ML-based diagnostics of spatial precipitation maximum using large-scale atmospheric predictors in midlatitudes

ML-based diagnostics of spatial precipitation maximum using large-scale atmospheric predictors in midlatitudes | 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 ML-based diagnostics of spatial precipitation maximum using large-scale atmospheric predictors in midlatitudes Yulia Yarinich, Mikhail Krinitskiy, Mikhail Varentsov, Victor Stepanenko, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7940169/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 This study is devoted to the problem of statistical downscaling of summer precipitation using the example of the Moscow region. We propose an approach to downscaling the local maximum of daily precipitation amounts within the region using machine learning (ML) models based on predictors characterizing large-scale meteorological processes. The study is based on 33 years of daily maximum precipitation data collected from 27 weather stations in the Moscow region used for ML model training and evaluation. We propose a set of physically justified precipitation predictors from ERA5 reanalysis (averaged over the region) including basic atmospheric variables (temperature, humidity, etc.) at different vertical levels as well as more complex indices characterizing convective instability, wind shear, humidity and circulation indicators. We evaluate three different ML models and several configurations of the feature selection and processing. The gradient boosting model with the daily averaged, standardized predictor set, including the reanalysis precipitation, demonstrated the best quality, with RMSE of 8.47 mm and R 2 of 0.6. The feature importance analysis revealed that the mean precipitation from reanalysis as well as several complex indices are the key influencing factors for precipitation maxima. Machine Learning statistical downscaling precipitation rainfall convective indices ERA5 station data Random Forest Ridge Regressor CatBoost Perfect Prognosis 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-7940169","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":544006098,"identity":"640a1f25-9eea-4ece-a63e-58d0ddc60b24","order_by":0,"name":"Yulia Yarinich","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/UlEQVRIiWNgGAWjYBACxgbmhgNgFjMDwwHGBhsQ04CAFkYULWmEtYA0IbMPE9bCPCOx8cAPhsPy5u28Bw/83HE+sX9288bHPAz3EhtwaGGckdhwsIfhsOGcw3wJB3vP3E6ccedYseEMhmK8Wg7wMBxmnMHMY3CYse12YsONHDOJDwwJ+G35w3DYHqrlXOL8GznmPxIIaDkMtCURquVA4gagLQx4bel52HBYxiA9GaTlYG9bsvHGG2nFkjMMEoxxaTFsTz788U2Fte0M/jPGH3622cnOu5G88TNPRYIsTi1gCYNmuIAjRCWeqJGHUHVwAXvcakfBKBgFo2CkAgDNVmOW0GotjQAAAABJRU5ErkJggg==","orcid":"","institution":"Lomonosov Moscow State University","correspondingAuthor":true,"prefix":"","firstName":"Yulia","middleName":"","lastName":"Yarinich","suffix":""},{"id":544006101,"identity":"a152e71b-0edb-4316-aafe-597d3bec75a5","order_by":1,"name":"Mikhail Krinitskiy","email":"","orcid":"","institution":"Moscow Institute of Physics and Technology","correspondingAuthor":false,"prefix":"","firstName":"Mikhail","middleName":"","lastName":"Krinitskiy","suffix":""},{"id":544006102,"identity":"aa90e59d-63e9-4eb6-9b54-95bd6d08f37a","order_by":2,"name":"Mikhail Varentsov","email":"","orcid":"","institution":"Lomonosov Moscow State University","correspondingAuthor":false,"prefix":"","firstName":"Mikhail","middleName":"","lastName":"Varentsov","suffix":""},{"id":544006103,"identity":"f6ef7963-c915-4ef0-92cc-829d6b10e761","order_by":3,"name":"Victor Stepanenko","email":"","orcid":"","institution":"Lomonosov Moscow State University","correspondingAuthor":false,"prefix":"","firstName":"Victor","middleName":"","lastName":"Stepanenko","suffix":""},{"id":544006106,"identity":"3e6904a8-b12a-40ac-ab9a-b9a9f210934b","order_by":4,"name":"Sergey Davletshin","email":"","orcid":"","institution":"Russian Institute of Hydrometeorological Information–World Data Center","correspondingAuthor":false,"prefix":"","firstName":"Sergey","middleName":"","lastName":"Davletshin","suffix":""},{"id":544006108,"identity":"31607ed6-f3b1-436e-a175-629c6987d9c7","order_by":5,"name":"Elena Dronova","email":"","orcid":"","institution":"Russian State Agrarian University – Moscow Timiryazev Agricultural Academy","correspondingAuthor":false,"prefix":"","firstName":"Elena","middleName":"","lastName":"Dronova","suffix":""},{"id":544006109,"identity":"75afe2d1-e99b-4c7f-ba3c-bc64151b0c61","order_by":6,"name":"Eduardo Bezerra","email":"","orcid":"","institution":"Federal Center for