Mechanism-informed prediction of complex karst water inflow: overcoming strong nonlinearity via a hybrid deep learning framework

Mechanism-informed prediction of complex karst water inflow: overcoming strong nonlinearity via a hybrid deep learning framework | 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 Mechanism-informed prediction of complex karst water inflow: overcoming strong nonlinearity via a hybrid deep learning framework Wenfei Chi, Jiazhong Qian, Yong Liu, Lei Ma, Yaping Zhang, Xin Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8972488/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 To address the challenges of strong nonlinearity and non-stationarity in predicting water inflow in karst engineering, this study investigates an underground intake pumping station of the Shanxi Yellow River Diversion Project, systematically revealing the nonlinear causes of inflow dynamics. The research reveals that the low-permeability boundary formed by lining construction transforms karst seepage from matrix diffuse flow to conduit concentrated flow, significantly amplifying the system's pulse response to extreme meteorological forcing. Based on this mechanism, a hybrid predictive framework integrating CEEMDAN, LSTM, and a Self-Attention (SA) mechanism was developed, with a focus on comparing the predictive performance of two SA topological configurations: pre-positioned and post-positioned. Experiments confirm that the topological placement of SA significantly impacts nonlinear capture capability: when positioned subsequent to the LSTM layer as a "global feature recalibrator," it effectively compensates for the LSTM gating mechanism's "smoothing effect" on low-energy pulse signals, achieving high-fidelity capture of nonlinear abrupt change features through cross-temporal association reweighting. Results show that the post-positioned architecture achieves high accuracy with R² = 0.902, MAE = 0.002, and RMSE = 0.003. Compared to the pre-positioned architecture, the post-positioned configuration further reduces RMSE and MAE by approximately 50% and 67%, respectively, significantly enhancing hazard identification sensitivity in data-sparse karst regions. This provides a scientific basis for transitioning disaster prevention management from passive sealing to mechanism-driven proactive early warning. Water inflow Karst geology Underground engineering Self-Attention (SA) Long Short-Term Memory (LSTM) 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-8972488","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":599479283,"identity":"371b4159-c1ba-415e-a48d-fb80f46f142d","order_by":0,"name":"Wenfei Chi","email":"","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Wenfei","middleName":"","lastName":"Chi","suffix":""},{"id":599479284,"identity":"236a58c5-9807-48e3-9c7d-0d06f99d5f49","order_by":1,"name":"Jiazhong Qian","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABB0lEQVRIiWNgGAWjYDACZiCWMGBgMABxPjbIgQUliNbCOLPBmIGHoBYYAGlh5iVGC99x5mcPLArs7M3Zew+/tt1hkLifgfngbR4GuzxcWiQPs5kbSBgkM1v2nEuzzj1jkNjDwJZszcOQXIzTPYcZzCQkDJjZDG7kmBnntv0BauExk+ZhOJDYgFML+zeglnoesBbLNpAt/N8IaOEB2XJYAqjF+DEjWAsPG14tkod5yoBajhsYnDljxtjbZmDcc5jN2HKOQTJOLXznj2+TlvhTbW9wvMf4w882A9n29uaHN95U2OHUwnAAGB3QaGCD0MxgB+NSD9HC+AHCZP6AR90oGAWjYBSMYAAADGROgLj3PPoAAAAASUVORK5CYII=","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Jiazhong","middleName":"","lastName":"Qian","suffix":""},{"id":599479286,"identity":"d8d7bcf3-8be1-4316-b8c7-510fb6a754ee","order_by":2,"name":"Yong Liu","email":"","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yong","middleName":"","lastName":"Liu","suffix":""},{"id":599479288,"identity":"61558816-4cbd-4e23-b5e4-4e524fadefde","order_by":3,"name":"Lei Ma","email":"","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Lei","middleName":"","lastName":"Ma","suffix":""},{"id":599479291,"identity":"646ddf3e-13fc-44af-8928-2c1c58d9107d","order_by":4,"name":"Yaping Zhang","email":"","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yaping","middleName":"","lastName":"Zhang","suffix":""},{"id":599479293,"identity":"d07531d3-f90b-473b-8201-4c1be15aee33","order_by":5,"name":"Xin Zhang","email":"","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2026-02-26 02:39:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8972488/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8972488/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104402256,"identity":"fe9330c1-8e36-4f5a-b106-96907cf0c15d","added_by":"auto","created_at":"2026-03-11 12:14:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2116751,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8972488/v1_covered_72a6ba14-2b28-4461-b3fe-23f121907440.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Mechanism-informed prediction of complex karst water inflow: overcoming strong nonlinearity via a hybrid deep learning framework","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":"Water inflow, Karst geology, Underground engineering, Self-Attention (SA), Long Short-Term Memory (LSTM)","lastPublishedDoi":"10.21203/rs.3.rs-8972488/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8972488/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTo address the challenges of strong nonlinearity and non-stationarity in predicting water inflow in karst engineering, this study investigates an underground intake pumping station of the Shanxi Yellow River Diversion Project, systematically revealing the nonlinear causes of inflow dynamics. The research reveals that the low-permeability boundary formed by lining construction transforms karst seepage from matrix diffuse flow to conduit concentrated flow, significantly amplifying the system's pulse response to extreme meteorological forcing. Based on this mechanism, a hybrid predictive framework integrating CEEMDAN, LSTM, and a Self-Attention (SA) mechanism was developed, with a focus on comparing the predictive performance of two SA topological configurations: pre-positioned and post-positioned. Experiments confirm that the topological placement of SA significantly impacts nonlinear capture capability: when positioned subsequent to the LSTM layer as a \"global feature recalibrator,\" it effectively compensates for the LSTM gating mechanism's \"smoothing effect\" on low-energy pulse signals, achieving high-fidelity capture of nonlinear abrupt change features through cross-temporal association reweighting. Results show that the post-positioned architecture achieves high accuracy with R\u0026sup2; = 0.902, MAE\u0026thinsp;=\u0026thinsp;0.002, and RMSE\u0026thinsp;=\u0026thinsp;0.003. Compared to the pre-positioned architecture, the post-positioned configuration further reduces RMSE and MAE by approximately 50% and 67%, respectively, significantly enhancing hazard identification sensitivity in data-sparse karst regions. This provides a scientific basis for transitioning disaster prevention management from passive sealing to mechanism-driven proactive early warning.\u003c/p\u003e","manuscriptTitle":"Mechanism-informed prediction of complex karst water inflow: overcoming strong nonlinearity via a hybrid deep learning framework","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-05 11:47:39","doi":"10.21203/rs.3.rs-8972488/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":"123413d9-8f29-4c9f-b4fa-cad57fb1f1dc","owner":[],"postedDate":"March 5th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-05T11:47:39+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-05 11:47:39","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8972488","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8972488","identity":"rs-8972488","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}