Optimizing Sustainable Power Generation with Triplet Deep Borehole Heat Exchangers: A Machine Learning Approach

Optimizing Sustainable Power Generation with Triplet Deep Borehole Heat Exchangers: A Machine Learning Approach | 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 Optimizing Sustainable Power Generation with Triplet Deep Borehole Heat Exchangers: A Machine Learning Approach Abubakar Magaji, Bin Dou, AL-Wesabi Ibrahim, Ismaila Yusuf Pindiga, and 6 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6185339/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 Geothermal energy, a renewable and sustainable resource, has significant potential for meeting global energy demands; most of the study on production and generation relies on numerical simulation. However, the computational intensity of physics-based numerical simulations for geothermal energy production poses challenges. This study explores the integration of machine learning models with numerical simulation to forecast long-term electricity generation from a triplet deep borehole heat exchanger system. A large dataset generated through COMSOL Multiphysics numerical simulations served as input for three machine learning models: Decision Tree, XGBoost, and Random Forest. The Random Forest model outperformed the others, achieving the lowest error metrics with a Root Mean Square Percentage Error (RMSPE) of 0.104, a Mean Absolute Percentage Error (MAPE) of 0.0539, and the highest R² value of 0.9996. These metrics indicate that the RF model provides exceptional prediction accuracy and generalization capabilities. The combined approach of numerical simulation and machine learning significantly reduced the computational time required, enabling the forecasting of an additional 15 years of power generation using Random Forest, which makes it easier and faster than waiting for almost 21 hours before simulating for 25 years. The results confirm the viability of Random Forest for optimizing geothermal energy forecasting, ensuring sustainability and operational efficiency in geothermal power generation. Physical sciences/Engineering/Civil engineering Physical sciences/Engineering Geothermal energy machine learning random forest Numerical simulation electricity forecasting computational efficiency. Full Text Additional Declarations No competing interests reported. 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-6185339","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":435020016,"identity":"cd0aacb7-1539-43cd-9965-4a73e6766c7d","order_by":0,"name":"Abubakar Magaji","email":"","orcid":"","institution":"China University of Geosciences","correspondingAuthor":false,"prefix":"","firstName":"Abubakar","middleName":"","lastName":"Magaji","suffix":""},{"id":435020017,"identity":"4566a734-66ae-43cd-a076-3e0a6824a2ff","order_by":1,"name":"Bin Dou","email":"","orcid":"","institution":"China University of Geosciences","correspondingAuthor":false,"prefix":"","firstName":"Bin","middleName":"","lastName":"Dou","suffix":""},{"id":435020018,"identity":"760e13ca-e3d6-478a-a84c-f7d56f2bd86a","order_by":2,"name":"AL-Wesabi Ibrahim","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAw0lEQVRIiWNgGAWjYBAC+RkMDMwMBgxyBmAuGxFa2CQgWoxJ1cLAkLiBeC3SvQ8/FxRsS98u3WPA8KHsMAP/7AYCWmSOG0vPMLidu3POGQPGGecOM0jcOUDIYWkM0jxALRtu5Bgw87YdZjCQSCCohfk3UEu6AUjLXyK1sIFsSQBrYSRKi8wxNmugFsMNN9IKDvacS+eRuEFAi/zsNubbPH9uyxvcSN744EeZtRz/DAJaUMABIOYhQf0oGAWjYBSMAlwAAHARPPwgMfXNAAAAAElFTkSuQmCC","orcid":"","institution":"Hunan University","correspondingAuthor":true,"prefix":"","firstName":"AL-Wesabi","middleName":"","lastName":"Ibrahim","suffix":""},{"id":435020019,"identity":"66373f7a-b9cf-436b-8bec-fda261c35e78","order_by":3,"name":"Ismaila Yusuf Pindiga","email":"","orcid":"","institution":"Kaduna Polytechnic","correspondingAuthor":false,"prefix":"","firstName":"Ismaila","middleName":"Yusuf","lastName":"Pindiga","suffix":""},{"id":435020020,"identity":"69d5c67b-6b6b-4436-bd07-e89dfbe6f532","order_by":4,"name":"Yasin Ileye","email":"","orcid":"","institution":"University of Geosciences","correspondingAuthor":false,"prefix":"","firstName":"Yasin","middleName":"","lastName":"Ileye","suffix":""},{"id":435020021,"identity":"8ed95cc5-f3ef-4101-9279-59f0eeb4961b","order_by":5,"name":"Riad Dhawood","email":"","orcid":"","institution":"China University of Geosciences","correspondingAuthor":false,"prefix":"","firstName":"Riad","middleName":"","lastName":"Dhawood","suffix":""},{"id":435020023,"identity":"e4e3332c-c979-44c4-b054-b58792870d3b","order_by":6,"name":"Khaled