Groundwater level prediction in Datong Basin based on multivariate LSTM neural network

Groundwater level prediction in Datong Basin based on multivariate LSTM neural network | 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 Groundwater level prediction in Datong Basin based on multivariate LSTM neural network Cang-Ning Wang, Ge Ning, Dong-Yang Su, Ya-Ting Zhang, Fang Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5310115/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 Considering that the groundwater level is influenced by a variety of complex factors, this paper constructs a groundwater level prediction model by introducing multiple variables to adapt to different geological and meteorological conditions. This model is established using a multivariate long short-term memory (M-LSTM) network in combination with an attention mechanism to provide an efficient artificial intelligence method for predicting groundwater levels. The model is trained using groundwater level data, normalized difference vegetation index (NDVI), rainfall, average air temperature, and relative humidity from 2018 to 2019 in the Datong Basin and validated with 2020 groundwater level data. Results indicate that the M-LSTM combined with the attention mechanism accurately predicts future groundwater level changes based on historical data, achieving root mean square errors (RMSE) of 0.2131, 0.2033, and 0.2844 in three experiments, demonstrating a high model fit. Meanwhile, an investigation of hydrogeology, meteorological data, and groundwater resources in the Datong Basin was conducted to perform a groundwater early warning analysis based on the extent of groundwater over-exploitation. The depth of groundwater in each area of the Datong Basin was predicted for the end of 2035 under high, medium, and low exploitation modes and varying precipitation conditions, with a quantitative analysis of the funnel center's location. numerical simulation LSTM Datong Basin predictive analysis 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-5310115","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":369351775,"identity":"9de57b65-323d-4991-95f5-6de8cb222095","order_by":0,"name":"Cang-Ning Wang","email":"","orcid":"","institution":"Taiyuan University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Cang-Ning","middleName":"","lastName":"Wang","suffix":""},{"id":369351776,"identity":"e4416457-e08c-420f-82ef-d00c851b38d7","order_by":1,"name":"Ge Ning","email":"","orcid":"","institution":"Xichang City Water Resources Bureau Heisha River Management Station","correspondingAuthor":false,"prefix":"","firstName":"Ge","middleName":"","lastName":"Ning","suffix":""},{"id":369351777,"identity":"251a4c79-730a-41f7-b0a3-2a6f00f1115e","order_by":2,"name":"Dong-Yang Su","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7klEQVRIiWNgGAWjYHACxgcfDGzk+NmbDwA5EjLEaGE2nFGQZizZcywBpIWHGC1swhwfDicazMgxAPEIa5HvP/6MmcGAOcGAIefzqxs1FjwM7IePbsCnxeBGjtnjAgO2PHOGs9usc44BHcaTlnYDrxYJHnbjGQY8xZaNvduMc9iAWiR4zPBqATlMmsdAInHDYZ5nxjn/iNDCcCDBDKjFIHHDMR7mx7ltRGgB+sXYcIZBAjCQ2cyYc/skeNgI+QXosIcPPvz5L8cv//jx55xvdcA4PXwMv8OQAJsEmCRWOQgwfyBF9SgYBaNgFIwcAACrEUgMz0OJLAAAAABJRU5ErkJggg==","orcid":"","institution":"Taiyuan University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Dong-Yang","middleName":"","lastName":"Su","suffix":""},{"id":369351778,"identity":"cc21c4b2-320b-46a8-ae05-8574440a6d98","order_by":3,"name":"Ya-Ting Zhang","email":"","orcid":"","institution":"Taiyuan University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Ya-Ting","middleName":"","lastName":"Zhang","suffix":""},{"id":369351779,"identity":"9a870193-befc-4992-be9d-e8c9fd574803","order_by":4,"name":"Fang Zhang","email":"","orcid":"","institution":"Taiyuan University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Fang","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2024-10-22 08:53:32","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5310115/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5310115/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":72492504,"identity":"72305a3e-0606-4593-987d-e5c0d68f1d43","added_by":"auto","created_at":"2024-12-27 23:31:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1142590,"visible":true,"origin":"","legend":"","description":"","filename":"GroundwaterlevelpredictioninDatongBasinbasedonmultivariateLSTMneuralnetwork..pdf","url":"https://assets-eu.researchsquare.com/files/rs-5310115/v1_covered_bf2fbfb9-e12d-4ccd-9344-8cbfefc202d8.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Groundwater level prediction in Datong Basin based on multivariate LSTM neural network","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":"numerical simulation, LSTM, Datong Basin, predictive analysis","lastPublishedDoi":"10.21203/rs.3.rs-5310115/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5310115/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eConsidering that the groundwater level is influenced by a variety of complex factors, this paper constructs a groundwater level prediction model by introducing multiple variables to adapt to different geological and meteorological conditions. This model is established using a multivariate long short-term memory (M-LSTM) network in combination with an attention mechanism to provide an efficient artificial intelligence method for predicting groundwater levels. The model is trained using groundwater level data, normalized difference vegetation index (NDVI), rainfall, average air temperature, and relative humidity from 2018 to 2019 in the Datong Basin and validated with 2020 groundwater level data. Results indicate that the M-LSTM combined with the attention mechanism accurately predicts future groundwater level changes based on historical data, achieving root mean square errors (RMSE) of 0.2131, 0.2033, and 0.2844 in three experiments, demonstrating a high model fit. Meanwhile, an investigation of hydrogeology, meteorological data, and groundwater resources in the Datong Basin was conducted to perform a groundwater early warning analysis based on the extent of groundwater over-exploitation. The depth of groundwater in each area of the Datong Basin was predicted for the end of 2035 under high, medium, and low exploitation modes and varying precipitation conditions, with a quantitative analysis of the funnel center's location.\u003c/p\u003e","manuscriptTitle":"Groundwater level prediction in Datong Basin based on multivariate LSTM neural network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-05 17:16:31","doi":"10.21203/rs.3.rs-5310115/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":"9100d33c-818e-4151-95bd-d713f9fe33c4","owner":[],"postedDate":"November 5th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-12-27T23:23:09+00:00","versionOfRecord":[],"versionCreatedAt":"2024-11-05 17:16:31","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5310115","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5310115","identity":"rs-5310115","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}