CNN–BiLSTM-Based Framework for Dam Failure Risk Prediction Using Hydrometeorological Time-Series Data

CNN–BiLSTM-Based Framework for Dam Failure Risk Prediction Using Hydrometeorological Time-Series Data | 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 CNN–BiLSTM-Based Framework for Dam Failure Risk Prediction Using Hydrometeorological Time-Series Data Mukhammadi Shamiev, Aleksandr Trofimov, Dilmurod Mardonov, Abror Yaxshiboyev This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8617422/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 Dam failure represents a critical hazard to human safety, infrastructure, and environmental stability, particularly under increasing climate variability and extreme hydrometeorological conditions. Accurate and reliable early warning systems therefore require predictive models capable of effectively capturing complex temporal dynamics in hydrometeorological processes. This study presents a CNN–BiLSTM-based deep learning framework for dam failure risk prediction using exclusively hydrometeorological time-series data. The proposed framework combines one-dimensional Convolutional Neural Networks (CNNs) for local temporal feature extraction with Bidirectional Long Short-Term Memory (BiLSTM) networks to model bidirectional temporal dependencies inherent in sequential data. The model was evaluated on a real-world hydrometeorological dataset consisting of 29,304 observations with pronounced class imbalance, where failure-related events account for approximately 10% of the samples. Model performance was assessed using evaluation metrics appropriate for imbalanced classification, including precision, recall, F1-score, receiver operating characteristic area under the curve (ROC AUC), and precision–recall area under the curve (PR AUC). The experimental results indicate that the proposed CNN–BiLSTM model achieves strong predictive performance, attaining an overall accuracy of 98.11%, a recall of 85.43% for failure events, and a PR AUC of 0.9591, while maintaining a low false alarm rate of 0.38%. These results demonstrate the capability of the proposed approach to balance early detection of potential failure events with operational reliability. The findings suggest that the CNN–BiLSTM framework offers a robust and data-driven solution for dam failure risk prediction and has significant potential for integration into real-time hydrometeorological monitoring and early warning systems. Dam failure risk Hydrometeorological time-series CNN–BiLSTM Early warning systems Imbalanced data classification 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-8617422","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":576239084,"identity":"f75ac7fe-6b15-41e8-a604-37ccedb45051","order_by":0,"name":"Mukhammadi Shamiev","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDElEQVRIie2PMUsDMRSA45Is0Vtfqba/QMghnB0U/8oVIS4nODm2TnbQ6urhn8iUuRBolhMnoUeWTnHRXaGC76zjXWk3kXxD3jfk4yWEBAJ/EkqX05BKgBB2hVP0Nkn4pEpgjWRCfgVSsmwb2H+Qcv6Z6e6OZR6l1xHl64v6uAASjW7SuiSZSRuPtYtzww9R4EC47LK8xYdB8aTqk7Nr2NZuSxlOUaCfP2ZyxjERcN6YtL60O1GGeRQY5nkhy8XKRE7buKWvDElQII2ATd3KLYWX7T3tTvEvCQrE9zyjblcAb/yLlUnrXbvju2frUQZdyqwv3xZHnWg0rk3q4OLnXPd6BZtvcjsQCAT+P987qGYIId2+3wAAAABJRU5ErkJggg==","orcid":"","institution":"National Research Nuclear University MEPhI (Moscow Engineering Physics Institute)","correspondingAuthor":true,"prefix":"","firstName":"Mukhammadi","middleName":"","lastName":"Shamiev","suffix":""},{"id":576239085,"identity":"88a309f4-0ec6-4ace-b416-7117eb324c5c","order_by":1,"name":"Aleksandr Trofimov","email":"","orcid":"","institution":"National Research Nuclear University MEPhI (Moscow Engineering Physics Institute)","correspondingAuthor":false,"prefix":"","firstName":"Aleksandr","middleName":"","lastName":"Trofimov","suffix":""},{"id":576239086,"identity":"80da088b-0540-4f80-9499-55ddfcd13e35","order_by":2,"name":"Dilmurod Mardonov","email":"","orcid":"","institution":"Urgut branch of Samarkand State University named after Sharof Rashidov, Samarkand, Uzbekistan","correspondingAuthor":false,"prefix":"","firstName":"Dilmurod","middleName":"","lastName":"Mardonov","suffix":""},{"id":576239087,"identity":"69dfc86e-d3b6-467d-8db1-c88bd08ece42","order_by":3,"name":"Abror Yaxshiboyev","email":"","orcid":"","institution":"Urgut branch of Samarkand State University named after Sharof Rashidov, Samarkand, Uzbekistan","correspondingAuthor":false,"prefix":"","firstName":"Abror","middleName":"","lastName":"Yaxshiboyev","suffix":""}],"badges":[],"createdAt":"2026-01-16 11:04:55","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8617422/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8617422/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100561109,"identity":"243fd8ac-fc9b-44f2-a149-a6759351f9ea","added_by":"auto","created_at":"2026-01-19 