Climate Prediction Based on ConvLSTM-XGBoost Hybrid Model: Validation and Application in the Hongyuan Mountain Region

Climate Prediction Based on ConvLSTM-XGBoost Hybrid Model: Validation and Application in the Hongyuan Mountain Region | 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 Climate Prediction Based on ConvLSTM-XGBoost Hybrid Model: Validation and Application in the Hongyuan Mountain Region Dai Yanting, Wu Boxian, Ren Shuaitao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6690615/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 22 Oct, 2025 Read the published version in Scientific Reports → Version 1 posted 2 You are reading this latest preprint version Abstract To address the challenge of decoupling spatiotemporal dynamics and topographic effects in climate modeling over complex terrain, this study proposes a ConvLSTM-XGBoost hybrid model based on dynamic Bayesian weighting. Using the Hongyuan Mountain region in Yunnan, China (22.5°-23.5°N, 102.5°-103.5°E) as a case study, the model achieves high-precision climate prediction. The ConvLSTM network captures the spatiotemporal evolution patterns (e.g., southwest monsoon front propagation) in the CN05.1 climate dataset at 0.25° resolution, while XGBoost quantifies the nonlinear modulation effects of 90-meter SRTM DEM topographic features (elevation, aspect) on precipitation phases. A Bayesian Model Averaging (BMA) framework is innovatively introduced to dynamically adjust model weights (XGBoost weight 0.68±0.05 during dry seasons, ConvLSTM weight 0.72±0.07 during monsoon periods), enhancing the model’s responsiveness to extreme events. Experiments based on climate data from 1961-2022 show that the hybrid model reduces the MAE in precipitation prediction by 30.5% compared to CMIP6 (0.0089), and improves the F1 score for identifying extreme precipitation events (>50 mm/day) by 20%. For temperature prediction, the model achieves a Tmax accuracy of 96.53% (error ≤3%), with a 52% reduction in high-value dispersion. This model provides a 1-kilometer resolution decision-making tool for mountain climate risk management, supporting drought warning and hydropower scheduling needs in Yunnan’s "Climate Adaptation Plan 2035", and offers a scalable framework for climate modeling in mountainous regions worldwide. Earth and environmental sciences/Climate sciences Earth and environmental sciences/Ecology Earth and environmental sciences/Environmental sciences Hybrid model Dynamic Bayesian weighting Mountain climate prediction Extreme event detection Hongyuan Mountains Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 22 Oct, 2025 Read the published version in Scientific Reports → Version 1 posted Submission checks completed at journal 20 May, 2025 First submitted to journal 20 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-6690615","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":459277788,"identity":"73816203-5204-476b-a04b-0df537d0530a","order_by":0,"name":"Dai Yanting","email":"","orcid":"","institution":"Southwest Forestry University, Yunnan Kunming","correspondingAuthor":false,"prefix":"","firstName":"Dai","middleName":"","lastName":"Yanting","suffix":""},{"id":459277789,"identity":"e11ed628-30e6-4550-b735-1cf833c8aa93","order_by":1,"name":"Wu Boxian","email":"","orcid":"","institution":"Southwest Forestry University","correspondingAuthor":false,"prefix":"","firstName":"Wu","middleName":"","lastName":"Boxian","suffix":""},{"id":459277790,"identity":"a0bfad3c-96d7-4e6c-81ec-221b62b8e1cf","order_by":2,"name":"Ren Shuaitao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8klEQVRIiWNgGAWjYJACZiDmAWLGBwwMciABA+K0APUwA5UaE68FZA2bBFFazNt7D38ubLOTsWc/fKzyZ5tBYgN78zYJhpo7OLXInDmXJj2zLZmHhyct7TYvSAvPsTIJhmPPcGqRkMgxY+ZtYwb6JcfsNuO2P4kNQBEJxobDuLXIvzH+zNtWz8PD/8as8Oc2oC3ybwhokeAxkOZtO8zDAzScgRekRYKHgBaeHDNpnnPHeXhuPEuW5v1nYNzGk1ZskXAMjxb2M8afecqq7dn7kw9+/HHGQLaf/fDGGx9qcGvBBGwgIoEEDaNgFIyCUTAKMAEAmiJIMz/pwWQAAAAASUVORK5CYII=","orcid":"","institution":"Southwest Forestry University, Yunnan Kunming","correspondingAuthor":true,"prefix":"","firstName":"Ren","middleName":"","lastName":"Shuaitao","suffix":""}],"badges":[],"createdAt":"2025-05-18 08:38:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6690615/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6690615/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-20882-1","type":"published","date":"2025-10-22T16:17:27+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":94490362,"identity":"fe28bf1f-0a04-4a53-8f25-43a37ebf59b8","added_by":"auto","created_at":"2025-10-27 17:09:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2001029,"visible":true,"origin":"","legend":"","description":"","filename":"nature.