{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T06:04:11Z","timestamp":1789625051527,"version":"build-2803163510"},"reference-count":75,"publisher":"Springer Science and Business Media LLC","issue":"8132","license":[{"start":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T00:00:00Z","timestamp":1785974400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T00:00:00Z","timestamp":1788912000000},"content-version":"vor","delay-in-days":34,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nature"],"published-print":{"date-parts":[[2026,9,17]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Tropical cyclones are among the most dangerous and costly weather phenomena, but forecasting them remains challenging. Here we introduce WeatherNext Cyclones (WN-C), an artificial intelligence (AI)-based operational weather model that produces state-of-the-art ensemble forecasts of the track, intensity and size of tropical cyclones worldwide. Trained on a combination of global analysis data\n                    <jats:sup>1<\/jats:sup>\n                    and a global database of historical tropical cyclones\n                    <jats:sup>2,3<\/jats:sup>\n                    , WN-C generates large ensembles of possible global weather and cyclone scenarios extending 15 days into the future. When evaluated on tropical cyclones from 2023 to 2025, the track, intensity and wind-radius predictions from WN-C offer an average lead-time advantage of 1\u2009day or more over leading operational models\u2014an improvement in accuracy comparable to the progress seen in the last decade of operational development. We achieved these results using inputs that are orders of magnitude coarser than regional models, suggesting that high resolution is not a strict prerequisite for state-of-the-art intensity forecasting and that these coarse atmospheric data contain more intensity signal than has been previously recognized. Including predictions from WN-C in a weighted-average consensus ensemble improves its skill substantially. The scalability of WN-C enables ensembles of up to 1,000 members, which are better at capturing rare events than conventional 50-member ensembles. By providing advanced operational ensemble\u00a0guidance to human forecasters, this work represents a step change towards more reliable and timely forecasts and warnings that can help to protect lives and to mitigate the devastating effects of tropical cyclones.\n                  <\/jats:p>","DOI":"10.1038\/s41586-026-10953-2","type":"journal-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T15:01:40Z","timestamp":1786028500000},"page":"680-688","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Operational tropical\u00a0cyclone forecasting with AI"],"prefix":"10.1038","volume":"657","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3059-0062","authenticated-orcid":false,"given":"Ferran","family":"Alet","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1556-9932","authenticated-orcid":false,"given":"Tom R.","family":"Andersson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4765-2703","authenticated-orcid":false,"given":"Ilan","family":"Price","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0434-6523","authenticated-orcid":false,"given":"Stratis","family":"Markou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6510-0831","authenticated-orcid":false,"given":"Andrew","family":"El-Kadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6945-8325","authenticated-orcid":false,"given":"Dominic","family":"Masters","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amy","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samier","family":"Merchant","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9281-1316","authenticated-orcid":false,"given":"Natalie","family":"Williams","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gregory","family":"Thornton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ken","family":"MacKay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivia","family":"Graham","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akib","family":"Uddin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ben","family":"Gaiarin