Self-Supervised Graph Attention Networks for Community-Engaged Lead Contamination Risk Assessment

Self-Supervised Graph Attention Networks for Community-Engaged Lead Contamination Risk Assessment | 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 Article Self-Supervised Graph Attention Networks for Community-Engaged Lead Contamination Risk Assessment Raphael Anaadumba, Nazim A. Belabbaci, Yigit Bozkurt, Connor Sullivan, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7529963/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 14 You are reading this latest preprint version Abstract Lead contamination in residential water supplies constitutes a nationwide public‑health emergency, burdening communities with chronic neurological, cardiovascular, and infrastructural costs. Current Environmental Protection Agency (EPA) Lead and Copper Rule protocols, which hinge on homeowner sampling and laboratory analyses, are prohibitively expensive, slow, and too sparsely deployed to flag emerging contamination clusters in time for preventive action. To bridge this gap, we propose a scalable graph machine learning-aided high‑resolution lead risk assessment framework using publicly available housing datasets (parcel, infrastructure) and historical lead testing data archives. The heart of the approach is a Self‑Supervised Graph Attention Network (SSGAT) that employs graph attention layers to model spatial dependencies between properties, coupled with self-supervised pretraining to enhance generalizability. An adaptive human‑in‑the‑loop module refines these attention weights through rapid expert review, ensuring locality‑specific nuances are captured without retraining from scratch. We pre‑trained the model on the publicly available Flint, Michigan dataset and fine‑tuned it using IRB‑approved parcel‑linked samples and stakeholder feedback collected in Andover, Massachusetts. The resulting system attains 90% classification accuracy and an AUC of 83.6%, surpassing state-of-the-art models by as much as 12% while cutting per‑parcel screening costs by a factor of five. By uniting self‑supervised graph learning, transferability, and participatory validation, this work elevates computational methodology and environmental‑engineering practice toward scalable, proactive surveillance of spatially correlated drinking‑water hazards. Physical sciences/Engineering Earth and environmental sciences/Environmental sciences Physical sciences/Mathematics and computing Lead contamination Graph neural networks Self-supervised learning Public health risk assessment Geospatial modeling Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 07 Jan, 2026 Reviews received at journal 05 Jan, 2026 Reviews received at journal 30 Dec, 2025 Reviews received at journal 29 Dec, 2025 Reviews received at journal 13 Dec, 2025 Reviewers agreed at journal 13 Dec, 2025 Reviewers agreed at journal 09 Dec, 2025 Reviewers agreed at journal 09 Dec, 2025 Reviewers agreed at journal 09 Dec, 2025 Reviewers invited by journal 09 Dec, 2025 Editor assigned by journal 09 Dec, 2025 Editor invited by journal 16 Sep, 2025 Submission checks completed at journal 12 Sep, 2025 First submitted to journal 12 Sep, 2025 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-7529963","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":557874362,"identity":"8eb6e820-f24c-4673-8f44-2a5b3f1dbe56","order_by":0,"name":"Raphael Anaadumba","email":"","orcid":"","institution":"University of Massachusetts Lowell","correspondingAuthor":false,"prefix":"","firstName":"Raphael","middleName":"","lastName":"Anaadumba","suffix":""},{"id":557874363,"identity":"a37bd402-6199-4c07-9d62-2a4b12ddcbc3","order_by":1,"name":"Nazim A. Belabbaci","email":"","orcid":"","institution":"University of Massachusetts Lowell","correspondingAuthor":false,"prefix":"","firstName":"Nazim","middleName":"A.","lastName":"Belabbaci","suffix":""},{"id":557874364,"identity":"d3ade53a-066e-4352-aa52-00f8f6610d34","order_by":2,"name":"Yigit Bozkurt","email":"","orcid":"","institution":"University of Massachusetts Lowell","correspondingAuthor":false,"prefix":"","firstName":"Yigit","middleName":"","lastName":"Bozkurt","suffix":""},{"id":557874365,"identity":"5f653ef1-cdf7-4a88-ab57-061bb5044055","order_by":3,"name":"Connor Sullivan","email":"","orcid":"","institution":"University of Massachusetts Lowell","correspondingAuthor":false,"prefix":"","firstName":"Connor","middleName":"","lastName":"Sullivan","suffix":""},{"id":557874366,"identity":"0111db0a-18b2-44bd-9590-8faa457562fa","order_by":4,"name":"Pradeep Kurup","email":"","orcid":"","institution":"University of Massachusetts Lowell","correspondingAuthor":false,"prefix":"","firstName":"Pradeep","middleName":"","lastName":"Kurup","suffix":""},{"id":557874367,"identity":"63290e10-b613-477d-b444-87321d1a5a73","order_by":5,"name":"Mohammad Arif Ul Alam","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABHUlEQVRIie3QsUrDQBzH8f9RaJarWa9I+wwHB0FR7Kt4BJxyUHAROjRBSJdKV0V8hxPhVpUOGTw6V7IoBScDRUcHvYTUQS7i6HDfJcmRD78QAJfrH0bvcHVFKaD4HQ8Bb5mHJ4Adc3hoJbsbMgOUXGIK/TZAiwKQRjLYkIsYUEmYIW3yGwmys/u3x+igJ/N5cmoIT72Ho1EnIuB7EbUSvQi3hQqZXPCaYKHyjiLQnb7ayTKihrS41GiyqgjUhC7tK+acfQg15rcaVSvj1C/UcUkGzSQwK/Nypf4wYkarFdJAtA72hMpYSZLzihQ33StFMNEvQyvJpiwXatST2nuO1yfAZ764Xhdqv+9PQmn9yz/6/L7Df3nd5XK5XPa+ADw1Z5CHYUeDAAAAAElFTkSuQmCC","orcid":"","institution":"University of Massachusetts