A novel causal meta-learning method based on causality for the prediction of CBM well productivity

A novel causal meta-learning method based on causality for the prediction of CBM well productivity | 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 A novel causal meta-learning method based on causality for the prediction of CBM well productivity Chao Min, Jialiang Ge, Guoquan Wen, Xiaogang Li, Zhaozhong Yang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7845158/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 6 You are reading this latest preprint version Abstract A novel causal meta-learning (CaML) approach is proposed to enhance the performance of the coalbed methane (CBM) productivity forecasting model by leveraging the causality among factors. First, the original production dataset is segmented into multiple subsets (i.e. task datasets) to create the causal meta-dataset, thereby optimizing data utilization in cases of insufficient data. Subsequently, the feature weight matrix (FWM) is calculated by employing the conditional average treatment effects (CATEs) estimators and adaptive algorithm in each task dataset. Then, we integrate all the task-specific knowledge within a meta-learning framework to build a more robust predictive model that has the ability to generalize across tasks. Finally, by treating the FWM as causal constraints, a CaML model is developed to maximize interpretability. Compared with generic methods, the proposed approach shows clear superiority in evaluation metrics, with an average improvement of 23% in prediction accuracy, along with significant enhancements in generalization and interpretability. Coalbed Methane Conditional Average Treatment Effect Feature Weight Matrix Causal Meta-learning algorithm Interpretability Full Text Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Major revisions 18 May, 2026 Reviewers agreed at journal 03 Feb, 2026 Reviewers invited by journal 02 Feb, 2026 Editor invited by journal 29 Dec, 2025 Editor assigned by journal 15 Oct, 2025 First submitted to journal 12 Oct, 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-7845158","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":584682905,"identity":"b897fa17-74b6-4b8e-b8d9-c92c1360834f","order_by":0,"name":"Chao Min","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxElEQVRIiWNgGAWjYDACZjBikENwidViTIIWqLLEBqK16LbzHvxcUGOTPn9G7jEJhgrrxAb2swfwajE7zJcsPeNYWu6GG3lpEgxn0hMbePISCGjhMWPmYTucu0E6x0yCse1wYoMEjwERWv4dTpefDdLyj1gtvG2HExhug7Q0EKfFWJq3L81ww/13yRYJx9KN23hyCGg5f8bwM883G3n5nrMHb3yosZbtZz+DXwsS4GFgSABSbMSqh2gZBaNgFIyCUYANAABoZT02ykH4vwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0003-1245-8142","institution":"Southwest Petroleum University","correspondingAuthor":true,"prefix":"","firstName":"Chao","middleName":"","lastName":"Min","suffix":""},{"id":584682906,"identity":"8ab97410-6c0c-4358-82c3-15a475d89811","order_by":1,"name":"Jialiang Ge","email":"","orcid":"","institution":"Southwest Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Jialiang","middleName":"","lastName":"Ge","suffix":""},{"id":584682907,"identity":"4368abc7-3560-4a84-a1e5-fbfa0736cf32","order_by":2,"name":"Guoquan Wen","email":"","orcid":"","institution":"Chengdu Technological University","correspondingAuthor":false,"prefix":"","firstName":"Guoquan","middleName":"","lastName":"Wen","suffix":""},{"id":584682908,"identity":"11096895-70c5-4c56-9bfc-241816884696","order_by":3,"name":"Xiaogang Li","email":"","orcid":"","institution":"Southwest Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Xiaogang","middleName":"","lastName":"Li","suffix":""},{"id":584682909,"identity":"d1ca548c-6841-4d15-bd96-df5b6ff1aab5","order_by":4,"name":"Zhaozhong Yang","email":"","orcid":"","institution":"Southwest Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Zhaozhong","middleName":"","lastName":"Yang","suffix":""}],"badges":[],"createdAt":"2025-10-13 06:28:36","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7845158/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7845158/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102397686,"identity":"7c28206e-e4fa-4bc2-8c18-ba9bd3cb7a0f","added_by":"auto","created_at":"2026-02-11 10:18:58","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":8142372,"visible":true,"origin":"","legend":"","description":"","filename":"AGPHD2500864reviewer.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7845158/v1_covered_8dbdc5cf-8309-4244-a5c0-a19872d772e0.pdf"}],"financialInterests":"","formattedTitle":"A novel causal meta-learning method based on causality for the prediction of CBM well productivity","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":"acta-geophysica","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"agph","sideBox":"Learn more about [Acta Geophysica](http://link.springer.com/journal/11600)","snPcode":"11600","submissionUrl":"https://www.editorialmanager.com/agph/default2.aspx","title":"Acta Geophysica","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Coalbed Methane, Conditional Average Treatment Effect, Feature Weight Matrix, Causal Meta-learning algorithm, Interpretability","lastPublishedDoi":"10.21203/rs.3.rs-7845158/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7845158/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e A novel causal meta-learning (CaML) approach is proposed to enhance the performance of the coalbed methane (CBM) productivity forecasting model by leveraging the causality among factors. First, the original production dataset is segmented into multiple subsets (i.e. task datasets) to create the causal meta-dataset, thereby optimizing data utilization in cases of insufficient data. Subsequently, the feature weight matrix (FWM) is calculated by employing the conditional average treatment effects (CATEs) estimators and adaptive algorithm in each task dataset. Then, we integrate all the task-specific knowledge within a meta-learning framework to build a more robust predictive model that has the ability to generalize across tasks. Finally, by treating the FWM as causal constraints, a CaML model is developed to maximize interpretability. Compared with generic methods, the proposed approach shows clear superiority in evaluation metrics, with an average improvement of 23% in prediction accuracy, along with significant enhancements in generalization and interpretability. \u003c/p\u003e","manuscriptTitle":"A novel causal meta-learning method based on causality for the prediction of CBM well productivity","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-05 15:15:52","doi":"10.21203/rs.3.rs-7845158/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revisions","date":"2026-05-19T01:40:22+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"","date":"2026-02-03T05:16:09+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-03T01:44:08+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"Acta Geophysica","date":"2025-12-29T10:20:01+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-15T07:24:07+00:00","index":"","fulltext":""},{"type":"submitted","content":"Acta Geophysica","date":"2025-10-13T02:09:22+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"acta-geophysica","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"agph","sideBox":"Learn more about [Acta Geophysica](http://link.springer.com/journal/11600)","snPcode":"11600","submissionUrl":"https://www.editorialmanager.com/agph/default2.aspx","title":"Acta Geophysica","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"0f563527-e75b-4a70-adfd-fbaf9d28927f","owner":[],"postedDate":"February 5th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Major revisions","date":"2026-05-19T01:40:22+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-05-19T05:41:35+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-05 15:15:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7845158","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7845158","identity":"rs-7845158","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}