban flood risks R. Prakash & J. Tripura https://doi.org/10.1680/jwama.25.00076
- Precipitation science: State-of-the-Art in measurement, estimation, and modeling F. Tapiador et al. https://doi.org/10.1016/j.atmosres.2026.109278
- Data-Driven Mesoscale Weather Forecasting Combining Swin-Unet and Diffusion Models Y. Hirabayashi & D. Matsuoka https://doi.org/10.2151/sola.2025-062
- Machine learning is revolutionizing weather forecasting - the next step is a change in how we work P. Dueben et al. https://doi.org/10.1016/j.jemets.2026.100050
31 citations as recorded by crossref.
- Binned spectral power loss for improved prediction of chaotic systems D. Chakraborty et al. https://doi.org/10.1016/j.jcp.2026.114866
- Assessing the real-world economic value of weather forecasts for compounding extremes L. Olivetti et al. https://doi.org/10.1088/1748-9326/ae9327
- Skill assessment of AI-based weather model in heavy precipitation prediction over South Korea S. Hong et al. https://doi.org/10.1007/s00704-026-06536-w
- Increasing resolution and accuracy in sub-seasonal forecasting through 3D U-Net: the western US J. Ryu et al. https://doi.org/10.5194/gmd-19-27-2026
- Resolving the limits of MJO forecast skill: large-sample-based ensemble optimization in the IAP-CAS S2S model Y. Liu et al. https://doi.org/10.3389/fclim.2026.1828808
- Evaluating the Shanghai Typhoon Model against State-of-the-Art Machine-Learning Weather Prediction Models: A Case Study for Typhoon Danas (2025) Z. Niu et al. https://doi.org/10.1007/s00376-025-5464-8
- Can data-driven weather models accurately forecast atmospheric rivers? F. Lopez-Marti et al. https://doi.org/10.1088/1748-9326/ae1e8e
- Ensemble Experiments in an AI-NWP Coupled Framework: A Typhoon Case Y. Ge et al. https://doi.org/10.1007/s13351-025-5038-9
- Evaluating deep learning-integrated physics-based models for tropical cyclone track and intensity predictions Y. Zeng et al. https://doi.org/10.1063/5.0303579
- Forecast-based attribution of extratropical cyclones using AI weather models B. Jiménez-Esteve et al. https://doi.org/10.1088/2752-5295/ae714b
- Machine learning advances and data model coevolution in geoscience A. Eltijnai & M. Mohammed https://doi.org/10.1007/s44288-026-00524-3
- Explaining AI’s successes: A no miracles argument for quasi-representations D. Rowbottom & A. Curtis-Trudel https://doi.org/10.1007/s11229-026-05525-w
- The potential of AI global weather models for reference evapotranspiration forecasting: a comparison with numerical weather prediction models S. Zhao et al. https://doi.org/10.1016/j.jhydrol.2025.134363
- Toward Operational Heat-Stress Early Warnings in Southern South America: AI-Based UTCI Forecasting S. Collazo et al. https://doi.org/10.1007/s41748-026-01194-4
- Impact of AIFS and GFS Initialization on WRF Operational Forecasts During High-Impact Storms in Spain (2025) R. Arasa Agudo et al. https://doi.org/10.3390/earth7030077
- Whose weather is it? A fairness framework for data-driven weather forecasting L. Olivetti & G. Messori https://doi.org/10.1088/1748-9326/ae21f5
- Effectiveness of machine learning and deep learning techniques for multi-horizon weather forecasting A. Sami et al. https://doi.org/10.1007/s00703-026-01183-2
- Data-driven forecasts of extreme weather in East Asia: feasibility of operational use S. Oh et al. https://doi.org/10.1016/j.wace.2026.100875
- Foundation Models of Ocean and Atmosphere in 2025: Milestones and Perspectives M. Krinitskiy https://doi.org/10.3103/S0027134925703084
- Fusion of multi-source precipitation records via coordinate-based generative models S. Sun et al. https://doi.org/10.1038/s41467-025-67987-9
- 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
- Evaluating the skill of AI and physics-based models for February 2020 North Atlantic storm hazards H. Afargan-Gerstman et al. https://doi.org/10.1038/s44304-026-00223-6
- Physics-based models outperform AI weather forecasts of record-breaking extremes Z. Zhang et al. https://doi.org/10.1126/sciadv.aec1433
- An extension of WeatherBench 2 to binary hydroclimatic forecasts T. Zhao et al. https://doi.org/10.5194/gmd-18-5781-2025
- A Hybrid Machine Learning–numerical Coupling Method for Regional Typhoon Forecasting Z. CHEN et al. https://doi.org/10.3724/j.1006-8775.2026.030
- A Modeling Effort for Medium-Range Weather Prediction over India with a Modified Pangu-Weather Architecture A. Choudhury et al. https://doi.org/10.1007/s13143-026-00458-3
- MoTiF: a self-supervised model for multi-source forecasting with application to tropical cyclones C. Dauvilliers & C. Monteleoni https://doi.org/10.1017/eds.2025.10014
- Comparative insights into short-term streamflow forecasting in navigating urban flood risks R. Prakash & J. Tripura https://doi.org/10.1680/jwama.25.00076
- Precipitation science: State-of-the-Art in measurement, estimation, and modeling F. Tapiador et al. https://doi.org/10.1016/j.atmosres.2026.109278
- Data-Driven Mesoscale Weather Forecasting Combining Swin-Unet and Diffusion Models Y. Hirabayashi & D. Matsuoka https://doi.org/10.2151/sola.2025-062
- Machine learning is revolutionizing weather forecasting - the next step is a change in how we work P. Dueben et al. https://doi.org/10.1016/j.jemets.2026.100050
Saved (final revised paper)
Latest update: 30 Sep 2026
Short summary
Data-driven models are becoming a viable alternative to physics-based models for weather forecasting up to 15 d into the future. However, it is unclear whether they are as reliable as physics-based models when forecasting weather extremes. We evaluate their performance in forecasting near-surface cold, hot, and windy extremes globally. We find that data-driven models can compete with physics-based models and that the choice of the best model mainly depends on the region and type of extreme.
Data-driven models are becoming a viable alternative to physics-based models for weather...