08:43:57","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1279808,"visible":true,"origin":"","legend":"","description":"","filename":"5CNNBiLSTMFinishHDL.docx","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/72acb5986434ca219c44034d.docx"},{"id":100560891,"identity":"9b0b9e8c-240a-49b6-9706-5295ff1afa1f","added_by":"auto","created_at":"2026-01-19 08:43:52","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6584,"visible":true,"origin":"","legend":"","description":"","filename":"626b427d4496472e912122ea41a56281.json","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/6c9b9e2553e5a74923550dc3.json"},{"id":100560932,"identity":"3bca27c8-8707-4556-b602-66d71f3247cc","added_by":"auto","created_at":"2026-01-19 08:43:53","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91649,"visible":true,"origin":"","legend":"","description":"","filename":"626b427d4496472e912122ea41a562811enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/390053c7139b17778a011ccb.xml"},{"id":100594828,"identity":"9d114a9a-d614-498e-8e73-55fb98e4d5a2","added_by":"auto","created_at":"2026-01-19 13:45:27","extension":"jpeg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":365396,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/e42802f339ff4530ac6f5306.jpeg"},{"id":100560966,"identity":"250abdb6-9e8f-4624-8a4f-bbd595d168e0","added_by":"auto","created_at":"2026-01-19 08:43:54","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":222894,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/ee9d731d04253bfc0b55a751.png"},{"id":100561018,"identity":"b993b392-dbec-4250-bb42-eb99c609f4d1","added_by":"auto","created_at":"2026-01-19 08:43:55","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":241247,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/8f1be89efb213a9e8cbaff0b.jpeg"},{"id":100561000,"identity":"9e450018-c209-4ff6-ba16-c1a3692cb4d0","added_by":"auto","created_at":"2026-01-19 08:43:54","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41732,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/49502f65b8fb3cef12450b69.png"},{"id":100561092,"identity":"e7f794e7-8de3-4aba-be57-99b64b27e6e9","added_by":"auto","created_at":"2026-01-19 08:43:56","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":163885,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/7d5e70e6082cf4cd0efca682.png"},{"id":100595269,"identity":"165f6633-485d-4283-b2af-7eaa814fba64","added_by":"auto","created_at":"2026-01-19 13:48:05","extension":"jpeg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":379473,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/f94fcea840c156f0297e806d.jpeg"},{"id":100594842,"identity":"ce171734-23dc-41d5-80ac-2f8af3fe7f78","added_by":"auto","created_at":"2026-01-19 13:45:34","extension":"jpeg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":75382,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/3b8e04a1e9d1be9745ece668.jpeg"},{"id":100561189,"identity":"8586e0d6-71e5-4d20-908f-ae3cca64bd8e","added_by":"auto","created_at":"2026-01-19 08:43:58","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":171999,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/e59bb93b4558f2b729b4aa3e.png"},{"id":100595067,"identity":"040fd9df-add0-40b3-a2c7-2926fdf18956","added_by":"auto","created_at":"2026-01-19 13:47:17","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":149575,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/bb89fba3fbbf8eff147679a0.png"},{"id":100560953,"identity":"475bf204-59a6-4ea7-a8e2-c27f3d1d5a87","added_by":"auto","created_at":"2026-01-19 08:43:53","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":46507,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/e9d8d406b9fb19a867cfe88e.png"},{"id":100560793,"identity":"7a63706c-4727-408e-bd5b-4dc0753c8a6f","added_by":"auto","created_at":"2026-01-19 08:43:50","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":51705,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/f04e6538b1659991e749a5a2.png"},{"id":100560982,"identity":"a5af9fad-d4fb-448a-bdc5-2b9400461e4a","added_by":"auto","created_at":"2026-01-19 08:43:54","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10804,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/0a187353ffcde48fb7ff10c4.png"},{"id":100595329,"identity":"9ffcc3a1-8566-4f22-a2fd-bc5c98f15313","added_by":"auto","created_at":"2026-01-19 13:48:14","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10809,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/a19824259ecd319468f4dcd4.png"},{"id":100561063,"identity":"c8a3c259-4c3e-49df-a206-8b6c09f350a3","added_by":"auto","created_at":"2026-01-19 08:43:55","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":47058,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/1d70cf7fcaa3365f3e982736.png"},{"id":100560927,"identity":"1a6a29c3-2a9a-456f-9147-fb470c6f2a27","added_by":"auto","created_at":"2026-01-19 