Technological Education of Rio de Janeiro (Cefet/RJ)","correspondingAuthor":false,"prefix":"","firstName":"Eduardo","middleName":"","lastName":"Bezerra","suffix":""},{"id":544006110,"identity":"99150e4b-cebc-4f39-8097-df445c0a6717","order_by":7,"name":"Fabio Porto","email":"","orcid":"","institution":"Laboratório Nacional de Computação Científica","correspondingAuthor":false,"prefix":"","firstName":"Fabio","middleName":"","lastName":"Porto","suffix":""}],"badges":[],"createdAt":"2025-10-24 21:55:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7940169/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7940169/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95784480,"identity":"341a8e8e-4813-4ce0-a996-1e780606f227","added_by":"auto","created_at":"2025-11-13 04:45:08","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":830709,"visible":true,"origin":"","legend":"","description":"","filename":"yarinichetalMoscow.docx","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/03d8090ec9c0527b2ee2e267.docx"},{"id":95784476,"identity":"cbbff147-97b8-4623-ac49-153bac16524d","added_by":"auto","created_at":"2025-11-13 04:45:08","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9059,"visible":true,"origin":"","legend":"","description":"","filename":"18da43d316314532b47cd155cbf151a7.json","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/df590dde0b30c5f7f6c2e615.json"},{"id":95784478,"identity":"a69cc446-5a44-4e6a-b49a-735450533015","added_by":"auto","created_at":"2025-11-13 04:45:08","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":214833,"visible":true,"origin":"","legend":"","description":"","filename":"18da43d316314532b47cd155cbf151a71enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/116c5f5b496931f22f71fe52.xml"},{"id":95802619,"identity":"4c7a60c3-0796-44ce-ad38-9d2c730d01fb","added_by":"auto","created_at":"2025-11-13 08:28:08","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":168093,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/99c868d9adc5b09681d83d2f.png"},{"id":95784483,"identity":"1d6d71c2-a22f-4dc3-b0a0-9532f7adbdf7","added_by":"auto","created_at":"2025-11-13 04:45:08","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":106547,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/6fa458bcfb563bfadc701a2f.png"},{"id":95801775,"identity":"56e816f4-85c3-49a0-8fb4-0bd92fb9a665","added_by":"auto","created_at":"2025-11-13 08:26:07","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":302915,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/78ba6ffb30a7a26d0318c078.jpeg"},{"id":95784481,"identity":"3d540f7d-3ffd-455a-90ac-f482fd93c9de","added_by":"auto","created_at":"2025-11-13 04:45:08","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":201218,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/60ccf248c4808807453fd8aa.jpeg"},{"id":95802166,"identity":"5f6ac4e5-6765-425f-a6c9-ab94c5714ac4","added_by":"auto","created_at":"2025-11-13 08:27:04","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":129865,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/ea43751a1d199cf8b0e51824.png"},{"id":95784477,"identity":"b76eb413-4d27-46b1-a210-ced82b7ebb28","added_by":"auto","created_at":"2025-11-13 04:45:08","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":31256,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/99581b4785baf38c16f36079.png"},{"id":95784490,"identity":"74b61601-0dab-46a8-8ba6-c405f735297e","added_by":"auto","created_at":"2025-11-13 04:45:08","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":108293,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/270e6538bee33977cdeec241.png"},{"id":95802110,"identity":"e2e9fa76-f543-4536-acca-0023f9fb0fc0","added_by":"auto","created_at":"2025-11-13 08:26:55","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41005,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/c2e75895f439adc953255ecd.png"},{"id":95802530,"identity":"e2b78c1b-fb1a-47c8-9c1f-a00b15a558dc","added_by":"auto","created_at":"2025-11-13 08:27:48","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27476,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/bf831c95c1224a5f1b53d6d5.png"},{"id":95784491,"identity":"60daa901-fd1e-4269-8344-918e3d916dc1","added_by":"auto","created_at":"2025-11-13 04:45:08","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":45340,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/888edb596c3601060ad0bbc0.png"},{"id":95784485,"identity":"22697ed6-9d6d-499f-8962-7f81901023c3","added_by":"auto","created_at":"2025-11-13 