Optimus Climas - Optimising the consideration of tipping points in regionalised Climate Simulations with Deep Learning

Optimus Climas - Optimising the consideration of tipping points in regionalised Climate Simulations with Deep Learning | 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 Research Article Optimus Climas - Optimising the consideration of tipping points in regionalised Climate Simulations with Deep Learning Lilly Schwarz, Charlotte Lange, Leon Kausch, Mike Vogt This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7041645/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 Numerical climate simulations are essential for predicting the impact of climate change. However, traditional methods require a lot of computing power, limiting the number of scenarios analysed and often only partially consider tipping points - local phenomena with global implications. This study introduces "Optimus Climas", a novel approach that leverages deep learning techniques to enhance climate simulations. By utilizing historical climate data, our model directly learns the dynamics of the Earth's climate system instead of approximating physical laws with numerical algorithms. This significantly reduces computation time and allows for a broader range of scenarios. We aim to optimise climate simulations with deep learning regarding regionalisation and consideration of tipping points such as the collapse of boreal permafrost and the West Antarctic Ice Sheet. We employ state-of-the-art deep learning methods, including modified Vision Transformers and modified Gramian Angular Fields. The results show high correlations with the results of the International Panel on Climate Change (IPCC). Furthermore the triggering and the consequences of multiple tipping points could be predicted, for example an additional rise in global temperature of up to 1.5 °C due to the collapse of the boreal permafrost was predicted. Our findings demonstrate that Optimus Climas can provide valuable insights into the potential consequences of climate change, offering a complementary tool to traditional numerical simulations. Deep Learning Vision Transformers tipping points climate simulations 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-7041645","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":481295342,"identity":"6fedf8b1-d802-47eb-93bb-df12876dd838","order_by":0,"name":"Lilly Schwarz","email":"data:image/png;base64,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","orcid":"","institution":"Schülerforschungszentrum Nordhessen","correspondingAuthor":true,"prefix":"","firstName":"Lilly","middleName":"","lastName":"Schwarz","suffix":""},{"id":481295343,"identity":"582070f1-e67b-4be4-ad8f-fff65b04c979","order_by":1,"name":"Charlotte Lange","email":"","orcid":"","institution":"Schülerforschungszentrum Nordhessen","correspondingAuthor":false,"prefix":"","firstName":"Charlotte","middleName":"","lastName":"Lange","suffix":""},{"id":481295344,"identity":"b2ec95c4-691e-46e3-9e05-fefaeccb53c7","order_by":2,"name":"Leon Kausch","email":"","orcid":"","institution":"Schülerforschungszentrum Nordhessen","correspondingAuthor":false,"prefix":"","firstName":"Leon","middleName":"","lastName":"Kausch","suffix":""},{"id":481295345,"identity":"df63b451-6adc-4e2d-a069-b5e9681f9030","order_by":3,"name":"Mike Vogt","email":"","orcid":"","institution":"Schülerforschungszentrum Nordhessen","correspondingAuthor":false,"prefix":"","firstName":"Mike","middleName":"","lastName":"Vogt","suffix":""}],"badges":[],"createdAt":"2025-07-03 23:08:04","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7041645/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7041645/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108070753,"identity":"90eb4b20-39e0-4fdf-9e65-9cf10ec7c13f","added_by":"auto","created_at":"2026-04-29 05:56:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":7634199,"visible":true,"origin":"","legend":"","description":"","filename":"OptimusClimasnew3anonymised2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7041645/v1_covered_35d13841-5dd5-4817-8a71-141e6ebd5a26.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Optimus Climas - Optimising the consideration of tipping points in regionalised Climate Simulations with Deep Learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Deep Learning, Vision Transformers, tipping points, climate simulations","lastPublishedDoi":"10.21203/rs.3.rs-7041645/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7041645/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eNumerical climate simulations are essential for predicting the impact of climate change. However, traditional methods require a lot of computing power, limiting the number of scenarios analysed and often only partially consider tipping points - local phenomena with global implications. This study introduces \"Optimus Climas\", a novel approach that leverages deep learning techniques to enhance climate simulations. By utilizing historical climate data, our model directly learns the dynamics of the Earth's climate system instead of approximating physical laws with numerical algorithms. This significantly reduces computation time and allows for a broader range of scenarios. We aim to optimise climate simulations with deep learning regarding regionalisation and consideration of tipping points such as the collapse of boreal permafrost and the West Antarctic Ice Sheet. We employ state-of-the-art deep learning methods, including modified Vision Transformers and modified Gramian Angular Fields. The results show high correlations with the results of the International Panel on Climate Change (IPCC). Furthermore the triggering and the consequences of multiple tipping points could be predicted, for example an additional rise in global temperature of up to 1.5 \u0026deg;C due to the collapse of the boreal permafrost was predicted. Our findings demonstrate that Optimus Climas can provide valuable insights into the potential consequences of climate change, offering a complementary tool to traditional numerical simulations.\u003c/p\u003e","manuscriptTitle":"Optimus Climas - Optimising the consideration of tipping points in regionalised Climate Simulations with Deep Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-09 05:07:46","doi":"10.21203/rs.3.rs-7041645/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":"26832884-d7f2-4570-9e3c-bfd552a893f8","owner":[],"postedDate":"July 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-29T05:55:56+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-09 05:07:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7041645","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7041645","identity":"rs-7041645","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}