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6690615/v1_covered_40cce21b-022f-43e0-ac73-8e70050642e1.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Climate Prediction Based on ConvLSTM-XGBoost Hybrid Model: Validation and Application in the Hongyuan Mountain Region","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Hybrid model, Dynamic Bayesian weighting, Mountain climate prediction, Extreme event detection, Hongyuan Mountains","lastPublishedDoi":"10.21203/rs.3.rs-6690615/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6690615/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTo address the challenge of decoupling spatiotemporal dynamics and topographic effects in climate modeling over complex terrain, this study proposes a ConvLSTM-XGBoost hybrid model based on dynamic Bayesian weighting. Using the Hongyuan Mountain region in Yunnan, China (22.5°-23.5°N, 102.5°-103.5°E) as a case study, the model achieves high-precision climate prediction. The ConvLSTM network captures the spatiotemporal evolution patterns (e.g., southwest monsoon front propagation) in the CN05.1 climate dataset at 0.25° resolution, while XGBoost quantifies the nonlinear modulation effects of 90-meter SRTM DEM topographic features (elevation, aspect) on precipitation phases. A Bayesian Model Averaging (BMA) framework is innovatively introduced to dynamically adjust model weights (XGBoost weight 0.68±0.05 during dry seasons, ConvLSTM weight 0.72±0.07 during monsoon periods), enhancing the model’s responsiveness to extreme events. Experiments based on climate data from 1961-2022 show that the hybrid model reduces the MAE in precipitation prediction by 30.5% compared to CMIP6 (0.0089), and improves the F1 score for identifying extreme precipitation events (\u0026gt;50 mm/day) by 20%. For temperature prediction, the model achieves a Tmax accuracy of 96.53% (error ≤3%), with a 52% reduction in high-value dispersion. This model provides a 1-kilometer resolution decision-making tool for mountain climate risk management, supporting drought warning and hydropower scheduling needs in Yunnan’s \"Climate Adaptation Plan 2035\", and offers a scalable framework for climate modeling in mountainous regions worldwide.\u003c/p\u003e","manuscriptTitle":"Climate Prediction Based on ConvLSTM-XGBoost Hybrid Model: Validation and Application in the Hongyuan Mountain Region","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-28 06:52:32","doi":"10.21203/rs.3.rs-6690615/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"checksComplete","content":"","date":"2025-05-20T10:54:25+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-05-20T10:53:17+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":"77fe2ca3-2232-48d4-8b65-eda625b2200b","owner":[],"postedDate":"May 28th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":48788843,"name":"Earth and environmental sciences/Climate sciences"},{"id":48788844,"name":"Earth and environmental sciences/Ecology"},{"id":48788845,"name":"Earth and environmental sciences/Environmental sciences"}],"tags":[],"updatedAt":"2025-10-27T16:28:23+00:00","versionOfRecord":{"articleIdentity":"rs-6690615","link":"https://doi.org/10.1038/s41598-025-20882-1","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-10-22 16:17:27","publishedOnDateReadable":"October 22nd, 2025"},"versionCreatedAt":"2025-05-28 06:52:32","video":"","vorDoi":"10.1038/s41598-025-20882-1","vorDoiUrl":"https://doi.org/10.1038/s41598-025-20882-1","workflowStages":[]},"version":"v1","identity":"rs-6690615","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6690615","identity":"rs-6690615","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}