{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T11:56:11Z","timestamp":1790855771197,"version":"4.1.0"},"reference-count":59,"publisher":"American Geophysical Union (AGU)","issue":"22","license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation","doi-asserted-by":"publisher","award":["CRSII5_201792"],"award-info":[{"award-number":["CRSII5_201792"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation","doi-asserted-by":"publisher","award":["10001754"],"award-info":[{"award-number":["10001754"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["agupubs.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Geophysical Research Letters"],"published-print":{"date-parts":[[2024,11,28]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Severe convective storms are among the most dangerous weather phenomena and accurate forecasts mitigate their impacts. The recently released suite of AI\u2010based weather models produces medium\u2010range forecasts within seconds, with a skill similar to state\u2010of\u2010the\u2010art operational forecasts for variables on single levels. However, predicting severe thunderstorm environments requires accurate combinations of dynamic and thermodynamic variables and the vertical structure of the atmosphere. Advancing the assessment of AI\u2010models toward process\u2010based evaluations lays the foundation for hazard\u2010driven applications. We assess the forecast skill of the top\u2010performing AI\u2010models GraphCast, Pangu\u2010Weather and FourCastNet for convective parameters at lead\u2010times up to 10\u00a0days against reanalysis and ECMWF's operational numerical weather prediction model IFS. In a case study and seasonal analyses, we see the best performance by GraphCast and Pangu\u2010Weather: these models match or even exceed the performance of IFS for instability and shear. This opens opportunities for fast and inexpensive predictions of severe weather environments.<\/jats:p>","DOI":"10.1029\/2024gl110960","type":"journal-article","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T10:59:39Z","timestamp":1732186779000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Lightning\u2010Fast Convective Outlooks: Predicting Severe Convective Environments With Global AI\u2010Based Weather Models"],"prefix":"10.1029","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8123-5415","authenticated-orcid":false,"given":"Monika","family":"Feldmann","sequence":"first","affiliation":[{"name":"Institute of Geography Oeschger Centre for Climate Change Research University of Bern  Bern Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5731-1040","authenticated-orcid":false,"given":"Tom","family":"Beucler","sequence":"additional","affiliation":[{"name":"Faculty of Geosciences and Environment Expertise Center for Climate Extremes University of Lausanne  Lausanne Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0421-3893","authenticated-orcid":false,"given":"Milton","family":"Gomez","sequence":"additional","affiliation":[{"name":"Faculty of Geosciences and Environment Expertise Center for Climate Extremes University of Lausanne  Lausanne Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8645-4702","authenticated-orcid":false,"given":"Olivia","family":"Martius","sequence":"additional","affiliation":[{"name":"Institute of Geography Oeschger Centre for Climate Change Research University of Bern  Bern Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"13","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.21957\/h20rz8"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.5194\/nhess\u201023\u20103651\u20102023"},{"key":"e_1_2_9_4_1","unstructured":"Beddoes B.