The Equilibrium Response of Atmospheric Machine-Learning Models to Uniform Sea Surface Temperature Warming

The Equilibrium Response of Atmospheric Machine-Learning Models to Uniform Sea Surface Temperature Warming | 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 The Equilibrium Response of Atmospheric Machine-Learning Models to Uniform Sea Surface Temperature Warming Bosong Zhang, Timothy Merlis This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7766652/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Machine learning models for the global atmosphere that are capable of producing stable, multi-year simulations of Earth’s climate have recently been developed. However, the ability of these ML models to generalize beyond the training distribution remains an open question. In this study, we evaluate the climate response of several state-of-theart ML models (ACE2-ERA5, NeuralGCM, and cBottle) to a uniform sea surface temperature warming, a widely used benchmark for evaluating climate change. We assess each ML model’s performance relative to a physics-based general circulation model (GFDL’s AM4) across key diagnostics, including surface air temperature, precipitation, temperature and wind profiles, and top-of-the-atmosphere radiation. While the ML models reproduce key aspects of the physical model response, particularly the response of precipitation, some exhibit notable departures from robust physical responses, including radiative responses and land region warming. Our results highlight the promise and current limitations of ML models for climate change applications and suggest that further improvements are needed for robust out-of-sample generalization. Earth and environmental sciences/Climate sciences Earth and environmental sciences/Environmental sciences Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted 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-7766652","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":523807308,"identity":"c8358286-d0ef-40f8-bceb-feac024ccfae","order_by":0,"name":"Bosong Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4UlEQVRIiWNgGAWjYBACAygtx8DA2AAXlSBGizFUiwHxWhIbkPl4tZiztz98XPCrLn279OG2Bz8q/siZMzAfvM2DR4tlzxlj45l9bLk7+xLbDXvOGBhbNrAlW+PTYnAjh02at4cnd8MZxjZpxjaDxA0HeMyk8WtJfwbUIpFuANbyD6SF/xsBLQlAM38YJEC0NIBtYcOrBewX3oYEw509jG2SPceMjQ0OsxlbzsGjBRxiPH/q5M152J9J/KiRkzM43vzwxhs8WsCAsQ0RQQwMzISUg8EfZC2jYBSMglEwCtAAACjYR01PQhiZAAAAAElFTkSuQmCC","orcid":"","institution":"Princeton University","correspondingAuthor":true,"prefix":"","firstName":"Bosong","middleName":"","lastName":"Zhang","suffix":""},{"id":523807309,"identity":"5a38adfb-85ae-4ee7-991d-eed4d67765f1","order_by":1,"name":"Timothy Merlis","email":"","orcid":"","institution":"Princeton University","correspondingAuthor":false,"prefix":"","firstName":"Timothy","middleName":"","lastName":"Merlis","suffix":""}],"badges":[],"createdAt":"2025-10-02 13:08:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7766652/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7766652/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92701144,"identity":"2c6effe4-d42f-4ac9-8c69-959abe394905","added_by":"auto","created_at":"2025-10-03 08:29:58","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7299343,"visible":true,"origin":"","legend":"","description":"","filename":"emulatorsuniwarming3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7766652/v1/662151f6795a7f43502d8f96.pdf"},{"id":92701143,"identity":"d7e40c5e-873b-4edf-b55f-bfd4ade3bc6b","added_by":"auto","created_at":"2025-10-03 08:29:57","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4883,"visible":true,"origin":"","legend":"","description":"","filename":"6696392050734b87b2437e66aeb9de59.json","url":"https://assets-eu.researchsquare.com/files/rs-7766652/v1/811eef3c82f04d9818d94efb.json"},{"id":101548260,"identity":"ece003ee-1262-4393-8395-82efab2421e0","added_by":"auto","created_at":"2026-01-31 06:10:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6729051,"visible":true,"origin":"","legend":"","description":"","filename":"emulatorsuniwarming3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7766652/v1_covered_9716b737-cac0-443d-90c5-e19bc1380988.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"The Equilibrium Response of Atmospheric Machine-Learning Models to Uniform Sea Surface Temperature Warming","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7766652/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7766652/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMachine learning models for the global atmosphere that are capable of producing stable, multi-year simulations of Earth’s climate have recently been developed. However, the ability of these ML models to generalize beyond the training distribution remains an open question. In this study, we evaluate the climate response of several state-of-theart ML models (ACE2-ERA5, NeuralGCM, and cBottle) to a uniform sea surface temperature warming, a widely used benchmark for evaluating climate change. We assess each ML model’s performance relative to a physics-based general circulation model (GFDL’s AM4) across key diagnostics, including surface air temperature, precipitation, temperature and wind profiles, and top-of-the-atmosphere radiation. While the ML models reproduce key aspects of the physical model response, particularly the response of precipitation, some exhibit notable departures from robust physical responses, including radiative responses and land region warming. Our results highlight the promise and current limitations of ML models for climate change applications and suggest that further improvements are needed for robust out-of-sample generalization.\u003c/p\u003e","manuscriptTitle":"The Equilibrium Response of Atmospheric Machine-Learning Models to Uniform Sea Surface Temperature Warming","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-03 08:29:52","doi":"10.21203/rs.3.rs-7766652/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"90ebc11f-723d-4e15-8d83-0561bf746a8b","owner":[],"postedDate":"October 3rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":55673682,"name":"Earth and environmental sciences/Climate sciences"},{"id":55673683,"name":"Earth and environmental sciences/Environmental sciences"}],"tags":[],"updatedAt":"2026-01-31T06:09:39+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-03 08:29:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7766652","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7766652","identity":"rs-7766652","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}