Towards Sustainable Nowcasting: Assessing the Environmental Costs of AI-Driven Extreme Rainfall Prediction

Towards Sustainable Nowcasting: Assessing the Environmental Costs of AI-Driven Extreme Rainfall Prediction | 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 Towards Sustainable Nowcasting: Assessing the Environmental Costs of AI-Driven Extreme Rainfall Prediction Douglas Brum, Luan Teylo, Fabricio Polifke da Silva, Fernanda Cerqueira Vasconcellos, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6751218/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 10 Mar, 2026 Read the published version in Scientific Reports → Version 1 posted 11 You are reading this latest preprint version Abstract The nowcasting of extreme rainfall poses significant daily challenges on a global scale, especially in vulnerable regions of the Global South. Conventional Numerical Weather Prediction models often fail to deliver accurate and timely forecasts for extreme weather events, exacerbating socioeconomic inequalities and increasing climate vulnerability. Deep learning approaches present a promising opportunity to uncover more precise predictive patterns; however, their application remains constrained by the high computational costs associated to their large parameter spaces. This study evaluates the effectiveness of the MS-RNN framework for improving computational efficiency and predictive accuracy in extreme precipitation nowcasting, using real weather radar data from the TAASRAD19 and Rio de Janeiro datasets. While the framework has been extensively validated both theoretically and experimentally in other scenarios, this work examines its application to real radar data. Metrics related to sustainability, such as energy consumption, CO2 emissions, and water usage, have not been calculated in this specific context and are rarely addressed in current literature. Our findings demonstrate the potential of the solution to enhance computational efficiency maintaining predictive performance when applied to real weather radar data, supporting sustainable and accessible AI solutions for climate resilience in resource-limited regions. Earth and environmental sciences/Environmental sciences/Environmental impact Earth and environmental sciences/Climate sciences/Climate change/Climate change impacts Earth and environmental sciences/Climate sciences/Climate change/Projection and prediction Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 10 Mar, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 14 Nov, 2025 Reviews received at journal 21 Oct, 2025 Reviewers agreed at journal 26 Sep, 2025 Editor invited by journal 25 Sep, 2025 Reviews received at journal 19 Jun, 2025 Reviewers agreed at journal 10 Jun, 2025 Reviewers agreed at journal 06 Jun, 2025 Reviewers invited by journal 04 Jun, 2025 Editor assigned by journal 31 May, 2025 Submission checks completed at journal 29 May, 2025 First submitted to journal 26 May, 2025 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-6751218","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":467501484,"identity":"47c2ce4d-2988-4a0b-9781-5da067afe32a","order_by":0,"name":"Douglas Brum","email":"","orcid":"","institution":"Fluminense Federal University","correspondingAuthor":false,"prefix":"","firstName":"Douglas","middleName":"","lastName":"Brum","suffix":""},{"id":467501485,"identity":"dd856b1a-d87b-4926-9305-fc967e387c34","order_by":1,"name":"Luan Teylo","email":"","orcid":"","institution":"Inria Bordeaux - Sud-Ouest Research Centre","correspondingAuthor":false,"prefix":"","firstName":"Luan","middleName":"","lastName":"Teylo","suffix":""},{"id":467501486,"identity":"1567fa45-0a5a-4b6f-a2cc-56f478dbc83a","order_by":2,"name":"Fabricio Polifke da Silva","email":"","orcid":"","institution":"Federal University of Rio de Janeiro","correspondingAuthor":false,"prefix":"","firstName":"Fabricio","middleName":"Polifke da","lastName":"Silva","suffix":""},{"id":467501487,"identity":"ea28ee5b-e4cc-406f-b58b-d13c0d4efe84","order_by":3,"name":"Fernanda Cerqueira Vasconcellos","email":"","orcid":"","institution":"Federal University of Rio de Janeiro","correspondingAuthor":false,"prefix":"","firstName":"Fernanda","middleName":"Cerqueira","lastName":"Vasconcellos","suffix":""},{"id":467501488,"identity":"05bd4394-0e2b-415f-b4cb-0661399948d5","order_by":4,"name":"Gabriel Berto Breder","email":"","orcid":"","institution":"Fluminense Federal University","correspondingAuthor":false,"prefix":"","firstName":"Gabriel","middleName":"Berto","lastName":"Breder","suffix":""},{"id":467501489,"identity":"87f10da3-5077-4036-b8c0-35065d1b1ac9","order_by":5,"name":"Lívia de Azevedo","email":"","orcid":"","institution":"Fluminense Federal University","correspondingAuthor":false,"prefix":"","firstName":"Lívia","middleName":"","lastName":"de Azevedo","suffix":""},{"id":467501490,"identity":"ccb95dd1-1247-4dd3-bc5c-a607f073a2ca","order_by":6,"name":"Eduardo Bezerra","email":"","orcid":"","institution":"Federal Center for Technological Education of Rio de Janeiro","correspondingAuthor":false,"prefix":"","firstName":"Eduardo","middleName":"","lastName":"Bezerra","suffix":""},{"id":467501491,"identity":"e2197df1-ee28-4548-be67-eb66a4958567","order_by":7,"name":"Fabio Porto","email":"","orcid":"","institution":"Laboratório Nacional de Computação