Learning Injection–Seismicity Coupling for Probabilistic Multi-Horizon Forecasting in Geothermal Systems

Learning Injection–Seismicity Coupling for Probabilistic Multi-Horizon Forecasting in Geothermal Systems | 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 Learning Injection–Seismicity Coupling for Probabilistic Multi-Horizon Forecasting in Geothermal Systems Zhengfa Bi, Nori Nakata This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8949913/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Induced seismicity presents significant challenges to the sustainable development of geothermal energy, as fluid injection and reservoir stimulation frequently trigger seismic events. The underlying physical mechanisms involve complex interactions between the solid Earth and injected fluid, which makes the numerical flow modeling and mechanical failure analysis difficult, and leads to inaccurate forecasting of induced seismicity. This study introduces a deep learning framework that integrates multi-horizon forecasting with interpretability to predict seismicity in geothermal fields. By dynamically selecting relevant seismicity and operational data through variable selection networks, the model unifies key drivers within a single predictive architecture. The model with self-attention mechanisms and probabilistic forecasting identifies key seismicity drivers and quantifies uncertainty to evaluate fluid injection on future seismicity. Case studies from two geothermal fields, the Geysers and Utah FORGE, reveal site-specific seismic response governed by hydromechanical conditions, offering insights into fluid-induced stress evolution. Beyond risk mitigation, this approach provides a data-driven pathway for probing subsurface rheology through seismic response to geothermal operations. Earth and environmental sciences/Solid Earth sciences/Seismology Earth and environmental sciences/Solid Earth sciences/Geophysics Induced seismicity Fluid injection Geothermal systems Seismicity forecasting Deep learning Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Under Review 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-8949913","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":600803385,"identity":"a928bef6-b677-4ff3-83b8-25f073a93016","order_by":0,"name":"Zhengfa Bi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAoElEQVRIie3QoQ7CMBDG8SNNTh2rrSDsFUowEzxMMagJJE8w1QfA8yJtmqD2CBOo6UkknUHfORLu73+5fAegab+YGSEt17QTEOwh330iGTEkIu2wzeXkJwL7eDoW2QxNKL2fCdx84RHTRl9JqWQ8ehZBJF86EaGVwEpsPLxYxGETcqxb0OGZR+rHyvK+TXtrS0os8g1dkIGaFd7QNE37nz6qsyphPOerLQAAAABJRU5ErkJggg==","orcid":"","institution":"Lawrence Berkeley National Lab","correspondingAuthor":true,"prefix":"","firstName":"Zhengfa","middleName":"","lastName":"Bi","suffix":""},{"id":600803386,"identity":"8452e8e8-1b34-4d09-b1b5-b112304c219a","order_by":1,"name":"Nori Nakata","email":"","orcid":"https://orcid.org/0000-0002-9295-9416","institution":"Lawrence Berkeley National Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Nori","middleName":"","lastName":"Nakata","suffix":""}],"badges":[],"createdAt":"2026-02-23 18:36:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8949913/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8949913/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104225222,"identity":"7409c309-e40a-4a61-921c-bbd0e1ecc799","added_by":"auto","created_at":"2026-03-09 10:57:55","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3298088,"visible":true,"origin":"","legend":"Article File","description":"","filename":"LearningtheCouplingBetweenFluidInjectionandInducedSeismicityforMultiHorizonForecastinginGeothermalSystems.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8949913/v1_covered_dd53485a-5c4f-412a-ba0b-ed33dec3bbd6.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Learning Injection–Seismicity Coupling for Probabilistic Multi-Horizon Forecasting in Geothermal Systems","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Induced seismicity, Fluid injection, Geothermal systems, Seismicity forecasting, Deep learning","lastPublishedDoi":"10.21203/rs.3.rs-8949913/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8949913/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Induced seismicity presents significant challenges to the sustainable development of geothermal energy, as fluid injection and reservoir stimulation frequently trigger seismic events. \r\nThe underlying physical mechanisms involve complex interactions between the solid Earth and injected fluid, which makes the numerical flow modeling and mechanical failure analysis difficult, and leads to inaccurate forecasting of induced seismicity.\r\nThis study introduces a deep learning framework that integrates multi-horizon forecasting with interpretability to predict seismicity in geothermal fields.\r\nBy dynamically selecting relevant seismicity and operational data through variable selection networks, the model unifies key drivers within a single predictive architecture.\r\nThe model with self-attention mechanisms and probabilistic forecasting identifies key seismicity drivers and quantifies uncertainty to evaluate fluid injection on future seismicity. \r\nCase studies from two geothermal fields, the Geysers and Utah FORGE, reveal site-specific seismic response governed by hydromechanical conditions, offering insights into fluid-induced stress evolution.\r\nBeyond risk mitigation, this approach provides a data-driven pathway for probing subsurface rheology through seismic response to geothermal operations.","manuscriptTitle":"Learning Injection–Seismicity Coupling for Probabilistic Multi-Horizon Forecasting in Geothermal Systems","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-09 10:56:14","doi":"10.21203/rs.3.rs-8949913/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"communications-earth-and-environment","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"commsenv","sideBox":"Learn more about [Communications Earth and Environment](https://www.nature.com/commsenv/)","snPcode":"","submissionUrl":"","title":"Communications Earth \u0026 Environment","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Communications Series","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"7f336e95-0baa-4360-8335-0fc72040b31a","owner":[],"postedDate":"March 9th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"This content is not available.","date":"2026-05-02T04:05:18+00:00","index":2,"fulltext":"This content is not available."}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":63938159,"name":"Earth and environmental sciences/Solid Earth sciences/Seismology"},{"id":63938160,"name":"Earth and environmental sciences/Solid Earth sciences/Geophysics"}],"tags":[],"updatedAt":"2026-03-09T10:56:14+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-09 10:56:14","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8949913","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8949913","identity":"rs-8949913","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}