GEN2: A Generative Prediction-Correction Framework for Long-time Emulations of Spatially-Resolved Climate Extremes

GEN2: A Generative Prediction-Correction Framework for Long-time Emulations of Spatially-Resolved Climate Extremes | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article GEN 2 : A Generative Prediction-Correction Framework for Long-time Emulations of Spatially-Resolved Climate Extremes Themistoklis Sapsis, Mengze Wang, Benedikt Barthel Sorensen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7394591/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Accurately quantifying the increased risks of climate extremes requires generating large ensembles of climate realization across a wide range of emissions scenarios, which is computationally challenging for conventional Earth System Models. We propose GEN 2 , a generative prediction-correction framework for an efficient and accurate forecast of the extreme event statistics. The prediction step is constructed as a conditional Gaussian emulator, followed by a non-Gaussian machine-learning (ML) correction step. The ML model is trained on pairs of the reference data and the emulated fields nudged towards the reference, to ensure the training is robust to chaos. We first validate the accuracy of our model on historical ERA5 data and then demonstrate the extrapolation capabilities on various future climate change scenarios. When trained on a single realization of one warming scenario, our model accurately predicts the statistics of extreme events in different scenarios, successfully extrapolating beyond the distribution of training data. Physical sciences/Mathematics and computing/Computational science Earth and environmental sciences/Climate sciences/Climate change/Climate and Earth system modelling Climate Science Machine Learning Dynamical Systems Reduced Order Modeling Full Text Additional Declarations There is NO Competing Interest. Supplementary Files GEN2NATURE2025SI.pdf Supplemental Information Cite Share Download PDF Status: Under Review Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7394591","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":513807341,"identity":"3d9bcaa0-a6a0-444b-addc-91f30618e630","order_by":0,"name":"Themistoklis Sapsis","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAArElEQVRIiWNgGAWjYLCCBAYbBjYQg4cELWkMbGwkaWFgOMzAQLQW+fazhz88+HM+mk++gfHB2zYitBicyUuTSGy7ndvGxsBsOJcoLQw5ZgyJDWAtbNK8xGiR739j/CHhzzmQFvbfRGlhuJFjIJHAdgBsCzNRWgxuvAP5JRmoJbFZcs45ohyWe/jjjz92ufObDx/88KaMGIch4oKxgSj1DKTF+CgYBaNgFIxMAAChgTOdpKOdXwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0003-0302-0691","institution":"Massachusetts Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Themistoklis","middleName":"","lastName":"Sapsis","suffix":""},{"id":513807342,"identity":"02656e29-c2b0-4ec0-bad3-93e9057ba5d9","order_by":1,"name":"Mengze Wang","email":"","orcid":"https://orcid.org/0000-0002-5417-7958","institution":"MIT","correspondingAuthor":false,"prefix":"","firstName":"Mengze","middleName":"","lastName":"Wang","suffix":""},{"id":513807343,"identity":"d9ed3fd6-395d-4ab7-9f58-3f26f1bb1b1e","order_by":2,"name":"Benedikt Barthel Sorensen","email":"","orcid":"","institution":"Massachusetts Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Benedikt","middleName":"Barthel","lastName":"Sorensen","suffix":""}],"badges":[],"createdAt":"2025-08-17 23:15:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7394591/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7394591/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91186381,"identity":"75795de2-de25-401c-ba9b-2e588d1da6c3","added_by":"auto","created_at":"2025-09-12 13:58:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3006518,"visible":true,"origin":"","legend":"Article File","description":"","filename":"GEN2NATURE2025mainv1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7394591/v1_covered_6cdc06eb-52ac-4e01-8d08-be50d77fd6d5.pdf"},{"id":91185195,"identity":"4ba328d8-2c50-417a-8dd8-8246ea7cc801","added_by":"auto","created_at":"2025-09-12 13:50:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":6366344,"visible":true,"origin":"","legend":"Supplemental Information","description":"","filename":"GEN2NATURE2025SI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7394591/v1/e8ffe961969bfbb43c03c682.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"GEN\u003csup\u003e2\u003c/sup\u003e: A Generative Prediction-Correction Framework for Long-time Emulations of Spatially-Resolved Climate Extremes","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Climate Science, Machine Learning, Dynamical Systems, Reduced Order Modeling","lastPublishedDoi":"10.21203/rs.3.rs-7394591/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7394591/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurately quantifying the increased risks of climate extremes requires generating large ensembles of climate realization across a wide range of emissions scenarios, which is computationally challenging for conventional Earth System Models. We propose GEN\u003csup\u003e2\u003c/sup\u003e, a generative prediction-correction framework for an efficient and accurate forecast of the extreme event statistics. The prediction step is constructed as a conditional Gaussian emulator, followed by a non-Gaussian machine-learning (ML) correction step. The ML model is trained on pairs of the reference data and the emulated fields nudged towards the reference, to ensure the training is robust to chaos. We first validate the accuracy of our model on historical ERA5 data and then demonstrate the extrapolation capabilities on various future climate change scenarios. When trained on a single realization of one warming scenario, our model accurately predicts the statistics of extreme events in different scenarios, successfully extrapolating beyond the distribution of training data.","manuscriptTitle":"GEN2: A Generative Prediction-Correction Framework for Long-time Emulations of Spatially-Resolved Climate Extremes","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-12 13:49:59","doi":"10.21203/rs.3.rs-7394591/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-computational-science","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"natcomputsci","sideBox":"Learn more about [Nature Computational Science](http://www.nature.com/natcomputsci/)","snPcode":"","submissionUrl":"","title":"Nature Computational Science","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Research","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"7e523ead-4ec8-4a74-9b1f-6a9f102b3d92","owner":[],"postedDate":"September 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":54588806,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":54588807,"name":"Earth and environmental sciences/Climate sciences/Climate change/Climate and Earth system modelling"}],"tags":[],"updatedAt":"2026-04-23T04:25:22+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-12 13:49:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7394591","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7394591","identity":"rs-7394591","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}