Improving Subseasonal Indian Summer Monsoon Rainfall Forecasts with U-Net Calibration

Improving Subseasonal Indian Summer Monsoon Rainfall Forecasts with U-Net Calibration | 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 Improving Subseasonal Indian Summer Monsoon Rainfall Forecasts with U-Net Calibration Emile D. Esmaili, Andrew Robertson, Muhammad Azhar Ehsan, Bohar Singh, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7744380/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 5 You are reading this latest preprint version Abstract Accurate subseasonal to seasonal (S2S) forecasts of Indian Summer Monsoon Rainfall (ISMR) are vital for agricultural planning, water resource management, and disaster risk reduction. Conventional post-processing techniques for S2S General Circulation Model (GCM) forecasts predominantly rely on linear methods, which often exhibit limited predictive skill. In this study, we investigate the use of deep learning—specifically, U-Net convolutional neural networks (CNNs)—for improving probabilistic ISMR forecasts. We apply U-Net-based bias correction to three state-of-the-art S2S GCMs: GEFSv12, ECMWF, and IITM ERPv2, training the U-Net models to calibrate tercile probabilities of weekly accumulated rainfall at lead times of 1 to 4 weeks for the monsoon season (June-September) over India. Our results show that the U-Net enhances probabilistic forecast skill, consistently outperforming the baseline Extended Logistic Regression (ELR) approach. Using hindcast data from 1989 to 2022, we observe a substantial improvement in weeks 3--4 probabilistic forecast skill, measured by the Ranked Probability Skill Score (RPSS). The extent of improvement, however, varies with the amount of training data available for each GCM, and can reach as high as a twofold increase, from 2% in the baseline to 4% with our U-Net model for Weeks 3--4. We also construct a multi-model ensemble (MME), which improves skill across all lead times. Additionally, the U-Net demonstrates superior performance to the linear baseline in a real-time forecasting context, for the summer of 2023. These findings underscore the promise of deep learning approaches to improve Indian Summer Monsoon Rainfall forecasts at the S2S timescale. Subseasonal-to-seasonal (S2S) Forecasting Deep Learning Indian Summer Monsoon Rainfall Ensemble Forecast Post-processing Full Text Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Major Revision 13 Jan, 2026 Reviewers agreed at journal 06 Oct, 2025 Reviewers invited by journal 03 Oct, 2025 Editor assigned by journal 03 Oct, 2025 First submitted to journal 29 Sep, 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-7744380","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":524184887,"identity":"d62ebd45-919c-4df7-b8f8-58e2a5433403","order_by":0,"name":"Emile D. Esmaili","email":"","orcid":"","institution":"Columbia University","correspondingAuthor":false,"prefix":"","firstName":"Emile","middleName":"D.","lastName":"Esmaili","suffix":""},{"id":524184888,"identity":"f57669ab-d558-40f1-9874-c56943b0a0f8","order_by":1,"name":"Andrew Robertson","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4klEQVRIie3PsQqCQBzH8b8IuRit/wr0FU6CECJ6FSWwJacgnOJEuMZWH6OWaBWh6R6gcMipqcGxsZNqKq7aGu47HveB/w9ApfrPtNIjaAHoFDSK9Qv5RHRSRW5P0O9Jo53yyKd3Ap9JKw3LbpPhZLWMWee4c20wki3KCB4mpCdImPKMdUOODjX3cymBIoBxTdboC8JQzJn2pcQWJK8PIw8yovZFTkgRaHHK0XsSn6IpJ87prEMVoSO2JAOxZczMYObKiMX3xtUjC7u1TLIi3C2GKyPfHGTktcZv31UqlUr1rhvK4UceCY5GGgAAAABJRU5ErkJggg==","orcid":"","institution":"Columbia University","correspondingAuthor":true,"prefix":"","firstName":"Andrew","middleName":"","lastName":"Robertson","suffix":""},{"id":524184889,"identity":"de34d749-cf56-4f0d-9d6a-e215ac34d88d","order_by":2,"name":"Muhammad Azhar Ehsan","email":"","orcid":"","institution":"Columbia University","correspondingAuthor":false,"prefix":"","firstName":"Muhammad","middleName":"Azhar","lastName":"Ehsan","suffix":""},{"id":524184890,"identity":"2509aef3-8596-4e80-b298-5dd67780c9c7","order_by":3,"name":"Bohar Singh","email":"","orcid":"","institution":"NOAA NCEP: NOAA National Centers for Environmental Prediction","correspondingAuthor":false,"prefix":"","firstName":"Bohar","middleName":"","lastName":"Singh","suffix":""},{"id":524184891,"identity":"f615c0f3-d85c-4d45-ae54-6f4bebbb5f95","order_by":4,"name":"Aaron Kaplan","email":"","orcid":"","institution":"Columbia University","correspondingAuthor":false,"prefix":"","firstName":"Aaron","middleName":"","lastName":"Kaplan","suffix":""},{"id":524184892,"identity":"699983bd-0499-4f46-89b7-9f5ed1ea3038","order_by":5,"name":"Avijit Dey","email":"","orcid":"","institution":"Indian Institute of Tropical Meteorology","correspondingAuthor":false,"prefix":"","firstName":"Avijit","middleName":"","lastName":"Dey","suffix":""},{"id":524184893,"identity":"5efada63-46d1-4740-9908-7da0815b1228","order_by":6,"name":"Susmitha Joseph","email":"","orcid":"","institution":"Indian Institute of Tropical Meteorology","correspondingAuthor":false,"prefix":"","firstName":"Susmitha","middleName":"","lastName":"Joseph","suffix":""}],"badges":[],"createdAt":"2025-09-29 17:32:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7744380/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7744380/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93644958,"identity":"2c201c8d-98eb-4307-8069-2e4fb83a973e","added_by":"auto","created_at":"2025-10-16 