08:43:53","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":22494,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/ef0bc2f9bab77959576c5e1f.png"},{"id":100561349,"identity":"0d70f284-46a5-469c-b5d8-323031c0b3de","added_by":"auto","created_at":"2026-01-19 08:43:59","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21903,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/d3a8bd7160cc4f8b12101613.png"},{"id":100594538,"identity":"f5c13e19-6b11-4bd7-b9de-fd8b9ac037bc","added_by":"auto","created_at":"2026-01-19 13:42:36","extension":"xml","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":90241,"visible":true,"origin":"","legend":"","description":"","filename":"626b427d4496472e912122ea41a562811structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/f84d23ce4ea74cab3dc25458.xml"},{"id":100561031,"identity":"9bcd90ce-3881-4884-a941-71817c8a5716","added_by":"auto","created_at":"2026-01-19 08:43:55","extension":"html","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":102392,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1/56811a4d6f8a5c4ff49af2a3.html"},{"id":101752855,"identity":"70d45221-dc13-48a9-9376-1641e79492cd","added_by":"auto","created_at":"2026-02-03 10:36:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":798583,"visible":true,"origin":"","legend":"","description":"","filename":"5CNNBiLSTMFinishHDL1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8617422/v1_covered_72086fb8-b980-49e6-8cba-fca377fb309c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"CNN–BiLSTM-Based Framework for Dam Failure Risk Prediction Using Hydrometeorological Time-Series Data","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Dam failure risk, Hydrometeorological time-series, CNN–BiLSTM, Early warning systems, Imbalanced data classification","lastPublishedDoi":"10.21203/rs.3.rs-8617422/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8617422/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDam failure represents a critical hazard to human safety, infrastructure, and environmental stability, particularly under increasing climate variability and extreme hydrometeorological conditions. Accurate and reliable early warning systems therefore require predictive models capable of effectively capturing complex temporal dynamics in hydrometeorological processes. This study presents a CNN\u0026ndash;BiLSTM-based deep learning framework for dam failure risk prediction using exclusively hydrometeorological time-series data.\u003c/p\u003e \u003cp\u003eThe proposed framework combines one-dimensional Convolutional Neural Networks (CNNs) for local temporal feature extraction with Bidirectional Long Short-Term Memory (BiLSTM) networks to model bidirectional temporal dependencies inherent in sequential data. The model was evaluated on a real-world hydrometeorological dataset consisting of 29,304 observations with pronounced class imbalance, where failure-related events account for approximately 10% of the samples. Model performance was assessed using evaluation metrics appropriate for imbalanced classification, including precision, recall, F1-score, receiver operating characteristic area under the curve (ROC AUC), and precision\u0026ndash;recall area under the curve (PR AUC).\u003c/p\u003e \u003cp\u003eThe experimental results indicate that the proposed CNN\u0026ndash;BiLSTM model achieves strong predictive performance, attaining an overall accuracy of 98.11%, a recall of 85.43% for failure events, and a PR AUC of 0.9591, while maintaining a low false alarm rate of 0.38%. These results demonstrate the capability of the proposed approach to balance early detection of potential failure events with operational reliability.\u003c/p\u003e \u003cp\u003eThe findings suggest that the CNN\u0026ndash;BiLSTM framework offers a robust and data-driven solution for dam failure risk prediction and has significant potential for integration into real-time hydrometeorological monitoring and early warning systems.\u003c/p\u003e","manuscriptTitle":"CNN–BiLSTM-Based Framework for Dam Failure Risk Prediction Using Hydrometeorological Time-Series Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-19 08:28:50","doi":"10.21203/rs.3.rs-8617422/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":"dc004c54-4ab1-40b4-8652-b4ff92e935a8","owner":[],"postedDate":"January 19th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-02-01T00:08:22+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-19 08:28:50","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8617422","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8617422","identity":"rs-8617422","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}