Daily water demand forecasting: Comparing AI models with SHAP-optimized features

Daily water demand forecasting: Comparing AI models with SHAP-optimized features | 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 Daily water demand forecasting: Comparing AI models with SHAP-optimized features Rui Li, Kunlun Xin, Weihao Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7075354/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 water demand prediction is critical for infrastructure stability and resource optimization, yet short-term forecasting remains challenging due to high volatility from meteorological, seasonal, and socio-temporal factors (e.g., holidays). To address this, we collected 402 days of urban water demand records augmented with web-scraped meteorological and temporal features. Through SHapley Additive exPlanations (SHAP) analysis, we identified and retained high-impact features (e.g., maximum temperature, day-of-week) while eliminating redundant variables (e.g., minimum temperature, cloudy conditions), achieving a 22% reduction in feature dimensionality with a 0.16 percentage point improvement in MAPE across all AI models. We systematically compared 7 machine learning models and 3 deep learning models against an ARIMA baseline model using four performance metrics. The results indicate that deep learning methods have significant advantages in prediction accuracy, while machine learning models have certain shortcomings in predicting time series. The organic combination of interpretable feature selection in machine learning and precise prediction in deep learning provides actionable insights for utilities. Water demand forecasting Feature engineering SHAP Artificial intelligence model Performance metrics Full Text Supplementary Files SupplementaryMaterial.docx 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-7075354","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":492602084,"identity":"7d675927-432c-4306-8738-f4ade970f8ca","order_by":0,"name":"Rui Li","email":"","orcid":"","institution":"Tongji University","correspondingAuthor":false,"prefix":"","firstName":"Rui","middleName":"","lastName":"Li","suffix":""},{"id":492602085,"identity":"402f6807-99cc-4834-9f3b-bca792f3ac32","order_by":1,"name":"Kunlun Xin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyklEQVRIiWNgGAWjYDACHubGByCasRnEIU4LY7PBAVK1tEkcgHOI0WFw5mBb9YeKO3bN7QyMD962McibE9Ii2dvYduPAmWfJjc0MzIZz2xgMdzYQ0MLPz9h242Db4WSgX9ikedsYEgwOENDCBtRSANXC/psoLfy8jW0MQC12IFuYidIi2XOwWeLMmcMJjM2MzZJzzkkYbiCkxeBM8sEPFRWH7Q37Dx/88KbMRp6gLTCQuLGBsQFISxCpHgjs5YlXOwpGwSgYBSMNAACemEE2bQpjHQAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0001-5476-9374","institution":"Tongji University College of Environmental Science and Engineering","correspondingAuthor":true,"prefix":"","firstName":"Kunlun","middleName":"","lastName":"Xin","suffix":""},{"id":492602086,"identity":"a4e06caa-cdba-4b6d-8a29-614c9c445f17","order_by":2,"name":"Weihao Chen","email":"","orcid":"","institution":"Tongji University","correspondingAuthor":false,"prefix":"","firstName":"Weihao","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2025-07-08 13:28:50","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7075354/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7075354/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":88401894,"identity":"07ab7f7b-143d-463b-8e24-ab2910cd740c","added_by":"auto","created_at":"2025-08-06 07:07:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":911075,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7075354/v1_covered_4bc08ad1-5312-4032-8ede-3a1114db5e57.pdf"},{"id":88136125,"identity":"55318579-574e-491d-96ce-904a8c501996","added_by":"auto","created_at":"2025-08-01 21:55:50","extension":"docx","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":113386,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryMaterial.docx","url":"https://assets-eu.researchsquare.com/files/rs-7075354/v1/073ff00a1a8c104bd3182d8a.docx"}],"financialInterests":"","formattedTitle":"Daily water demand forecasting: Comparing AI models with SHAP-optimized features","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","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":"Water demand forecasting, Feature engineering, SHAP, Artificial intelligence model, Performance metrics","lastPublishedDoi":"10.21203/rs.3.rs-7075354/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7075354/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate water demand prediction is critical for infrastructure stability and resource optimization, yet short-term forecasting remains challenging due to high volatility from meteorological, seasonal, and socio-temporal factors (e.g., holidays). To address this, we collected 402 days of urban water demand records augmented with web-scraped meteorological and temporal features. Through SHapley Additive exPlanations (SHAP) analysis, we identified and retained high-impact features (e.g., maximum temperature, day-of-week) while eliminating redundant variables (e.g., minimum temperature, cloudy conditions), achieving a 22% reduction in feature dimensionality with a 0.16 percentage point improvement in MAPE across all AI models. We systematically compared 7 machine learning models and 3 deep learning models against an ARIMA baseline model using four performance metrics. The results indicate that deep learning methods have significant advantages in prediction accuracy, while machine learning models have certain shortcomings in predicting time series. The organic combination of interpretable feature selection in machine learning and precise prediction in deep learning provides actionable insights for utilities.\u003c/p\u003e","manuscriptTitle":"Daily water demand forecasting: Comparing AI models with SHAP-optimized features","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-01 21:39:45","doi":"10.21203/rs.3.rs-7075354/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":"e69293ad-a557-4a50-b19e-214b3c11b570","owner":[],"postedDate":"August 1st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-08-06T06:58:55+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-01 21:39:45","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7075354","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7075354","identity":"rs-7075354","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}