04:01:48","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9673,"visible":true,"origin":"","legend":"","description":"","filename":"cldyCLDYD2501063.xml","url":"https://assets-eu.researchsquare.com/files/rs-7744380/v1/ff631b9677d6fc263622f6d1.xml"},{"id":93644610,"identity":"a64aa8d7-0163-48d3-a166-1b953fcf1282","added_by":"auto","created_at":"2025-10-16 03:53:48","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":947,"visible":true,"origin":"","legend":"","description":"","filename":"CLDYD250106322047.go.xml","url":"https://assets-eu.researchsquare.com/files/rs-7744380/v1/b7e8ebea977a3e67ade4647f.xml"},{"id":93645493,"identity":"fe85187f-d66a-4db2-838c-2f2eb6c4b7f3","added_by":"auto","created_at":"2025-10-16 04:09:48","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":775,"visible":true,"origin":"","legend":"","description":"","filename":"CLDYD2501063Import.xml","url":"https://assets-eu.researchsquare.com/files/rs-7744380/v1/43d8b53a508afddf299009f7.xml"},{"id":93645950,"identity":"d6480d10-686b-4c04-b4d7-29bdc487faae","added_by":"auto","created_at":"2025-10-16 04:18:22","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":26272855,"visible":true,"origin":"","legend":"","description":"","filename":"CNNUnetMonsoonPaper29Sep2025.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7744380/v1_covered_16978e73-c04a-4595-b546-fb81a185655d.pdf"}],"financialInterests":"","formattedTitle":"Improving Subseasonal Indian Summer Monsoon Rainfall Forecasts with U-Net Calibration","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"climate-dynamics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"cldy","sideBox":"Learn more about [Climate Dynamics](https://www.springer.com/journal/382)","snPcode":"382","submissionUrl":"https://submission.nature.com/new-submission/382/3","title":"Climate Dynamics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Subseasonal-to-seasonal (S2S) Forecasting, Deep Learning, Indian Summer Monsoon Rainfall, Ensemble Forecast Post-processing","lastPublishedDoi":"10.21203/rs.3.rs-7744380/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7744380/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate subseasonal to seasonal (S2S) forecasts of Indian Summer Monsoon Rainfall (ISMR) are vital for agricultural planning, water resource management, and disaster risk reduction. Conventional post-processing techniques for S2S General Circulation Model (GCM) forecasts predominantly rely on linear methods, which often exhibit limited predictive skill. In this study, we investigate the use of deep learning—specifically, U-Net convolutional neural networks (CNNs)—for improving probabilistic ISMR forecasts. We apply U-Net-based bias correction to three state-of-the-art S2S GCMs: GEFSv12, ECMWF, and IITM ERPv2, training the U-Net models to calibrate tercile probabilities of weekly accumulated rainfall at lead times of 1 to 4 weeks for the monsoon season (June-September) over India. Our results show that the U-Net enhances probabilistic forecast skill, consistently outperforming the baseline Extended Logistic Regression (ELR) approach. Using hindcast data from 1989 to 2022, we observe a substantial improvement in weeks 3--4 probabilistic forecast skill, measured by the Ranked Probability Skill Score (RPSS). The extent of improvement, however, varies with the amount of training data available for each GCM, and can reach as high as a twofold increase, from 2% in the baseline to 4% with our U-Net model for Weeks 3--4. We also construct a multi-model ensemble (MME), which improves skill across all lead times. Additionally, the U-Net demonstrates superior performance to the linear baseline in a real-time forecasting context, for the summer of 2023. These findings underscore the promise of deep learning approaches to improve Indian Summer Monsoon Rainfall forecasts at the S2S timescale.","manuscriptTitle":"Improving Subseasonal Indian Summer Monsoon Rainfall Forecasts with U-Net Calibration","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-16 03:53:43","doi":"10.21203/rs.3.rs-7744380/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major Revision","date":"2026-01-13T11:17:35+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"","date":"2025-10-06T05:21:34+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-03T09:50:13+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-03T05:39:08+00:00","index":"","fulltext":""},{"type":"submitted","content":"Climate Dynamics","date":"2025-09-29T13:32:02+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"climate-dynamics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"cldy","sideBox":"Learn more about [Climate Dynamics](https://www.springer.com/journal/382)","snPcode":"382","submissionUrl":"https://submission.nature.com/new-submission/382/3","title":"Climate Dynamics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"feb613e6-e2b6-4654-bb78-548488a9a5c4","owner":[],"postedDate":"October 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-05-22T18:26:24+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-16 03:53:43","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7744380","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7744380","identity":"rs-7744380","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}