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Devaja","family":"Shah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elinor","family":"Kruse","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wallace","family":"Hogsett","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Zelinsky","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Cangialosi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0510-5982","authenticated-orcid":false,"given":"Jonathan","family":"Martinez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Franklin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"DeMaria","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5394-3913","authenticated-orcid":false,"given":"Kate","family":"Musgrave","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2993-9308","authenticated-orcid":false,"given":"Caroline L.","family":"Bain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1654-9826","authenticated-orcid":false,"given":"Helen","family":"Titley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7859-3384","authenticated-orcid":false,"given":"Jacklynn","family":"Stott","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4222-5358","authenticated-orcid":false,"given":"Remi","family":"Lam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaron","family":"Bell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Komarek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8730-1927","authenticated-orcid":false,"given":"Matthew","family":"Willson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alvaro","family":"Sanchez-Gonzalez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3622-7111","authenticated-orcid":false,"given":"Peter","family":"Battaglia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,6]]},"reference":[{"key":"10953_CR1","doi-asserted-by":"publisher","first-page":"1999","DOI":"10.1002\/qj.3803","volume":"146","author":"H Hersbach","year":"2020","unstructured":"Hersbach, H. et al. The ERA5 global reanalysis. Q. J. R. Meteorol. Soc. 146, 1999\u20132049 (2020).","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"10953_CR2","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1175\/2009BAMS2755.1","volume":"91","author":"KR Knapp","year":"2010","unstructured":"Knapp, K. R., Kruk, M. C., Levinson, D. H., Diamond, H. J. & Neumann, C. J. The international best track archive for climate stewardship (IBTrACS): unifying tropical cyclone data. Bull. Am. Meteorol. Soc. 91, 363\u2013376 (2010).","journal-title":"Bull. Am. Meteorol. Soc."},{"key":"10953_CR3","doi-asserted-by":"publisher","unstructured":"Gahtan, J. et al. International best track archive for climate stewardship (IBTrACS) project, version 4r01. NOAA National Centers for Environmental Information https:\/\/doi.org\/10.25921\/82ty-9e16 (2024).","DOI":"10.25921\/82ty-9e16"},{"key":"10953_CR4","unstructured":"World Meteorological Organization. WMO Atlas of Mortality and Economic Losses from Weather, Climate and Water Extremes (1970\u20132019) (WMO, 2021)."},{"key":"10953_CR5","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/s00703-003-0055-6","volume":"87","author":"Y Wang","year":"2004","unstructured":"Wang, Y. & Wu, C.-C. Current understanding of tropical cyclone structure and intensity changes\u2013a review. Meteorol. Atmos. Phys. 87, 257\u2013278 (2004).","journal-title":"Meteorol. Atmos. Phys."},{"key":"10953_CR6","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.tcrr.2023.05.001","volume":"12","author":"X Chen","year":"2023","unstructured":"Chen, X. et al. Research advances on internal processes affecting tropical cyclone intensity change from 2018\u20132022. Trop. Cyclone Res. Rev. 12, 10\u201329 (2023).","journal-title":"Trop. Cyclone Res. Rev."},{"key":"10953_CR7","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/j.tcrr.2023.11.003","volume":"12","author":"JP Dunion","year":"2023","unstructured":"Dunion, J. P. et al. Recommendations for improved tropical cyclone formation and position probabilistic forecast products. Trop. Cyclone Res. Rev. 12, 241\u2013258 (2023).","journal-title":"Trop. Cyclone Res. Rev."