Deep Learning-Driven Mapping of Pre-Monsoon features for Indian Summer Monsoon Precipitation Forecasting

Deep Learning-Driven Mapping of Pre-Monsoon features for Indian Summer Monsoon Precipitation Forecasting | 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 Deep Learning-Driven Mapping of Pre-Monsoon features for Indian Summer Monsoon Precipitation Forecasting Deepak Singh Bisht, Vivekananda Hazra, Durgesh Nandan Piyush This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6983200/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 11 Feb, 2026 Read the published version in Natural Hazards → Version 1 posted 5 You are reading this latest preprint version Abstract Accurate forecasting of the Indian summer monsoon is critical for water resource management, agricultural planning, and disaster mitigation. In this study, we developed a unique DL methodology to assess whether pre-monsoon atmospheric features can reliably predict monsoon season rainfall. Our model integrates several key parameters, namely, SST, SKT, near-surface air temperature (t2m), TCWV, and a convective index (vimd), which are merged to form a unified thermal variable that captures both marine and terrestrial influences. The domain-summed inland Indian region rainfall is analyzed over a test period from 2012 to 2024 using CDFs, spatial precipitation maps, frequency-of-exceedance curves, and grouped annual performance metrics. The CDF analysis reveals that observed cumulative monthly precipitation for test data has a median of approximately 1.2 m and a mean of 1.3 m, while the predicted distribution exhibits a lower median of about 1.1 m and a mean near 1.0 m, indicating systematic under-prediction, particularly in the upper tail, where the 90th percentile of observed values reaches roughly 1.8 m compared to 1.5 m for predictions. Spatial maps demonstrate that although the model captures broad rainfall patterns along the Western Ghats and Bay of Bengal, regional biases persist, with coastal areas often overestimated and inland regions underestimated. The frequency-of-exceedance analysis further indicates that the model underestimates the occurrence of extreme events. Grouped annual performance metrics, featuring an average correlation of 0.78 and a Kling–Gupta Efficiency of 0.72, underscore the model’s moderate skill across varying monsoon conditions. The statistical analysis of model performance suggests that although there are associated specific systematic biases intrinsic to the model, overall, our integrated DL model effectively captures the general properties of monsoon precipitation and hence can be utilized for extended-range precipitation forecasting. Indian Monsoon Deep Learning Precipitation Forecasting Spatial Bias Extreme Events Cumulative Distribution Function Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Full Text Cite Share Download PDF Status: Published Journal Publication published 11 Feb, 2026 Read the published version in Natural Hazards → Version 1 posted Reviewers agreed at journal 30 Jul, 2025 Reviewers invited by journal 30 Jul, 2025 Editor invited by journal 25 Jul, 2025 Editor assigned by journal 26 Jun, 2025 First submitted to journal 26 Jun, 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-6983200","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":493250359,"identity":"b2aa78d6-f072-45b2-9426-5525ae775028","order_by":0,"name":"Deepak Singh Bisht","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0002-3027-0779","institution":"National Centre for Medium Range Weather Forecasting","correspondingAuthor":true,"prefix":"","firstName":"Deepak","middleName":"Singh","lastName":"Bisht","suffix":""},{"id":493250360,"identity":"509adbeb-5dca-4eb0-ad92-f8347fce0c7d","order_by":1,"name":"Vivekananda Hazra","email":"","orcid":"","institution":"CSIR Fourth Paradigm Institute","correspondingAuthor":false,"prefix":"","firstName":"Vivekananda","middleName":"","lastName":"Hazra","suffix":""},{"id":493250361,"identity":"cfc68005-680e-4ab7-86c7-8aa9fca2d8fb","order_by":2,"name":"Durgesh Nandan Piyush","email":"","orcid":"","institution":"National Centre for Medium Range Weather Forecasting","correspondingAuthor":false,"prefix":"","firstName":"Durgesh","middleName":"Nandan","lastName":"Piyush","suffix":""}],"badges":[],"createdAt":"2025-06-26 11:52:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6983200/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6983200/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11069-025-07919-4","type":"published","date":"2026-02-11T15:57:12+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":88207553,"identity":"3455585b-ebd9-4263-a994-dabeeea91f02","added_by":"auto","created_at":"2025-08-04 03:47:30","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":121256,"visible":true,"origin":"","legend":"\u003cp\u003eSchematic overview of the proposed DL framework for forecasting the Indian summer monsoon. The workflow is divided into three components: Data Pipeline (Blue), which covers pre-processing tasks Model Architecture (Green), Training \u0026amp; Evaluation (Red), Data Pre-processing and Variable\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-6983200/v1/f19d5099a6152c876dd5c782.png"},{"id":88208145,"identity":"7e9853cb-cda9-4e05-be02-d4b57da0d2d5","added_by":"auto","created_at":"2025-08-04 03:55:30","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":70645,"visible":true,"origin":"","legend":"\u003cp\u003eCDF of monthly domain-summed precipitation for the test period (2012–2024), shown for each monsoon month (JJAS).\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-6983200/v1/7f2becf6cf133a74c2f361ea.png"},{"id":88207556,"identity":"ab833aa5-d365-42be-85bb-cf4d538ba794","added_by":"auto","created_at":"2025-08-04 03:47:30","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":128093,"visible":true,"origin":"","legend":"\u003cp\u003eSpatial distribution of monthly accumulated precipitation (in meters) across the Indian monsoon domain for JJAS (test period), comparing observed (left), model-predicted (center), and bias fields (right).