Alwesabi","email":"","orcid":"","institution":"Al-Razi University","correspondingAuthor":false,"prefix":"","firstName":"Khaled","middleName":"","lastName":"Alwesabi","suffix":""},{"id":435020026,"identity":"0d652dd4-885a-471f-86ef-7422f87ea379","order_by":7,"name":"Roobaea Alroobaea","email":"","orcid":"","institution":"Taif University","correspondingAuthor":false,"prefix":"","firstName":"Roobaea","middleName":"","lastName":"Alroobaea","suffix":""},{"id":435020028,"identity":"cfbf9be5-416b-4fc0-93bc-1f6a2a158a01","order_by":8,"name":"Afnan Alhazmi","email":"","orcid":"","institution":"Taif University","correspondingAuthor":false,"prefix":"","firstName":"Afnan","middleName":"","lastName":"Alhazmi","suffix":""},{"id":435020030,"identity":"e223f881-6ff6-4a0e-996c-14937f514128","order_by":9,"name":"Moustafa Ahmed Ibrahim","email":"","orcid":"","institution":"University of Business and Technology","correspondingAuthor":false,"prefix":"","firstName":"Moustafa","middleName":"Ahmed","lastName":"Ibrahim","suffix":""}],"badges":[],"createdAt":"2025-03-08 17:38:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6185339/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6185339/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":80020351,"identity":"bf5e8fc2-6f0b-472e-8431-73c1081f2f4b","added_by":"auto","created_at":"2025-04-07 04:47:15","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1003867,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptScientificreports1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6185339/v1_covered_13c97ee6-d256-4266-bd16-8d1c725fd8a2.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Optimizing Sustainable Power Generation with Triplet Deep Borehole Heat Exchangers: A Machine Learning Approach","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":"Geothermal energy, machine learning, random forest, Numerical simulation, electricity forecasting, computational efficiency.","lastPublishedDoi":"10.21203/rs.3.rs-6185339/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6185339/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eGeothermal energy, a renewable and sustainable resource, has significant potential for meeting global energy demands; most of the study on production and generation relies on numerical simulation. However, the computational intensity of physics-based numerical simulations for geothermal energy production poses challenges. This study explores the integration of machine learning models with numerical simulation to forecast long-term electricity generation from a triplet deep borehole heat exchanger system. A large dataset generated through COMSOL Multiphysics numerical simulations served as input for three machine learning models: Decision Tree, XGBoost, and Random Forest. The Random Forest model outperformed the others, achieving the lowest error metrics with a Root Mean Square Percentage Error (RMSPE) of 0.104, a Mean Absolute Percentage Error (MAPE) of 0.0539, and the highest R\u0026sup2; value of 0.9996. These metrics indicate that the RF model provides exceptional prediction accuracy and generalization capabilities. The combined approach of numerical simulation and machine learning significantly reduced the computational time required, enabling the forecasting of an additional 15 years of power generation using Random Forest, which makes it easier and faster than waiting for almost 21 hours before simulating for 25 years. The results confirm the viability of Random Forest for optimizing geothermal energy forecasting, ensuring sustainability and operational efficiency in geothermal power generation.\u003c/p\u003e","manuscriptTitle":"Optimizing Sustainable Power Generation with Triplet Deep Borehole Heat Exchangers: A Machine Learning Approach","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-01 03:59:55","doi":"10.21203/rs.3.rs-6185339/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":"4a38ec4b-7275-4087-a98b-a4ee0f228005","owner":[],"postedDate":"April 1st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":46323864,"name":"Physical sciences/Engineering/Civil engineering"},{"id":46323865,"name":"Physical sciences/Engineering"}],"tags":[],"updatedAt":"2025-04-07T04:39:07+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-01 03:59:55","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6185339","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6185339","identity":"rs-6185339","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}