},{"key":"10953_CR8","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.tcrr.2023.05.004","volume":"12","author":"Z Zhang","year":"2023","unstructured":"Zhang, Z. et al. A review of recent advances (2018\u20132021) on tropical cyclone intensity change from operational perspectives, part 1: dynamical model guidance. Trop. Cyclone Res. Rev. 12, 30\u201349 (2023).","journal-title":"Trop. Cyclone Res. Rev."},{"key":"10953_CR9","doi-asserted-by":"publisher","unstructured":"ECMWF in IFS Documentation CY46R1 https:\/\/doi.org\/10.21957\/38yug0cev (2019).","DOI":"10.21957\/38yug0cev"},{"key":"10953_CR10","doi-asserted-by":"publisher","first-page":"E680","DOI":"10.1175\/BAMS-D-20-0134.1","volume":"103","author":"GJ Alaka","year":"2022","unstructured":"Alaka, G. J., Zhang, X. & Gopalakrishnan, S. G. High-definition hurricanes: Improving forecasts with storm-following nests. Bull. Am. Meteorol. Soc. 103, E680\u2013E703 (2022).","journal-title":"Bull. Am. Meteorol. Soc."},{"key":"10953_CR11","doi-asserted-by":"publisher","first-page":"1416","DOI":"10.1126\/science.adi2336","volume":"382","author":"R Lam","year":"2023","unstructured":"Lam, R. et al. Learning skillful medium-range global weather forecasting. Science 382, 1416\u20131421 (2023).","journal-title":"Science"},{"key":"10953_CR12","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/s41586-023-06185-3","volume":"619","author":"K Bi","year":"2023","unstructured":"Bi, K. et al. Accurate medium-range global weather forecasting with 3D neural networks. Nature 619, 533\u2013538 (2023).","journal-title":"Nature"},{"key":"10953_CR13","doi-asserted-by":"publisher","first-page":"1060","DOI":"10.1038\/s41586-024-07744-y","volume":"632","author":"D Kochkov","year":"2024","unstructured":"Kochkov, D. et al. Neural general circulation models for weather and climate. Nature 632, 1060\u20131066 (2024).","journal-title":"Nature"},{"key":"10953_CR14","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1038\/s41586-024-08252-9","volume":"637","author":"I Price","year":"2025","unstructured":"Price, I. et al. Probabilistic weather forecasting with machine learning. Nature 637, 84\u201390 (2025).","journal-title":"Nature"},{"key":"10953_CR15","volume":"4","author":"M DeMaria","year":"2025","unstructured":"DeMaria, M. et al. An operations-based evaluation of tropical cyclone track and intensity forecasts from artificial intelligence weather prediction models. Artif. Intell. Earth Syst. 4, e240085 (2025).","journal-title":"Artif. Intell. Earth Syst."},{"key":"10953_CR16","volume":"1","author":"H-Y Liu","year":"2024","unstructured":"Liu, H.-Y. et al. A hybrid machine learning\/physics-based modeling framework for 2-week extended prediction of tropical cyclones. J. Geophys. Res. Mach. Learn. Comput. 1, e2024JH000207 (2024).","journal-title":"J. Geophys. Res. Mach. Learn. Comput."},{"key":"10953_CR17","doi-asserted-by":"publisher","DOI":"10.1038\/s41612-025-01009-9","volume":"8","author":"J Pu","year":"2025","unstructured":"Pu, J., Mu, M., Feng, J., Zhong, X. & Li, H. A fast physics-based perturbation generator of machine learning weather model for efficient ensemble forecasts of tropical cyclone track. npj Clim. Atmos. Sci. 8, 128 (2025).","journal-title":"npj Clim. Atmos. Sci."},{"key":"10953_CR18","doi-asserted-by":"publisher","DOI":"10.1038\/s41612-023-00512-1","volume":"6","author":"L Chen","year":"2023","unstructured":"Chen, L. et al. FuXi: a cascade machine learning forecasting system for 15-day global weather forecast. npj Clim. Atmos. Sci. 6, 190 (2023).","journal-title":"npj Clim. Atmos. Sci."},{"key":"10953_CR19","doi-asserted-by":"publisher","unstructured":"Yang, S. et al. Generative assimilation and prediction for weather and climate. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2503.03038 (2025).","DOI":"10.48550\/arXiv.2503.03038"},{"key":"10953_CR20","doi-asserted-by":"publisher","first-page":"1172","DOI":"10.1038\/s41586-025-08897-0","volume":"641","author":"A Allen","year":"2025","unstructured":"Allen, A. et al. End-to-end data-driven weather prediction. Nature 641, 1172\u20131179 (2025).","journal-title":"Nature"},{"key":"10953_CR21","doi-asserted-by":"publisher","DOI":"10.1029\/2024GL110651","volume":"51","author":"PT Vonich","year":"2024","unstructured":"Vonich, P. T. & Hakim, G. J. Predictability limit of the 2021 pacific northwest heatwave from deep-learning sensitivity analysis. Geophys. Res. Lett. 51, e2024GL110651 (2024).","journal-title":"Geophys. Res. Lett."