Overcoming Data Scarcity in Transit Planning: A Novel Framework Combining Machine Learning and Metaheuristics

Overcoming Data Scarcity in Transit Planning: A Novel Framework Combining Machine Learning and Metaheuristics | 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 Overcoming Data Scarcity in Transit Planning: A Novel Framework Combining Machine Learning and Metaheuristics Shagun Mittal, Satish Ukkusuri This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4954028/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 10 Feb, 2025 Read the published version in Data Science for Transportation → Version 1 posted 9 You are reading this latest preprint version Abstract Public transit systems in developing regions often face challenges due to rapid urbanization, limited resources, and a lack of comprehensive transit data, hindering effective strategic planning. This study proposes a framework for leveraging emerging data sources to guide transit network planning in data-limited environments. Using Greater-Maputo, Mozambique as a case study, we demonstrate how mobile phone location data, OpenStreetMap, and land use information can be utilized to extract key transit network components, including transit-viable road segments, high-demand stop locations, and efficient routes. We employ a modified semi-supervised self-training algorithm for transit viability prediction, density-based clustering for stop location extraction, and multi-objective metaheuristics for route extraction. The results show strong alignment with the operational GTFS data, capturing spatial patterns of transit suitability, identifying critical transit locations, redundancies, and underserved areas, and generating more direct and demand-aligned routes. The compiled extracted results in the form of GTFS data show a 17% potential improvement in accessibility compared to the operational GTFS data. The proposed approach offers a potent and transferable methodology for data-driven transit planning, supporting the development of efficient, equitable, and sustainable transit systems in various contexts. This research contributes to the growing body of knowledge on evidence-based transit planning in data-scarce environments and lays the foundation for future research and policy interventions aimed at optimizing transit networks, enhancing accessibility, and promoting sustainable urban development in developing regions. Strategic transit planning Data-driven methodology Emerging data sources Developing regions Sustainable urban development Full Text Additional Declarations Competing interest reported. Prof. Satish Ukkusuri, the corresponding author of this paper, serves as a co-Editor in Chief of the Data Science for Transportation journal. Cite Share Download PDF Status: Published Journal Publication published 10 Feb, 2025 Read the published version in Data Science for Transportation → Version 1 posted Editorial decision: Revision requested 21 Nov, 2024 Reviews received at journal 15 Nov, 2024 Reviews received at journal 08 Oct, 2024 Reviewers agreed at journal 26 Aug, 2024 Reviewers agreed at journal 26 Aug, 2024 Reviewers invited by journal 26 Aug, 2024 Editor assigned by journal 22 Aug, 2024 Submission checks completed at journal 22 Aug, 2024 First submitted to journal 21 Aug, 2024 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-4954028","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":355391023,"identity":"76c85000-18a4-48a8-9a94-b4b6ad03802c","order_by":0,"name":"Shagun Mittal","email":"","orcid":"","institution":"Purdue University West Lafayette","correspondingAuthor":false,"prefix":"","firstName":"Shagun","middleName":"","lastName":"Mittal","suffix":""},{"id":355391024,"identity":"91290573-22ef-450e-939a-03230a0b823c","order_by":1,"name":"Satish Ukkusuri","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0ElEQVRIiWNgGAWjYFACNmYwxQ8ieMDMBCK1SDaQrMXgALFa5GekJRvz/Dmcb3y7x+zD2zYbBn72HAO8WgxupB1O5m07bLntzhnjmXPb0hgke94Q0CKR3nyYt+GwgdmNHGNmoF6gIQRskZ8B1AJ0mIHxDLCW/wz2hLQwgBzGw3bYwEACrOUA0F5CfjnzLNlwblu6gcSdY8WMc84l80iceVaA32HtacYSb/5YG/DPbt7M8KbMTo6/PXkDfofBgQSE4iFSOZKWUTAKRsEoGAUYAABIm0H1/HhjJAAAAABJRU5ErkJggg==","orcid":"","institution":"Purdue University West Lafayette","correspondingAuthor":true,"prefix":"","firstName":"Satish","middleName":"","lastName":"Ukkusuri","suffix":""}],"badges":[],"createdAt":"2024-08-21 22:21:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4954028/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4954028/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s42421-025-00116-6","type":"published","date":"2025-02-10T15:56:50+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":76487401,"identity":"7fb81f25-163e-46f2-b7e6-41325c1d58ca","added_by":"auto","created_at":"2025-02-17 16:01:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":9853786,"visible":true,"origin":"","legend":"","description":"","filename":"paper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4954028/v1_covered_1f48c70f-f705-4b73-8d42-fa33b5064c50.pdf"}],"financialInterests":"Competing