Look Out Below: Predicting Wastewater Infrastructure Service Type at the Land Parcel Scale

Look Out Below: Predicting Wastewater Infrastructure Service Type at the Land Parcel Scale | 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 Look Out Below: Predicting Wastewater Infrastructure Service Type at the Land Parcel Scale Nelson da Luz, Jay Taneja, Emily Kumpel This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6656886/v2 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 30 Sep, 2025 Read the published version in ACS ES&T Engineering → Version 2 posted You are reading this latest preprint version Show more versions Abstract There has not been comprehensive national data collection of wastewater infrastructure serving the US population for 30 years, creating a data gap with implications for public health and asset management. We developed a model leveraging geospatial data and machine learning (Random Forest) to predict wastewater infrastructure in places where it is unknown. We employ a two-stage machine learning approach to model wastewater infrastructure coverage: Stage 1 identifies whether a parcel needs wastewater infrastructure and Stage 2 identifies whether it is served by an onsite wastewater treatment system or by a centralized sewer connection. We test this approach using data from Florida, including evaluating the approach’s applicability within Florida and an out-of-sample test in Virginia. The model achieved 91.8% accuracy across Florida with a 96.4% median Stage 2 confidence, suggesting potential use of confidence as a proxy for accuracy where ground-truth data is limited. The model achieved 81.9% accuracy in Virginia when predicting with a model trained only on data from Florida, suggesting strong transferability to new geographies. Variations in performance highlight opportunities for improvement in resolving sewer service boundary underestimation and testing to account for a range of local and historical circumstances. Our approach represents a scalable and transferable framework. Environmental Engineering wastewater infrastructure sanitation machine learning sewer septic Full Text Additional Declarations The authors declare no competing interests. Supplementary Files SepticPaperSIESTEng02.pdf Supplemental Information Cite Share Download PDF Status: Published Journal Publication published 30 Sep, 2025 Read the published version in ACS ES&T Engineering → Version 2 posted You are reading this latest preprint version Show more versions 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-6656886","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":456344646,"identity":"69b2cad5-bc9a-46fb-9753-f5d0c9761668","order_by":0,"name":"Nelson da Luz","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuElEQVRIiWNgGAWjYFCCBMYDDAw2MB4zUVoYgFrSSNdymAQt5uzJDw7z/DmfuLb9+OMPDBXWiQ2EtFj2PDM4zMNzO3HbmRwzCYYz6YS1GNxIAGqRAGo5kMPGwNh2mBgt6R8O8xicS9x2/vnjD4z/iNKSA7Ql4UDiNqB1EowNxGg586bg4JwDycbbbrwxk0g4lm5MWMvx9I0P3vyxk912Pv3xhw811rIEtaCCBNKUj4JRMApGwSjABQBrNUgkJ49WAQAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0001-6657-7273","institution":"University of Massachusetts Amherst","correspondingAuthor":true,"prefix":"","firstName":"Nelson","middleName":"da","lastName":"Luz","suffix":""},{"id":456344647,"identity":"a5d080be-05ac-4e8b-91c3-caca83bf0805","order_by":1,"name":"Jay Taneja","email":"","orcid":"https://orcid.org/0000-0001-7590-2509","institution":"University of Massachusetts Amherst","correspondingAuthor":false,"prefix":"","firstName":"Jay","middleName":"","lastName":"Taneja","suffix":""},{"id":456344648,"identity":"a66eb5b4-bf6f-4717-818a-6644b830d5f5","order_by":2,"name":"Emily Kumpel","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxUlEQVRIiWNgGAWjYDACHjBpIQfjMzYQqUXCmHQtiTCVhLXw85wx3VxQIZG+4drhxx9/MNjIbjhAQItkb4/Z7RlnJHI33E4zk+ZhSDMmqMXgPI/Zbd42kJYEM2YGhsOJBLXYg7X8k0g3uJ3+Geiw/4S1GPACHcbbIJFgcDvHQIKH4QBhLRJnjpXdnnFMwnDm7ZwyaR6DZOOZhLTw9yRvu11QYyPPdzt988cfFXayfYS0gAAzkjuJUI6mZRSMglEwCkYBFgAAol5DKofBBCsAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0003-0138-8441","institution":"University of Massachusetts Amherst","correspondingAuthor":true,"prefix":"","firstName":"Emily","middleName":"","lastName":"Kumpel","suffix":""}],"badges":[],"createdAt":"2025-05-13 15:12:18","currentVersionCode":2,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6656886/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-6656886/v2","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1021/acsestengg.5c00637","type":"published","date":"2025-10-01T00:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":92948032,"identity":"8054e956-1006-4cd7-896c-3b600cd5f4a0","added_by":"auto","created_at":"2025-10-07 12:54:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":757000,"visible":true,"origin":"","legend":"","description":"","filename":"SepticPaperESTEng01.