},{"key":"10953_CR22","unstructured":"Law, H. & Deng, J. CornerNet: detecting objects as paired keypoints. In Computer Vision \u2013 ECCV 2018 Vol. 11218 (eds Ferrari, V., Hebert, M., Sminchisescu, C. & Weiss, Y.) 734\u2013750 (Springer, 2018)."},{"key":"10953_CR23","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1198\/016214506000001437","volume":"102","author":"T Gneiting","year":"2007","unstructured":"Gneiting, T. & Raftery, A. E. Strictly proper scoring rules, prediction, and estimation. J. Am. Stat. Assoc. 102, 359\u2013378 (2007).","journal-title":"J. Am. Stat. Assoc."},{"key":"10953_CR24","unstructured":"Lakshminarayanan, B., Pritzel, A. & Blundell, C. Simple and scalable predictive uncertainty estimation using deep ensembles. In Proc. Advances in Neural Information Processing Systems 30 (NIPS 2017) 6402\u20136413 (NeurIPS, 2017)."},{"key":"10953_CR25","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1175\/2009WAF2222280.1","volume":"25","author":"J Kaplan","year":"2010","unstructured":"Kaplan, J., DeMaria, M. & Knaff, J. A. A revised tropical cyclone rapid intensification index for the atlantic and eastern north pacific basins. Weather Forecast. 25, 220\u2013241 (2010).","journal-title":"Weather Forecast."},{"key":"10953_CR26","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1002\/qj.3712","volume":"146","author":"HA Titley","year":"2020","unstructured":"Titley, H. A., Bowyer, R. L. & Cloke, H. L. A global evaluation of multi-model ensemble tropical cyclone track probability forecasts. Q. J. R. Meteorol. Soc. 146, 531\u2013545 (2020).","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"10953_CR27","doi-asserted-by":"publisher","first-page":"1913","DOI":"10.1175\/WAF-D-20-0059.1","volume":"35","author":"JP Cangialosi","year":"2020","unstructured":"Cangialosi, J. P. et al. Recent progress in tropical cyclone intensity forecasting at the National Hurricane Center. Weather Forecast. 35, 1913\u20131922 (2020).","journal-title":"Weather Forecast."},{"key":"10953_CR28","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1175\/1520-0493(1977)105<0421:TCMSLP>2.0.CO;2","volume":"105","author":"GD Atkinson","year":"1977","unstructured":"Atkinson, G. D. & Holliday, C. R. Tropical cyclone minimum sea level pressure\/maximum sustained wind relationship for the western north pacific. Mon. Weather Rev. 105, 421\u2013427 (1977).","journal-title":"Mon. Weather Rev."},{"key":"10953_CR29","unstructured":"NCEP. Format of Tropical Cyclone Vital Statistics Records (\u201cTCVitals\u201d) http:\/\/www.emc.ncep.noaa.gov\/mmb\/data_processing\/tcvitals_description.htm (2007)."},{"key":"10953_CR30","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1175\/WAF-D-11-00063.1","volume":"27","author":"S Trahan","year":"2012","unstructured":"Trahan, S. & Sparling, L. An analysis of NCEP tropical cyclone vitals and potential effects on forecasting models. Weather Forecast. 27, 744\u2013756 (2012).","journal-title":"Weather Forecast."},{"key":"10953_CR31","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1080\/07350015.2018.1506926","volume":"36","author":"E Lazarus","year":"2018","unstructured":"Lazarus, E., Lewis, D. J., Stock, J. H. & Watson, M. W. HAR inference: recommendations for practice. J. Bus. Econ. Stat. 36, 541\u2013559 (2018).","journal-title":"J. Bus. Econ. Stat."},{"key":"10953_CR32","unstructured":"Cangialosi, J. P. & Martinez, J. National Hurricane Center Forecast Verification Report: 2024 Hurricane Season (NHC, 2024)."},{"key":"10953_CR33","unstructured":"ECMWF. Tropical cyclone activity (Including genesis) https:\/\/charts.ecmwf.int\/products\/medium-tc-genesis (ECMWF, 2026)."},{"key":"10953_CR34","unstructured":"NHC. Tropical Cyclone Wind Speed Probabilities Products https:\/\/www.nhc.noaa.gov\/about\/pdf\/About_Windspeed_Probabilities.pdf (NHC, 2014)."