Integrating Artificial Neural Networks into SEIR Models for Adaptive Epidemic Forecasting

Integrating Artificial Neural Networks into SEIR Models for Adaptive Epidemic Forecasting | 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 Integrating Artificial Neural Networks into SEIR Models for Adaptive Epidemic Forecasting Milad tahavor, Nader Hosseingholipouraghdamtasouj, Mahdiyeh Baseri Bagh Siyah This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7651422/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 In this paper, we present an extended version of the classical SEIR epidemic model in which the key parameters are no longer fixed but adapt dynamically through an artificial neural network (ANN). By feeding the ANN with external signals such as policy interventions, population mobility, seasonal factors, and vaccination coverage the model is able to reflect how real outbreaks respond to changing social and environmental conditions. Our theoretical analysis confirms that the ANN-SEIR system remains mathematically consistent: solutions stay positive and bounded, and the time-dependent reproduction number R 0 ( t ) continues to determine whether a disease dies out or persists. Numerical experiments further demonstrate that adaptive behavior and timely interventions can significantly change the trajectory of an epidemic. Overall, the proposed approach brings together the strengths of traditional epidemiological modeling and modern machine learning. It provides a flexible, data-informed tool for understanding epidemic dynamics and for exploring possible outcomes under different policy or behavioral scenarios. SEIR model Artificial Neural Network (ANN) Epidemic modeling Time-varying parameters Disease-free equilibrium Endemic equilibrium Stability analysis Behavioral response Public health interventions. Full Text Additional Declarations The authors declare no competing interests. Supplementary Files SEIRmodelwithANN.rar 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-7651422","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":517205252,"identity":"2d963a2c-ac82-47aa-beaf-88662aecb447","order_by":0,"name":"Milad tahavor","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAElEQVRIiWNgGAWjYDACZuYGBh4GhgQw50OFDZBkbDyAXwsjUEsCRAvjjDNpIKoBvxYGJC3MnG2HwWJ4tei2MzZ+ePvDLo9/RvKxz4xt5+3Wth8G2lJjE41Li9lhxmbJOQnJxRI30pJnF5y7nbztTCJQy7G03AbcWhqkeRKYExvOnDFmnlF2O9nsAFALY8NhfFqaf/Mk1CfOB2nhYTuXbHb+IUEtbUBbDiduON4D1NJ2wM7sBmFb2iznpB1P3Hi8LRkYyMkJZjeAtiTg88v5w4dvvLGpTpx3mPkwMCrt7M3Opz988KHGBqcWDJAIVplArHIQsCdF8SgYBaNgFIwMAACNWGmSOrhDWQAAAABJRU5ErkJggg==","orcid":"","institution":"Department of Mathematics, Iran University of Science and Technology, Tehran, Iran","correspondingAuthor":true,"prefix":"","firstName":"Milad","middleName":"","lastName":"tahavor","suffix":""},{"id":517205317,"identity":"af19f851-846e-4c02-8c84-721f6c3ff0ec","order_by":1,"name":"Nader Hosseingholipouraghdamtasouj","email":"","orcid":"","institution":"Department of Physics and Energy Engineering, Amirkabir University of Technology, Tehran, Iran","correspondingAuthor":false,"prefix":"","firstName":"Nader","middleName":"","lastName":"Hosseingholipouraghdamtasouj","suffix":""},{"id":517205364,"identity":"e3846061-7242-422c-96ff-48b508da91c1","order_by":2,"name":"Mahdiyeh Baseri Bagh Siyah","email":"","orcid":"","institution":"Department of Mechanical Engineering, Sharif University of Technology, Tehran, Iran","correspondingAuthor":false,"prefix":"","firstName":"Mahdiyeh","middleName":"Baseri Bagh","lastName":"Siyah","suffix":""}],"badges":[],"createdAt":"2025-09-18 15:55:43","currentVersionCode":1,"declarations":{"humanSubjects":true,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":true,"humanSubjectConsent":true,"humanSubjectClinicalTrial":true,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7651422/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7651422/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91898122,"identity":"e1c53780-a662-4897-9d02-6a9ae12995b4","added_by":"auto","created_at":"2025-09-22 19:07:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1229242,"visible":true,"origin":"","legend":"","description":"","filename":"SEIRmodelwithANN.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7651422/v1_covered_a3451de9-2ddc-4309-932f-e1a1386a089e.pdf"},{"id":91898004,"identity":"09820a24-08f1-43ae-9787-491ee780b1d5","added_by":"auto","created_at":"2025-09-22 18:59:22","extension":"rar","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2028837,"visible":true,"origin":"","legend":"","description":"","filename":"SEIRmodelwithANN.rar","url":"https://assets-eu.researchsquare.com/files/rs-7651422/v1/21478c8003736e34716eb6e4.rar"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eIntegrating Artificial Neural Networks into SEIR Models for Adaptive Epidemic Forecasting\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Iran University of Science and Technology","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"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":"SEIR model, Artificial Neural Network (ANN), Epidemic modeling, Time-varying parameters, Disease-free equilibrium, Endemic equilibrium, Stability analysis, Behavioral response, Public health interventions.","lastPublishedDoi":"10.21203/rs.3.rs-7651422/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7651422/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn this paper, we present an extended version of the classical SEIR epidemic model in which the key parameters are no longer fixed but adapt dynamically through an artificial neural network (ANN). By feeding the ANN with external signals such as policy interventions, population mobility, seasonal factors, and vaccination coverage the model is able to reflect how real outbreaks respond to changing social and environmental conditions. Our theoretical analysis confirms that the ANN-SEIR system remains mathematically consistent: solutions stay positive and bounded, and the time-dependent reproduction number \u003cem\u003eR\u003c/em\u003e\u003csub\u003e0\u003c/sub\u003e(\u003cem\u003et\u003c/em\u003e) continues to determine whether a disease dies out or persists. Numerical experiments further demonstrate that adaptive behavior and timely interventions can significantly change the trajectory of an epidemic. Overall, the proposed approach brings together the strengths of traditional epidemiological modeling and modern machine learning. It provides a flexible, data-informed tool for understanding epidemic dynamics and for exploring possible outcomes under different policy or behavioral scenarios.\u003c/p\u003e","manuscriptTitle":"Integrating Artificial Neural Networks into SEIR Models for Adaptive Epidemic Forecasting","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-22 18:59:17","doi":"10.21203/rs.3.rs-7651422/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":"dd830619-0af5-4315-a264-c6a360e7c512","owner":[],"postedDate":"September 22nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-09-22T18:59:17+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-22 18:59:17","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7651422","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7651422","identity":"rs-7651422","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}