Científica","correspondingAuthor":false,"prefix":"","firstName":"Fabio","middleName":"","lastName":"Porto","suffix":""},{"id":467501492,"identity":"1c71ff4b-ae59-44bc-82bd-03c1698918b9","order_by":8,"name":"Mariza Ferro","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAs0lEQVRIiWNgGAWjYJCCAwwMNjwgxocKEJtILWkgLYwzzhCrBQgOMxCvRbf97MODP2rOy/A38Bg2HGC4k09Qi9mZdIMDEsdu80gcAGt5ZtlAUMuBNIYDBmy3eQwYeMwff2A4bEDYlvPPGA4k/DsH0gKyhRgtN4C2HGw7QJKWZwwHG/uSeSQOsxU2HDB4RozD0pg//vhmZ8/f3ryx4UDFHcJaEIAZRJCiYRSMglEwCkYBbgAAgNVAzcisN4cAAAAASUVORK5CYII=","orcid":"","institution":"Fluminense Federal University","correspondingAuthor":true,"prefix":"","firstName":"Mariza","middleName":"","lastName":"Ferro","suffix":""}],"badges":[],"createdAt":"2025-05-26 13:23:06","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6751218/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6751218/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-026-43029-2","type":"published","date":"2026-03-10T15:57:41+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":104739340,"identity":"0a8db348-b5df-4cdb-9ba6-3b72a307d402","added_by":"auto","created_at":"2026-03-16 16:03:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":479282,"visible":true,"origin":"","legend":"","description":"","filename":"PaperScientificReportsGreenAIVersion32.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6751218/v1_covered_475bd38d-e3f2-401e-8e7b-31611087f3c5.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Towards Sustainable Nowcasting: Assessing the Environmental Costs of AI-Driven Extreme Rainfall Prediction","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-6751218/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6751218/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The nowcasting of extreme rainfall poses significant daily challenges on a global scale, especially in vulnerable regions of the Global South. Conventional Numerical Weather Prediction models often fail to deliver accurate and timely forecasts for extreme weather events, exacerbating socioeconomic inequalities and increasing climate vulnerability. Deep learning approaches present a promising opportunity to uncover more precise predictive patterns; however, their application remains constrained by the high computational costs associated to their large parameter spaces. This study evaluates the effectiveness of the MS-RNN framework for improving computational efficiency and predictive accuracy in extreme precipitation nowcasting, using real weather radar data from the TAASRAD19 and Rio de Janeiro datasets. While the framework has been extensively validated both theoretically and experimentally in other scenarios, this work examines its application to real radar data. Metrics related to sustainability, such as energy consumption, CO2 emissions, and water usage, have not been calculated in this specific context and are rarely addressed in current literature. Our findings demonstrate the potential of the solution to enhance computational efficiency maintaining predictive performance when applied to real weather radar data, supporting sustainable and accessible AI solutions for climate resilience in resource-limited regions. ","manuscriptTitle":"Towards Sustainable Nowcasting: Assessing the Environmental Costs of AI-Driven Extreme Rainfall Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-09 07:59:41","doi":"10.21203/rs.3.rs-6751218/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-11-14T07:25:45+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-21T17:16:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"148136717854376309172581218762122231955","date":"2025-09-26T15:18:59+00:00","index":"hide","fulltext":""},{"type":"editorInvited","content":"","date":"2025-09-25T11:56:13+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-19T15:54:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"271267445054968544757131915409195515200","date":"2025-06-10T06:39:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"82129441190724212139491541231933134060","date":"2025-06-06T10:37:08+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-05T02:19:37+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-31T06:50:56+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-30T01:39:52+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-05-26T13:08:28+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"27eb0d35-4dd8-4012-9b31-f0e905c450d7","owner":[],"postedDate":"June 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":49637497,"name":"Earth and environmental sciences/Environmental sciences/Environmental impact"},{"id":49637498,"name":"Earth and environmental sciences/Climate sciences/Climate change/Climate change impacts"},{"id":49637499,"name":"Earth and environmental sciences/Climate sciences/Climate change/Projection and prediction"}],"tags":[],"updatedAt":"2026-03-16T16:01:30+00:00","versionOfRecord":{"articleIdentity":"rs-6751218","link":"https://doi.org/10.1038/s41598-026-43029-2","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2026-03-10 15:57:41","publishedOnDateReadable":"March 10th, 2026"},"versionCreatedAt":"2025-06-09 07:59:41","video":"","vorDoi":"10.1038/s41598-026-43029-2","vorDoiUrl":"https://doi.org/10.1038/s41598-026-43029-2","workflowStages":[]},"version":"v1","identity":"rs-6751218","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6751218","identity":"rs-6751218","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}