},{"key":"10953_CR35","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1002\/qj.49712656313","volume":"126","author":"DS Richardson","year":"2000","unstructured":"Richardson, D. S. Skill and relative economic value of the ECMWF ensemble prediction system. Q. J. R. Meteorol. Soc. 126, 649\u2013667 (2000).","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"10953_CR36","doi-asserted-by":"publisher","first-page":"1713","DOI":"10.1175\/WAF-D-19-0255.1","volume":"35","author":"J Lin","year":"2020","unstructured":"Lin, J., Emanuel, K. & Vigh, J. L. Forecasts of hurricanes using large-ensemble outputs. Weather Forecast. 35, 1713\u20131731 (2020).","journal-title":"Weather Forecast."},{"key":"10953_CR37","unstructured":"NHC. NHC Active Tropical Cyclones https:\/\/www.nhc.noaa.gov\/cyclones\/ (NHC, 2025)."},{"key":"10953_CR38","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1175\/1520-0493(2000)128<1187:TCTFUA>2.0.CO;2","volume":"128","author":"JS Goerss","year":"2000","unstructured":"Goerss, J. S. Tropical cyclone track forecasts using an ensemble of dynamical models. Mon. Weather Rev. 128, 1187\u20131193 (2000).","journal-title":"Mon. Weather Rev."},{"key":"10953_CR39","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1175\/2007WAF2007028.1","volume":"23","author":"CR Sampson","year":"2008","unstructured":"Sampson, C. R., Franklin, J. L., Knaff, J. A. & DeMaria, M. Experiments with a simple tropical cyclone intensity consensus. Weather Forecast. 23, 304\u2013312 (2008).","journal-title":"Weather Forecast."},{"key":"10953_CR40","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1175\/1520-0434(2004)019<0633:AHOWNP>2.0.CO;2","volume":"19","author":"JS Goerss","year":"2004","unstructured":"Goerss, J. S., Sampson, C. R. & Gross, J. M. A history of western north pacific tropical cyclone track forecast skill. Weather Forecast. 19, 633\u2013638 (2004).","journal-title":"Weather Forecast."},{"key":"10953_CR41","unstructured":"NHC. NHC Track and Intensity Models https:\/\/www.nhc.noaa.gov\/modelsummary.shtml (NHC, 2026)."},{"key":"10953_CR42","unstructured":"NHC. 2025 Tropical Cyclone Advisory Archive https:\/\/www.nhc.noaa.gov\/archive\/2025\/ (NHC, 2025)."},{"key":"10953_CR43","unstructured":"NHC. NHC a-decks and b-decks https:\/\/ftp.nhc.noaa.gov\/atcf\/archive\/ (NHC, accessed 9 March 2026)."},{"key":"10953_CR44","doi-asserted-by":"publisher","first-page":"5023","DOI":"10.5194\/gmd-14-5023-2021","volume":"14","author":"PA Ullrich","year":"2021","unstructured":"Ullrich, P. A. et al. TempestExtremes v2.1: A community framework for feature detection, tracking, and analysis in large datasets. Geosci. Model Dev. 14, 5023\u20135048 (2021).","journal-title":"Geosci. Model Dev."},{"key":"10953_CR45","doi-asserted-by":"publisher","unstructured":"Man, X., Zhang, C., Feng, J., Li, C. & Shao, J. W-MAE: pre-trained weather model with masked autoencoder for multi-variable weather forecasting. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2304.08754 (2023).","DOI":"10.48550\/arXiv.2304.08754"},{"key":"10953_CR46","unstructured":"Wilson, A. G. & Izmailov, P. Bayesian deep learning and a probabilistic perspective of generalization. In Proc. Advances in Neural Information Processing Systems 33 (NeurIPS 2020) 46397\u20134708 (NeurIPS, 2020)."},{"key":"10953_CR47","doi-asserted-by":"crossref","unstructured":"Wild, V. D., Ghalebikesabi, S., Sejdinovic, D. & Knoblauch, J. A rigorous link between deep ensembles and (variational) Bayesian methods. In Proc. Advances in Neural Information Processing Systems 36 (NeurIPS 2023) 39811\u201339782 (NeurIPS, 2023).","DOI":"10.52202\/075280-1729"},{"key":"10953_CR48","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1002\/qj.49712556006","volume":"125","author":"R Buizza","year":"1999","unstructured":"Buizza, R., Milleer, M. & Palmer, T. N. Stochastic representation of model uncertainties in the ECMWF ensemble prediction system. Q. J. R. Meteorol. Soc. 125, 2887\u20132908 (1999).","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"10953_CR49","first-page":"279","volume":"127","author":"TN Palmer","year":"2001","unstructured":"Palmer, T. N. A nonlinear dynamical perspective on model error: a proposal for non-local stochastic-dynamic parametrization in weather and climate prediction models. Q. J. R. Meteorol. Soc. 127, 279\u2013304 (2001).","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"10953_CR50","unstructured":"Alet, F. Learning Inside the Prediction Function. PhD thesis, Massachusetts Institute of Technology (2022)."