04:45:08","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":48926,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/5692b65d51fc86029e7cbeea.png"},{"id":95784487,"identity":"dcd00414-f1c4-4021-b8f8-227bd428e777","added_by":"auto","created_at":"2025-11-13 04:45:08","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32535,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/d39dffcb8dbd89d9dd3d5a91.png"},{"id":95784486,"identity":"e88a75be-c1fa-4c2e-8d67-7c38902a8acd","added_by":"auto","created_at":"2025-11-13 04:45:08","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10563,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/9fe68fd7c94c4b688b07d71f.png"},{"id":95784489,"identity":"eda2b7a2-b46e-4331-b943-c51197e1d78c","added_by":"auto","created_at":"2025-11-13 04:45:08","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":22638,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/2a636ec039fd7167c8597784.png"},{"id":95784494,"identity":"45ab5e72-66cd-47eb-a017-cedca5b6d7f9","added_by":"auto","created_at":"2025-11-13 04:45:09","extension":"xml","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":213302,"visible":true,"origin":"","legend":"","description":"","filename":"18da43d316314532b47cd155cbf151a71structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/a7ca2d2d9cd952933a933171.xml"},{"id":95802547,"identity":"f22194b4-748e-4a0f-81c2-ee30231d1ceb","added_by":"auto","created_at":"2025-11-13 08:27:51","extension":"html","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":225073,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1/c7f6f4029526793be827c4ac.html"},{"id":98776478,"identity":"ee359ecd-8467-49d0-a7b1-bfe40b7ef94a","added_by":"auto","created_at":"2025-12-22 12:22:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":929815,"visible":true,"origin":"","legend":"","description":"","filename":"yarinichetalMoscow.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7940169/v1_covered_4b8f6eb6-b1a4-4840-8412-06dec26c0046.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"ML-based diagnostics of spatial precipitation maximum using large-scale atmospheric predictors in midlatitudes","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":"Machine Learning, statistical downscaling, precipitation, rainfall, convective indices, ERA5, station data, Random Forest, Ridge Regressor, CatBoost, Perfect Prognosis","lastPublishedDoi":"10.21203/rs.3.rs-7940169/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7940169/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study is devoted to the problem of statistical downscaling of summer precipitation using the example of the Moscow region. We propose an approach to downscaling the local maximum of daily precipitation amounts within the region using machine learning (ML) models based on predictors characterizing large-scale meteorological processes. The study is based on 33 years of daily maximum precipitation data collected from 27 weather stations in the Moscow region used for ML model training and evaluation. We propose a set of physically justified precipitation predictors from ERA5 reanalysis (averaged over the region) including basic atmospheric variables (temperature, humidity, etc.) at different vertical levels as well as more complex indices characterizing convective instability, wind shear, humidity and circulation indicators. We evaluate three different ML models and several configurations of the feature selection and processing. The gradient boosting model with the daily averaged, standardized predictor set, including the reanalysis precipitation, demonstrated the best quality, with RMSE of 8.47 mm and R\u003csup\u003e2\u003c/sup\u003e of 0.6. The feature importance analysis revealed that the mean precipitation from reanalysis as well as several complex indices are the key influencing factors for precipitation maxima.\u003c/p\u003e","manuscriptTitle":"ML-based diagnostics of spatial precipitation maximum using large-scale atmospheric predictors in midlatitudes","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-13 04:45:03","doi":"10.21203/rs.3.rs-7940169/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":"111eedf2-ce96-4eb3-9a12-4bba06623164","owner":[],"postedDate":"November 13th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-12-21T07:38:50+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-13 04:45:03","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7940169","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7940169","identity":"rs-7940169","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}