Event Aware Flood Mapping for Agricultural Landscapes: A Robustness Oriented Comparison of Deep Learning and Machine Learning in the Arkansas 2025 Flood Event

Event Aware Flood Mapping for Agricultural Landscapes: A Robustness Oriented Comparison of Deep Learning and Machine Learning in the Arkansas 2025 Flood Event | 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 Event Aware Flood Mapping for Agricultural Landscapes: A Robustness Oriented Comparison of Deep Learning and Machine Learning in the Arkansas 2025 Flood Event Manh-Dung Vu, Gia-Hien Tran, Ming-Che Hu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9384304/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 Accurate flood mapping is essential for rapid impact assessment in agricultural landscapes, where inundation can interrupt production, damage rural infrastructure, and complicate recovery. Recent research has shown that deep learning can support flood delineation from remotely sensed data, but the literature still reports recurring weaknesses in robustness assessment, uncertainty interpretation, and transparent benchmarking against simpler machine learning baselines. In this study, we developed an event aware flood mapping framework for the Arkansas 2025 flood event by integrating terrain, antecedent water conditions, rainfall dynamics, and hydrologic proximity within a spatial learning workflow. We evaluated progressively richer predictor configurations using a U Net based convolutional neural network and assessed robustness through repeated seed experiments under fixed train, validation, and test splits. A Random Forest benchmark was introduced to provide a transparent classical machine learning reference. Mean probability, uncertainty, and agreement maps were also generated to characterize spatial confidence patterns. The results showed that adding rainfall substantially improved performance relative to the more complex advanced deep learning configuration, increasing mean best validation IoU by 7.3%, mean test IoU by 15.8%, and mean test F1 by 12.4%, while also reducing the variability of test IoU, test F1, and threshold selection. The rainfall based U Net achieved a best validation IoU of 0.278 ± 0.015, a test IoU of 0.264 ± 0.014, and a test F1 of 0.417 ± 0.018. The more complex configuration that added distance to river and Focal Tversky optimization did not deliver a consistent gain, with a best validation IoU of 0.259 ± 0.011, a test IoU of 0.228 ± 0.033, and a test F1 of 0.371 ± 0.044. The Random Forest benchmark was unexpectedly strong, reaching a validation IoU of 0.608 at the selected threshold and a test IoU of 0.351 with a test F1 of 0.519, equivalent to gains of 33.0% in test IoU and 24.5% in test F1 relative to the best deep learning configuration. Feature importance analysis identified elevation, slope, rainfall peak, and event total rainfall as dominant contributors. Spatial uncertainty was concentrated along transitional flood margins, while agreement maps highlighted coherent high confidence cores. Cropland overlay analysis further demonstrated that the framework can support first pass agricultural exposure assessment. Rather than promoting model complexity for its own sake, this study shows that event aware predictors, robustness oriented evaluation, and explicit benchmark comparison are central to credible geospatial flood intelligence in agricultural environments. Environmental Engineering Hydrology Agricultural Economics & Policy flood mapping agricultural exposure event aware predictors U Net Random Forest uncertainty analysis Arkansas floodplain 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-9384304","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":621290683,"identity":"01c34b41-080d-44ab-bbdd-13c1395bc8d2","order_by":0,"name":"Manh-Dung Vu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5ElEQVRIie3PvwqCQBzA8ZPgXH7k+juUnuEgsIbAVxECpwuawrHJhmqvt3BqbsrlGgPFpRZbXIIGh6DUB7Abg+4L92e4D3dHiE73k/n1CCl4ybLe8LEqkX2HyGNDUJEY0WBC0sYSBcIT4d6e0gVjf7/E1RyJtVr73USWo6ETBtCzxSLb1A9DeY47CdsJ10Z5AmqLIIWacJwpEBa9AZgMspcKsVC47BFRQDRPudItFhQLm0gKHATNHY7w9S/UnB5YFVKPm0mRla/JwFptu0lTD9oFeDt/Pd5kVO1iXpVO63Q63f/1AVfXQtlaSchRAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0001-6585-2007","institution":"National Taiwan University","correspondingAuthor":true,"prefix":"","firstName":"Manh-Dung","middleName":"","lastName":"Vu","suffix":""},{"id":621290684,"identity":"f091b97c-6a98-4440-a229-8dcf251d49ee","order_by":1,"name":"Gia-Hien Tran","email":"","orcid":"https://orcid.org/0009-0008-8764-5632","institution":"Hanoi – Amsterdam Highschool for the Gifted","correspondingAuthor":false,"prefix":"","firstName":"Gia-Hien","middleName":"","lastName":"Tran","suffix":""},{"id":621290685,"identity":"c8154637-ab0b-4ce3-a9fe-6a41fb6a2161","order_by":2,"name":"Ming-Che Hu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAo0lEQVRIiWNgGAWjYFACHgaGDxCWAfFaGGdAVAOJBCK1MPOQpEW3/ewxadsdfxIb2Ju3STD+OExYi9mZvDTp3DMGiQ08x8okGBKI0XKDx0w6tw2oRSLHDKjlNpFaLEFa5N+QooURbAsPsVrO5Bhb9rYZG7fxpBVbJKT9J0LL8TOGN362ycn2sx/eeOODTRphLXDABiISSNAwCkbBKBgFowAPAAAxmTKP5zARWgAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-5288-2936","institution":"National Taiwan University","correspondingAuthor":true,"prefix":"","firstName":"Ming-Che","middleName":"","lastName":"Hu","suffix":""}],"badges":[],"createdAt":"2026-04-11 04:07:29","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-9384304/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9384304/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106961000,"identity":"e252d8b2-6d6e-4515-a69b-35a5e0d4c1a6","added_by":"auto","created_at":"2026-04-15 09:23:56","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1172082,"visible":true,"origin":"","legend":"","description":"","filename":"arkansasfloodmanuscriptMDVuGHTranMCHu.