},{"key":"10953_CR51","unstructured":"Fortunato, M. et al. Noisy networks for exploration. In Proc. 6th International Conference on Learning Representations (ICLR, 2018)."},{"key":"10953_CR52","unstructured":"Saatci, Y. & Wilson, A. G. Bayesian GAN. In Proc. Advances in Neural Information Processing Systems 30 (NIPS 2017) 3622\u20133631 (NeurIPS, 2017)."},{"key":"10953_CR53","unstructured":"Sun, Y. et al. Test-time training with self-supervision for generalization under distribution shifts. In Proc. 37th International Conference on Machine Learning (PMLR 119) 9229\u20139248 (PMLR, 2020)."},{"key":"10953_CR54","doi-asserted-by":"publisher","unstructured":"Bibas, K., Fogel, Y. & Feder, M. Deep pNML: predictive normalized maximum likelihood for deep neural networks. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1904.12286 (2019).","DOI":"10.48550\/arXiv.1904.12286"},{"key":"10953_CR55","unstructured":"Wang, D., Shelhamer, E., Liu, S., Olshausen, B. & Darrell, T. Tent: fully test-time adaptation by entropy minimization. In Proc. 9th International Conference on Learning Representations (ICLR, 2021)."},{"key":"10953_CR56","unstructured":"Alet, F. Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time. In Proc. Advances in Neural Information Processing Systems 34 (NeurIPS 2021) 29217\u201329206 (NeurIPS, 2021)."},{"key":"10953_CR57","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1002\/qj.2931","volume":"143","author":"P Ollinaho","year":"2017","unstructured":"Ollinaho, P. et al. Towards process-level representation of model uncertainties: stochastically perturbed parametrizations in the ECMWF ensemble. Q. J. R. Meteorol. Soc. 143, 408\u2013422 (2017).","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"10953_CR58","doi-asserted-by":"publisher","first-page":"1548","DOI":"10.1126\/science.285.5433.1548","volume":"285","author":"TN Krishnamurti","year":"1999","unstructured":"Krishnamurti, T. N. et al. Improved weather and seasonal climate forecasts from multimodel superensemble. Science 285, 1548\u20131550 (1999).","journal-title":"Science"},{"key":"10953_CR59","doi-asserted-by":"publisher","DOI":"10.1038\/s44387-026-00073-7","volume":"2","author":"S Lang","year":"2026","unstructured":"Lang, S. et al. AIFS-CRPS: ensemble forecasting using a model trained with a loss function based on the continuous ranked probability score. npj Artif. Intell. 2, 18 (2026).","journal-title":"npj Artif. Intell."},{"key":"10953_CR60","doi-asserted-by":"publisher","unstructured":"Kingma, D. P. & Welling, M. Auto-encoding variational Bayes. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1312.6114 (2013).","DOI":"10.48550\/arXiv.1312.6114"},{"key":"10953_CR61","unstructured":"Rezende, D. J., Mohamed, S. & Wierstra, D. Stochastic backpropagation and approximate inference in deep generative models. In Proc. 31st International Conference on Machine Learning (PMLR 32) 1278\u20131286 (PMLR, 2014)."},{"key":"10953_CR62","unstructured":"Titsias, M. & L\u00e1zaro-Gredilla, M. Doubly stochastic variational Bayes for non-conjugate inference. In Proc. 31st International Conference on Machine Learning (PMLR 32) 1971\u20131979 (PMLR, 2014)."},{"key":"10953_CR63","first-page":"1","volume":"21","author":"S Mohamed","year":"2020","unstructured":"Mohamed, S., Rosca, M., Figurnov, M. & Mnih, A. Monte Carlo gradient estimation in machine learning. J. Mach. Learn. Res. 21, 1\u201362 (2020).","journal-title":"J. Mach. Learn. Res."},{"key":"10953_CR64","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/s11004-017-9709-7","volume":"50","author":"M Zamo","year":"2018","unstructured":"Zamo, M. & Naveau, P. Estimation of the continuous ranked probability score with limited information and applications to ensemble weather forecasts. Math. Geosci. 50, 209\u2013234 (2018).","journal-title":"Math. Geosci."},{"key":"10953_CR65","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1002\/qj.3387","volume":"145","author":"M Leutbecher","year":"2019","unstructured":"Leutbecher, M. Ensemble size: how suboptimal is less than infinity?