(2020).Ranking the Easter 2020 tornado outbreak versus the worst outbreaks in history.https:\/\/www.whsv.com\/content\/news\/Ranking\u2010the\u2010Easter\u20102020\u2010outbreak\u2010versus\u2010the\u2010worst\u2010outbreaks\u2010in\u2010history\u2010569861941.html"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adj7250"},{"key":"e_1_2_9_6_1","volume-title":"How to use the power of AI to reduce the impact of climate change on Switzerland. Swiss Academy of Engineering Sciences (SATW)","author":"Beucler T.","year":"2024"},{"key":"e_1_2_9_7_1","volume-title":"Sigma: Natural catastrophes in 2020: Secondary perils in the spotlight, but don\u2019t forget primary\u2010peril risks","author":"Bevere L.","year":"2021"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586\u2010023\u201006185\u20103"},{"key":"e_1_2_9_9_1","unstructured":"Bodnar C. Bruinsma W. P. Lucic A. Stanley M. Brandstetter J. Garvan P. et\u00a0al. (2024).Aurora: A foundation model of the atmosphere."},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1029\/2023GL107377"},{"key":"e_1_2_9_11_1","first-page":"2806","volume-title":"Proceedings of the 40th international conference on machine learning","author":"Bonev B.","year":"2023"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1175\/BAMS\u2010D\u201023\u20100162.1"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1175\/2010BAMS2853.1"},{"key":"e_1_2_9_14_1","unstructured":"Bowen S. Kerschner B. &Zheng Ng J.(2024).Natural catastrophe and climate report 2023. Gallagher Re. Retrieved fromhttps:\/\/www.ajg.com\/gallagherre\/\u2010\/media\/files\/gallagher\/gallagherre\/news\u2010and\u2010insights\/2024\/january\/natural_catastrophe_and_climate_report_2023.pdf"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.atmosres.2010.09.004"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.atmosres.2012.04.002"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0169\u20108095(03)00045\u20100"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1175\/BAMS\u2010D\u201021\u20100262.1"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41612\u2010024\u201000638\u2010w"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41612\u2010023\u201000512\u20101"},{"key":"e_1_2_9_21_1","unstructured":"Copernicus Services. (2020).Surface air temperature for march 2020. Retrieved fromhttps:\/\/climate.copernicus.eu\/surface\u2010air\u2010temperature\u2010march\u20102020"},{"key":"e_1_2_9_22_1","unstructured":"Dean A. &Dial G.(2020).Day 4\u20108 severe weather outlook issued on Apr 8 2020.https:\/\/www.spc.noaa.gov\/products\/exper\/day4\u20108\/archive\/2020\/day4\u20108_20200408.html"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1038\/d41586\u2010023\u201002084\u20109"},{"key":"e_1_2_9_24_1","unstructured":"ECMWF. (2023).AI\u2010models (version 0.2.13)[Software].https:\/\/github.com\/ecmwf\u2010lab\/ai\u2010models"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","unstructured":"Feldmann M.(2024).feldmann\u2010m\/Ai\u2010storm: Version 0.2[Software].Zenodo.https:\/\/doi.org\/10.5281\/zenodo.13694726","DOI":"10.5281\/zenodo.13694726"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1175\/MWR\u2010D\u201012\u201000155.1"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1175\/2009WAF2222269.1"},{"key":"e_1_2_9_28_1","unstructured":"Google LLC. (2023).WeatherBench 2[Dataset].https:\/\/weatherbench2.readthedocs.io\/en\/latest\/"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1175\/BAMS\u2010D\u201023\u20100220.1"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.21957\/mlvapkke"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1175\/AIES\u2010D\u201023\u20100090.1"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/qj.3803"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-374266-7.00008-1"},{"key":"e_1_2_9_34_1","unstructured":"Jeppesen J.(2024).European met services pool resources to intensify use of AI in weather prediction [Text].https:\/\/www.ecmwf.int\/en\/about\/media\u2010centre\/news\/2024\/european\u2010met\u2010services\u2010pool\u2010resources\u2010intensify\u2010use\u2010ai\u2010weather"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.5194\/nhess\u20107\u2010327\u20102007"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","unstructured":"Ladwig W.