\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-6983200/v1/2c60c76332d63c8c230e37e4.png"},{"id":88207559,"identity":"bf25e05c-36cf-4cac-93d4-8fedf8c73cfa","added_by":"auto","created_at":"2025-08-04 03:47:30","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":77677,"visible":true,"origin":"","legend":"\u003cp\u003eLegend not included with this version.\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-6983200/v1/cfdf7dd34833e19389771d8b.png"},{"id":88207560,"identity":"a0a2f0d9-dd90-4867-ab25-684e7014cf67","added_by":"auto","created_at":"2025-08-04 03:47:30","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":33872,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003eGrouped bar chart illustrating the annual variability (test period) of correlation, Kling–Gupta Efficiency (KGE), and average bias for JJAS monsoon forecasts, highlighting year-to-year fluctuations in model performance.\u003c/em\u003e\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-6983200/v1/0ff093dc1b43ade88a46fa46.png"},{"id":102785381,"identity":"7c9bc091-282f-4db2-81ac-fa4dce682acb","added_by":"auto","created_at":"2026-02-16 16:06:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":636045,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6983200/v1_covered_3a9e04ad-cdac-459f-9ccb-d41c89406563.pdf"}],"financialInterests":"","formattedTitle":"Deep Learning-Driven Mapping of Pre-Monsoon features for Indian Summer Monsoon Precipitation Forecasting","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":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"natural-hazards","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nhaz","sideBox":"Learn more about [Natural Hazards](https://www.springer.com/journal/11069)","snPcode":"11069","submissionUrl":"https://submission.nature.com/new-submission/11069/3","title":"Natural Hazards","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Indian Monsoon, Deep Learning, Precipitation Forecasting, Spatial Bias, Extreme Events, Cumulative Distribution Function","lastPublishedDoi":"10.21203/rs.3.rs-6983200/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6983200/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate forecasting of the Indian summer monsoon is critical for water resource management, agricultural planning, and disaster mitigation. In this study, we developed a unique DL methodology to assess whether pre-monsoon atmospheric features can reliably predict monsoon season rainfall. Our model integrates several key parameters, namely, SST, SKT, near-surface air temperature (t2m), TCWV, and a convective index (vimd), which are merged to form a unified thermal variable that captures both marine and terrestrial influences. The domain-summed inland Indian region rainfall is analyzed over a test period from 2012 to 2024 using CDFs, spatial precipitation maps, frequency-of-exceedance curves, and grouped annual performance metrics. The CDF analysis reveals that observed cumulative monthly precipitation for test data has a median of approximately 1.2 m and a mean of 1.3 m, while the predicted distribution exhibits a lower median of about 1.1 m and a mean near 1.0 m, indicating systematic under-prediction, particularly in the upper tail, where the 90th percentile of observed values reaches roughly 1.8 m compared to 1.5 m for predictions. Spatial maps demonstrate that although the model captures broad rainfall patterns along the Western Ghats and Bay of Bengal, regional biases persist, with coastal areas often overestimated and inland regions underestimated. The frequency-of-exceedance analysis further indicates that the model underestimates the occurrence of extreme events. Grouped annual performance metrics, featuring an average correlation of 0.78 and a Kling\u0026ndash;Gupta Efficiency of 0.72, underscore the model\u0026rsquo;s moderate skill across varying monsoon conditions. The statistical analysis of model performance suggests that although there are associated specific systematic biases intrinsic to the model, overall, our integrated DL model effectively captures the general properties of monsoon precipitation and hence can be utilized for extended-range precipitation forecasting.\u003c/p\u003e","manuscriptTitle":"Deep Learning-Driven Mapping of Pre-Monsoon features for Indian Summer Monsoon Precipitation Forecasting","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-04 03:47:26","doi":"10.21203/rs.3.rs-6983200/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"","date":"2025-07-30T16:04:21+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-07-30T14:28:51+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"Natural Hazards","date":"2025-07-25T09:51:48+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-26T14:45:25+00:00","index":"","fulltext":""},{"type":"submitted","content":"Natural Hazards","date":"2025-06-26T07:51:54+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"natural-hazards","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nhaz","sideBox":"Learn more about [Natural Hazards](https://www.springer.com/journal/11069)","snPcode":"11069","submissionUrl":"https://submission.nature.com/new-submission/11069/3","title":"Natural Hazards","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"75041fa5-1bec-4820-b7fc-b23fc13ccfab","owner":[],"postedDate":"August 4th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-02-16T16:03:00+00:00","versionOfRecord":{"articleIdentity":"rs-6983200","link":"https://doi.org/10.1007/s11069-025-07919-4","journal":{"identity":"natural-hazards","isVorOnly":false,"title":"Natural Hazards"},"publishedOn":"2026-02-11 15:57:12","publishedOnDateReadable":"February 11th, 2026"},"versionCreatedAt":"2025-08-04 03:47:26","video":"","vorDoi":"10.1007/s11069-025-07919-4","vorDoiUrl":"https://doi.org/10.1007/s11069-025-07919-4","workflowStages":[]},"version":"v1","identity":"rs-6983200","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6983200","identity":"rs-6983200","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}