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6656886/v2_covered_69b064cc-0f8e-4d45-8993-b13c776ace6c.pdf"},{"id":87438706,"identity":"785eff71-bf33-4525-8d9b-44076105c4e2","added_by":"auto","created_at":"2025-07-23 19:18:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1664073,"visible":true,"origin":"","legend":"\u003cp\u003eSupplemental Information\u003c/p\u003e","description":"","filename":"SepticPaperSIESTEng02.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6656886/v2/ee2e013529cfdb3671a77ee9.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"Look Out Below: Predicting Wastewater Infrastructure Service Type at the Land Parcel Scale","fulltext":[],"fulltextSource":"","fullText":"","funders":[{"identity":"3c311b59-7aaa-4185-8ab7-e442486df9eb","identifier":"10.13039/100004814","name":"California State Water Resources Control Board","awardNumber":"NA","order_by":0}],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"University of Massachusetts Amherst","isAcceptedByJournal":true,"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":"wastewater, infrastructure, sanitation, machine learning, sewer, septic","lastPublishedDoi":"10.21203/rs.3.rs-6656886/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6656886/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThere has not been comprehensive national data collection of wastewater infrastructure serving the US population for 30 years, creating a data gap with implications for public health and asset management. We developed a model leveraging geospatial data and machine learning (Random Forest) to predict wastewater infrastructure in places where it is unknown. We employ a two-stage machine learning approach to model wastewater infrastructure coverage: Stage 1 identifies whether a parcel needs wastewater infrastructure and Stage 2 identifies whether it is served by an onsite wastewater treatment system or by a centralized sewer connection. We test this approach using data from Florida, including evaluating the approach\u0026rsquo;s applicability within Florida and an out-of-sample test in Virginia. The model achieved 91.8% accuracy across Florida with a 96.4% median Stage 2 confidence, suggesting potential use of confidence as a proxy for accuracy where ground-truth data is limited. The model achieved 81.9% accuracy in Virginia when predicting with a model trained only on data from Florida, suggesting strong transferability to new geographies. Variations in performance highlight opportunities for improvement in resolving sewer service boundary underestimation and testing to account for a range of local and historical circumstances. Our approach represents a scalable and transferable framework.\u003c/p\u003e","manuscriptTitle":"Look Out Below: Predicting Wastewater Infrastructure Service Type at the Land Parcel Scale","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2025-07-23 19:10:48","doi":"10.21203/rs.3.rs-6656886/v2","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}},{"code":1,"date":"2025-05-14 06:55:34","doi":"10.21203/rs.3.rs-6656886/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":"13abe28b-72f2-4764-b869-1425c9fed1fe","owner":[],"postedDate":"July 23rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":48504617,"name":"Environmental Engineering"}],"tags":[],"updatedAt":"2025-10-07T12:37:10+00:00","versionOfRecord":{"articleIdentity":"rs-6656886","link":"https://doi.org/10.1021/acsestengg.5c00637","journal":{"identity":"acs-esandt-engineering","isVorOnly":true,"title":"ACS ES\u0026T Engineering"},"publishedOn":"2025-10-01 00:00:00","publishedOnDateReadable":"October 1st, 2025"},"versionCreatedAt":"2025-07-23 19:10:48","video":"","vorDoi":"10.1021/acsestengg.5c00637","vorDoiUrl":"https://doi.org/10.1021/acsestengg.5c00637","workflowStages":[]},"version":"v2","identity":"rs-6656886","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6656886","identity":"rs-6656886","version":["v2"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}