interest reported. Prof. Satish Ukkusuri, the corresponding author of this paper, serves as a co-Editor in Chief of the Data Science for Transportation journal.","formattedTitle":"Overcoming Data Scarcity in Transit Planning: A Novel Framework Combining Machine Learning and Metaheuristics","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"data-science-for-transportation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Data Science for Transportation](https://www.springer.com/journal/42421)","snPcode":"42421","submissionUrl":"https://submission.nature.com/new-submission/42421/3","title":"Data Science for Transportation","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"snapp","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Strategic transit planning, Data-driven methodology, Emerging data sources, Developing regions, Sustainable urban development","lastPublishedDoi":"10.21203/rs.3.rs-4954028/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4954028/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Public transit systems in developing regions often face challenges due to rapid urbanization, limited resources, and a lack of comprehensive transit data, hindering effective strategic planning. This study proposes a framework for leveraging emerging data sources to guide transit network planning in data-limited environments. Using Greater-Maputo, Mozambique as a case study, we demonstrate how mobile phone location data, OpenStreetMap, and land use information can be utilized to extract key transit network components, including transit-viable road segments, high-demand stop locations, and efficient routes. We employ a modified semi-supervised self-training algorithm for transit viability prediction, density-based clustering for stop location extraction, and multi-objective metaheuristics for route extraction. The results show strong alignment with the operational GTFS data, capturing spatial patterns of transit suitability, identifying critical transit locations, redundancies, and underserved areas, and generating more direct and demand-aligned routes. The compiled extracted results in the form of GTFS data show a 17\\% potential improvement in accessibility compared to the operational GTFS data. The proposed approach offers a potent and transferable methodology for data-driven transit planning, supporting the development of efficient, equitable, and sustainable transit systems in various contexts. This research contributes to the growing body of knowledge on evidence-based transit planning in data-scarce environments and lays the foundation for future research and policy interventions aimed at optimizing transit networks, enhancing accessibility, and promoting sustainable urban development in developing regions.","manuscriptTitle":"Overcoming Data Scarcity in Transit Planning: A Novel Framework Combining Machine Learning and Metaheuristics","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-20 04:26:59","doi":"10.21203/rs.3.rs-4954028/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-11-21T12:54:44+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-15T07:57:25+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-10-08T11:27:48+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"299853329614608612418933699764142804648","date":"2024-08-26T08:50:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"326543206729952906546928689464781783434","date":"2024-08-26T07:21:06+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-08-26T07:15:32+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-08-22T08:08:22+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-08-22T08:07:24+00:00","index":"","fulltext":""},{"type":"submitted","content":"Data Science for Transportation","date":"2024-08-21T22:18:05+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"data-science-for-transportation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Data Science for Transportation](https://www.springer.com/journal/42421)","snPcode":"42421","submissionUrl":"https://submission.nature.com/new-submission/42421/3","title":"Data Science for Transportation","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"snapp","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"b30f2734-71ee-4242-a202-02e6385cd606","owner":[],"postedDate":"September 20th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-02-17T15:58:23+00:00","versionOfRecord":{"articleIdentity":"rs-4954028","link":"https://doi.org/10.1007/s42421-025-00116-6","journal":{"identity":"data-science-for-transportation","isVorOnly":false,"title":"Data Science for Transportation"},"publishedOn":"2025-02-10 15:56:50","publishedOnDateReadable":"February 10th, 2025"},"versionCreatedAt":"2024-09-20 04:26:59","video":"","vorDoi":"10.1007/s42421-025-00116-6","vorDoiUrl":"https://doi.org/10.1007/s42421-025-00116-6","workflowStages":[]},"version":"v1","identity":"rs-4954028","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4954028","identity":"rs-4954028","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}