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9384304/v1_covered_e44df0bd-0a7d-4b18-9249-6bcb4b741845.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eEvent Aware Flood Mapping for Agricultural Landscapes: A Robustness Oriented Comparison of Deep Learning and Machine Learning in the Arkansas 2025 Flood Event\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"National Taiwan University","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":"flood mapping, agricultural exposure, event aware predictors, U Net, Random Forest, uncertainty analysis, Arkansas floodplain ","lastPublishedDoi":"10.21203/rs.3.rs-9384304/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9384304/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate flood mapping is essential for rapid impact assessment in agricultural landscapes, where \u0026nbsp;inundation can interrupt production, damage rural infrastructure, and complicate recovery. Recent research \u0026nbsp;has shown that deep learning can support flood delineation from remotely sensed data, but the literature \u0026nbsp;still reports recurring weaknesses in robustness assessment, uncertainty interpretation, and transparent \u0026nbsp;benchmarking against simpler machine learning baselines. In this study, we developed an event aware \u0026nbsp;flood mapping framework for the Arkansas 2025 flood event by integrating terrain, antecedent water \u0026nbsp;conditions, rainfall dynamics, and hydrologic proximity within a spatial learning workflow. We evaluated \u0026nbsp;progressively richer predictor configurations using a U Net based convolutional neural network and \u0026nbsp;assessed robustness through repeated seed experiments under fixed train, validation, and test splits. A \u0026nbsp;Random Forest benchmark was introduced to provide a transparent classical machine learning reference. \u0026nbsp;Mean probability, uncertainty, and agreement maps were also generated to characterize spatial confidence \u0026nbsp;patterns. The results showed that adding rainfall substantially improved performance relative to the more \u0026nbsp;complex advanced deep learning configuration, increasing mean best validation IoU by 7.3%, mean test \u0026nbsp;IoU by 15.8%, and mean test F1 by 12.4%, while also reducing the variability of test IoU, test F1, and \u0026nbsp;threshold selection. The rainfall based U Net achieved a best validation IoU of 0.278 ± 0.015, a test IoU of \u0026nbsp;0.264 ± 0.014, and a test F1 of 0.417 ± 0.018. The more complex configuration that added distance to river \u0026nbsp;and Focal Tversky optimization did not deliver a consistent gain, with a best validation IoU of 0.259 ± \u0026nbsp;0.011, a test IoU of 0.228 ± 0.033, and a test F1 of 0.371 ± 0.044. The Random Forest benchmark was \u0026nbsp;unexpectedly strong, reaching a validation IoU of 0.608 at the selected threshold and a test IoU of 0.351 \u0026nbsp;with a test F1 of 0.519, equivalent to gains of 33.0% in test IoU and 24.5% in test F1 relative to the best \u0026nbsp;deep learning configuration. Feature importance analysis identified elevation, slope, rainfall peak, and \u0026nbsp;event total rainfall as dominant contributors. Spatial uncertainty was concentrated along transitional flood \u0026nbsp;margins, while agreement maps highlighted coherent high confidence cores. Cropland overlay analysis \u0026nbsp;further demonstrated that the framework can support first pass agricultural exposure assessment. Rather \u0026nbsp;than promoting model complexity for its own sake, this study shows that event aware predictors, robustness \u0026nbsp;oriented evaluation, and explicit benchmark comparison are central to credible geospatial flood intelligence \u0026nbsp;in agricultural environments.\u003c/p\u003e","manuscriptTitle":"Event Aware Flood Mapping for Agricultural Landscapes: A Robustness Oriented Comparison of Deep Learning and Machine Learning in the Arkansas 2025 Flood Event","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-14 05:25:10","doi":"10.21203/rs.3.rs-9384304/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":"f8991512-77dc-4fe3-872a-1ddec25ba5e0","owner":[],"postedDate":"April 14th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":66122377,"name":"Environmental Engineering"},{"id":66122378,"name":"Hydrology"},{"id":66122379,"name":"Agricultural Economics \u0026 Policy"}],"tags":[],"updatedAt":"2026-04-14T05:25:10+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-14 05:25:10","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9384304","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9384304","identity":"rs-9384304","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}