Lowell","correspondingAuthor":true,"prefix":"","firstName":"Mohammad","middleName":"Arif Ul","lastName":"Alam","suffix":""}],"badges":[],"createdAt":"2025-09-03 19:53:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7529963/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7529963/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97982029,"identity":"5659e000-b79f-4837-9ef5-b9af0a824597","added_by":"auto","created_at":"2025-12-11 12:57:51","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8980,"visible":true,"origin":"","legend":"","description":"","filename":"d02e36704e1742a99d0009779cf84bf2.json","url":"https://assets-eu.researchsquare.com/files/rs-7529963/v1/85afd2698ec55e1f5da420a9.json"},{"id":98425067,"identity":"592d31ea-8294-4a9c-9532-c0149f053526","added_by":"auto","created_at":"2025-12-17 16:34:15","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1389611,"visible":true,"origin":"","legend":"","description":"","filename":"SelfSupervisedGraphAttentionNetworksforCommunityEngagedLeadContaminationRiskAssessment.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7529963/v1_covered_d50e44ec-451e-4ad1-bdcd-3f25e993822c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Self-Supervised Graph Attention Networks for Community-Engaged Lead Contamination Risk Assessment","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Lead contamination, Graph neural networks, Self-supervised learning, Public health risk assessment, Geospatial modeling","lastPublishedDoi":"10.21203/rs.3.rs-7529963/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7529963/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Lead contamination in residential water supplies constitutes a nationwide public‑health emergency, burdening communities with chronic neurological, cardiovascular, and infrastructural costs. Current Environmental Protection Agency (EPA) Lead and Copper Rule protocols, which hinge on homeowner sampling and laboratory analyses, are prohibitively expensive, slow, and too sparsely deployed to flag emerging contamination clusters in time for preventive action. To bridge this gap, we propose a scalable graph machine learning-aided high‑resolution lead risk assessment framework using publicly available housing datasets (parcel, infrastructure) and historical lead testing data archives. The heart of the approach is a Self‑Supervised Graph Attention Network (SSGAT) that employs graph attention layers to model spatial dependencies between properties, coupled with self-supervised pretraining to enhance generalizability. An adaptive human‑in‑the‑loop module refines these attention weights through rapid expert review, ensuring locality‑specific nuances are captured without retraining from scratch. We pre‑trained the model on the publicly available Flint, Michigan dataset and fine‑tuned it using IRB‑approved parcel‑linked samples and stakeholder feedback collected in Andover, Massachusetts. The resulting system attains 90\\% classification accuracy and an AUC of 83.6\\%, surpassing state-of-the-art models by as much as 12\\% while cutting per‑parcel screening costs by a factor of five. By uniting self‑supervised graph learning, transferability, and participatory validation, this work elevates computational methodology and environmental‑engineering practice toward scalable, proactive surveillance of spatially correlated drinking‑water hazards.","manuscriptTitle":"Self-Supervised Graph Attention Networks for Community-Engaged Lead Contamination Risk Assessment","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-11 12:57:46","doi":"10.21203/rs.3.rs-7529963/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-01-07T05:33:50+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-06T03:53:24+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-30T23:56:30+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-29T12:06:02+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-13T13:05:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"93923512662612776778004870274538464254","date":"2025-12-13T12:42:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"270860535618871383144299582567972320769","date":"2025-12-09T22:15:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"120540952241539129301798426429555622636","date":"2025-12-09T07:45:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"138829159625288544440549906577842855907","date":"2025-12-09T05:48:34+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-09T05:44:06+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-09T05:42:00+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-09-16T09:04:52+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-12T23:43:03+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-09-12T23:41:37+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"9e0edfaa-7e4f-4d7b-ab96-6d0ae0a37699","owner":[],"postedDate":"December 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":59379812,"name":"Physical sciences/Engineering"},{"id":59379813,"name":"Earth and environmental sciences/Environmental sciences"},{"id":59379814,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-08T11:38:09+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-11 12:57:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7529963","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7529963","identity":"rs-7529963","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}