(2017).WRF\u2010Python (version 1.3.4.1)[Software].https:\/\/doi.org\/10.5065\/D6W094P1","DOI":"10.5065\/D6W094P1"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.adi2336"},{"key":"e_1_2_9_38_1","unstructured":"Lang S. Alexe M. Chantry M. Dramsch J. Pinault F. Raoult B. et\u00a0al. (2024).AIFS \u2010 ECMWF\u2019S data\u2010driven forecasting system."},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1002\/asl.687"},{"key":"e_1_2_9_40_1","unstructured":"Leon J. A. P.(2018).Addressing biases in near\u2010surface forecasts [Text].https:\/\/www.ecmwf.int\/en\/newsletter\/157\/meteorology\/addressing\u2010biases\u2010near\u2010surface\u2010forecasts"},{"key":"e_1_2_9_41_1","article-title":"Stress\u2010testing the coupled behavior of hybrid physics\u2010machine learning climate simulations on an unseen","author":"Lin J.","year":"2024","journal-title":"warmer climate"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470682104"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1063\/PT.3.5379"},{"key":"e_1_2_9_44_1","unstructured":"Mensch C. A.(2021).Impacts of vertical grid resolution on the representation of a convective environment. ProQuest Dissertations and Theses. Retrieved fromhttps:\/\/www.proquest.com\/dissertations\u2010theses\/impacts\u2010vertical\u2010grid\u2010resolution\u2010on\/docview\/2549273827\/se\u20102.141"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1175\/MWR\u2010D\u201018\u20100106.1"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2301.10343"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.5194\/gmd\u201017\u20102347\u20102024"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.5194\/egusphere\u20102024\u20101042"},{"key":"e_1_2_9_49_1","doi-asserted-by":"crossref","unstructured":"Rasp S. Hoyer S. Merose A. Langmore I. Battaglia P. Russel T. et\u00a0al. (2024).Weatherbench 2: A benchmark for the next generation of data\u2010driven global weather models.https:\/\/doi.org\/10.48550\/arXiv.2308.15560","DOI":"10.1029\/2023MS004019"},{"key":"e_1_2_9_50_1","unstructured":"Storm Prediction Center. (2020a).20200412\u2019s storm reports (20200412 1200 UTC\u201420200413 1159 UTC). Retrieved fromhttps:\/\/www.spc.noaa.gov\/exper\/archive\/event.php?date=20200412"},{"key":"e_1_2_9_51_1","unstructured":"Storm Prediction Center. (2020b).20200413\u2019s storm reports (20200413 1200 UTC\u201420200414 1159 UTC). Retrieved fromhttps:\/\/www.spc.noaa.gov\/exper\/archive\/event.php?date=20200413"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1175\/JCLI\u2010D\u201020\u20100345.1"},{"key":"e_1_2_9_53_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41612\u2010021\u201000190\u2010x"},{"key":"e_1_2_9_54_1","doi-asserted-by":"publisher","DOI":"10.1175\/MWR\u2010D\u201016\u20100384.1"},{"key":"e_1_2_9_55_1","doi-asserted-by":"publisher","DOI":"10.1002\/qj.49711750206"},{"key":"e_1_2_9_56_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139047241"},{"key":"e_1_2_9_57_1","doi-asserted-by":"publisher","DOI":"10.1175\/JCLI\u2010D\u201020\u20100278.1"},{"key":"e_1_2_9_58_1","doi-asserted-by":"publisher","DOI":"10.1175\/2009WAF2222271.1"},{"key":"e_1_2_9_59_1","doi-asserted-by":"publisher","DOI":"10.1175\/2008MWR2415.1"},{"key":"e_1_2_9_60_1","doi-asserted-by":"publisher","DOI":"10.1038\/d41586\u2010023\u201003552\u2010y"}],"container-title":["Geophysical Research Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/agupubs.onlinelibrary.wiley.com\/doi\/pdf\/10.1029\/2024GL110960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T22:46:00Z","timestamp":1734129960000},"score":1,"resource":{"primary":{"URL":"https:\/\/agupubs.onlinelibrary.wiley.com\/doi\/10.1029\/2024GL110960"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"references-count":59,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2024,11,28]]}},"alternative-id":["10.1029\/2024GL110960"],"URL":"https:\/\/doi.org\/10.1029\/2024gl110960","archive":["Portico"],"relation":{},"ISSN":["0094-8276","1944-8007"],"issn-type":[{"value":"0094-8276","type":"print"},{"value":"1944-8007","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"2024-06-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2024GL110960"}}