\u00a0Q. J. R. Meteorol. Soc. 145, 107\u2013128 (2019).","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"10953_CR66","doi-asserted-by":"crossref","unstructured":"Oskarsson, J., Landelius, T., Deisenroth, M. & Lindsten, F. Probabilistic weather forecasting with hierarchical graph neural networks. In Proc. Advances in Neural Information Processing Systems 37 (NeurIPS 2024) 41648\u201341577 (NeurIPS, 2024).","DOI":"10.52202\/079017-1316"},{"key":"10953_CR67","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adu2854","volume":"11","author":"X Zhong","year":"2025","unstructured":"Zhong, X. et al. FuXi-ENS: a machine learning model for efficient and accurate ensemble weather prediction. Sci. Adv. 11, eadu2854 (2025).","journal-title":"Sci. Adv."},{"key":"10953_CR68","first-page":"1","volume":"25","author":"L Pacchiardi","year":"2024","unstructured":"Pacchiardi, L., Adewoyin, R. A., Dueben, P. & Dutta, R. Probabilistic forecasting with generative networks via scoring rule minimization. J. Mach. Learn. Res. 25, 1\u201364 (2024).","journal-title":"J. Mach. Learn. Res."},{"key":"10953_CR69","unstructured":"Bouchacourt, D., Mudigonda, P. K. & Nowozin, S. DISCO Nets: dissimilarity coefficients networks. In Proc. Advances in Neural Information Processing Systems 29 (NIPS 2016) 352\u2013360 (NeurIPS, 2016)."},{"key":"10953_CR70","unstructured":"Gritsenko, A., Salimans, T., Berg, R., van den, Snoek, J. & Kalchbrenner, N. A spectral energy distance for parallel speech synthesis. In Proc. Advances in Neural Information Processing Systems 33 (NeurIPS 2020) 13062\u201313072 (NeurIPS, 2020)."},{"key":"10953_CR71","doi-asserted-by":"publisher","unstructured":"Chen, M. et al. AdaSpeech: adaptive text to speech for custom voice. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2103.00993 (2021).","DOI":"10.48550\/arXiv.2103.00993"},{"key":"10953_CR72","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S. & Aila, T. A style-based generator architecture for generative adversarial networks. In Proc. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 4401\u20134410 (IEEE, 2019).","DOI":"10.1109\/CVPR.2019.00453"},{"key":"10953_CR73","unstructured":"Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. In Proc. 7th International Conference on Learning Representations (ICLR, 2019)."},{"key":"10953_CR74","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/MCSE.2007.55","volume":"9","author":"JD Hunter","year":"2007","unstructured":"Hunter, J. D. Matplotlib: a 2D graphics environment. Comput. Sci. Eng. 9, 90\u201395 (2007).","journal-title":"Comput. Sci. Eng."},{"key":"10953_CR75","unstructured":"Cartopy: a cartographic Python library (Met Office, 2023)."}],"container-title":["Nature"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41586-026-10953-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-026-10953-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-026-10953-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T05:37:42Z","timestamp":1789623462000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41586-026-10953-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,6]]},"references-count":75,"journal-issue":{"issue":"8132","published-print":{"date-parts":[[2026,9,17]]}},"alternative-id":["10953"],"URL":"https:\/\/doi.org\/10.1038\/s41586-026-10953-2","relation":{},"ISSN":["0028-0836","1476-4687"],"issn-type":[{"value":"0028-0836","type":"print"},{"value":"1476-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,6]]},"assertion":[{"value":"23 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This work was performed under a Cooperative Research and Development Agreement (CRADA) between the NOAA and the Collaborator. However, the views expressed herein are not necessarily those of NOAA, the Department of Commerce or the US Government. F.A., I.P., A.E.-K., D.M. and A.S.-G. have filed a patent related to the core FGN probabilistic weather model, but not related to the cyclone-specific modelling\u00a0F.A., T.R.A., I.P., S. Markou, A.E.-K., D.M., S. Merchant, N.W., G.T., K. MacKay, O.G., A.U., B.G., D.S., E.K., J.S., R.L., A.B., P.K., M.W., A.S.-G., and P.B. are employees of Google and hold stock in Alphabet Inc.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}]}}