Variational Autoencoder-Assisted Accelerated Benders Decomposition for Resilient Stochastic Air Transport Network Reconfiguration under Airspace Disruptions

Variational Autoencoder-Assisted Accelerated Benders Decomposition for Resilient Stochastic Air Transport Network Reconfiguration under Airspace Disruptions | 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 Variational Autoencoder-Assisted Accelerated Benders Decomposition for Resilient Stochastic Air Transport Network Reconfiguration under Airspace Disruptions Iman Rahimi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9673076/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 This study proposes a Variational Autoencoder (VAE)-assisted stochastic optimization framework for resilient air transport network reconfiguration under large-scale airspace disruptions. The proposed bi-objective model simultaneously minimizes total operational cost and expected unmet demand, enabling analysis of resilience–cost trade-offs under uncertain disruption conditions. To represent disruption uncertainty more realistically, a VAE is employed to generate synthetic disruption scenarios involving airport-capacity reductions, route closures, routing-cost escalation, and demand variation. The generated scenarios are clustered and integrated into a stochastic mixed-integer optimization framework. To solve the resulting large-scale stochastic problem efficiently, an accelerated multi-cut Benders decomposition algorithm incorporating scenario-specific cuts, trust-region stabilization, and cut-management mechanisms is developed. Computational experiments on benchmark-style air transport networks demonstrate that the proposed framework substantially outperforms classical single-cut and classical multi-cut Benders approaches in convergence speed, runtime, and iteration efficiency. The proposed method reduces the number of Benders iterations from more than 80 iterations to fewer than 10 in most tested cases, while reducing generated cuts by up to 90%. In high-penalty disruption scenarios, the classical multi-cut approach required nearly 29,000 seconds of runtime, whereas the proposed framework maintained consistently low computational time across all disruption levels. The results further reveal that reserve capacity becomes concentrated on strategically important hubs, particularly DXB and IST, under severe disruption conditions. Overall, the study highlights the value of integrating deep generative learning with accelerated stochastic decomposition for scalable and resilience-oriented air transport network planning under disruption. Artificial Intelligence and Machine Learning Operations Research Benders Decomposition VAE Deep Learning Stochastic Optimization Full Text Additional Declarations The authors declare no competing interests. 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-9673076","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":637794668,"identity":"d01f4833-17fc-4123-8b54-5ce5aa79a886","order_by":0,"name":"Iman Rahimi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8UlEQVRIiWNgGAWjYBACNiidwMbA2MCQUAHhSRCv5cEZiGq8WmAgAUQwPmwjQguf2OFnDxj32OUBGQ0MifMO18k3MB+8zcNgl9iAy2HSaeYGDM+Si9mkgWoStx2WMDjAlmzNw5CMR0uCmQTDAebENunE9h9gLQw8ZtI8DMx4tKR/A2qpB2kB2jLnsIR8A/83oJZ6PFpyQLYchmppOAzk8LABtRzGp6VMIuHAcYiWhGPpkhsOsxlbzjE4boxLi/zs9G0SHw5UJ86fnf6A8UeNNb98e/PDG28qqmVxaQGDBBQeM4gwwKd+FIyCUTAKRgEhAACtd03h9dUTqAAAAABJRU5ErkJggg==","orcid":"","institution":"University of Technology Sydney","correspondingAuthor":true,"prefix":"","firstName":"Iman","middleName":"","lastName":"Rahimi","suffix":""}],"badges":[],"createdAt":"2026-05-10 23:29:21","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9673076/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9673076/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109076341,"identity":"5f3b41c0-294e-472a-83ac-5420207b7e89","added_by":"auto","created_at":"2026-05-12 11:02:17","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1257526,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9673076/v1_covered_c42dede5-b702-4c6b-b491-be8ef6e399a3.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eVariational Autoencoder-Assisted Accelerated Benders Decomposition for Resilient Stochastic Air Transport Network Reconfiguration under Airspace Disruptions\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"University of Technology Sydney","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":"Benders Decomposition, VAE, Deep Learning, Stochastic Optimization","lastPublishedDoi":"10.21203/rs.3.rs-9673076/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9673076/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study proposes a Variational Autoencoder (VAE)-assisted stochastic optimization framework for resilient air transport network reconfiguration under large-scale airspace disruptions. The proposed bi-objective model simultaneously minimizes total operational cost and expected unmet demand, enabling analysis of resilience–cost trade-offs under uncertain disruption conditions. To represent disruption uncertainty more realistically, a VAE is employed to generate synthetic disruption scenarios involving airport-capacity reductions, route closures, routing-cost escalation, and demand variation. The generated scenarios are clustered and integrated into a stochastic mixed-integer optimization framework. To solve the resulting large-scale stochastic problem efficiently, an accelerated multi-cut Benders decomposition algorithm incorporating scenario-specific cuts, trust-region stabilization, and cut-management mechanisms is developed. Computational experiments on benchmark-style air transport networks demonstrate that the proposed framework substantially outperforms classical single-cut and classical multi-cut Benders approaches in convergence speed, runtime, and iteration efficiency. The proposed method reduces the number of Benders iterations from more than 80 iterations to fewer than 10 in most tested cases, while reducing generated cuts by up to 90%. In high-penalty disruption scenarios, the classical multi-cut approach required nearly 29,000 seconds of runtime, whereas the proposed framework maintained consistently low computational time across all disruption levels. The results further reveal that reserve capacity becomes concentrated on strategically important hubs, particularly DXB and IST, under severe disruption conditions. Overall, the study highlights the value of integrating deep generative learning with accelerated stochastic decomposition for scalable and resilience-oriented air transport network planning under disruption.\u003c/p\u003e","manuscriptTitle":"Variational Autoencoder-Assisted Accelerated Benders Decomposition for Resilient Stochastic Air Transport Network Reconfiguration under Airspace Disruptions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-12 10:36:39","doi":"10.21203/rs.3.rs-9673076/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":"0a819c10-3912-4436-9482-d5025e5d5b25","owner":[],"postedDate":"May 12th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":67879672,"name":"Artificial Intelligence and Machine Learning"},{"id":67879673,"name":"Operations Research"}],"tags":[],"updatedAt":"2026-05-12T10:36:39+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-12 10:36:39","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9673076","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9673076","identity":"rs-9673076","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}