An Integrated Model for Conglomerate Reservoir Quality Classification Based on Graph Attention and Multiscale Multimodal Features

An Integrated Model for Conglomerate Reservoir Quality Classification Based on Graph Attention and Multiscale Multimodal 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 Article An Integrated Model for Conglomerate Reservoir Quality Classification Based on Graph Attention and Multiscale Multimodal Features Bingjin Zhao, Shanyong Liu, Yishan Lou, Biao Yin This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8928129/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 19 Apr, 2026 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Conglomerate reservoirs are jointly controlled by multiscale sedimentary architectures and diagenetic processes, resulting in pronounced spatial heterogeneity and strong discontinuity in petrophysical and rock mechanical properties. This complexity substantially increases the difficulty of identifying dominant controlling factors and performing reservoir quality classification. To address this challenge, an integrated modeling framework that combines dominant factor identification with reservoir quality grading is proposed. In this study, a sample similarity graph is constructed to explicitly characterize geological relationships among reservoir samples. A Point Graph–based Graph Attention Network (Point Graph-GAT) is employed to quantitatively evaluate the relative importance of geological and engineering parameters. Using production performance as a reference, a Hierarchical Transformer–based Multimodal Fusion model is developed to achieve multiscale and multimodal reservoir quality classification. Through a cross-attention mechanism and hierarchical Transformer architecture, the proposed model effectively captures the complex relationships between dominant reservoir factors and production capacity, while a grade-mapping module is designed to realize reservoir quality grading. The results indicate that the importance of controlling factors for conglomerate reservoirs decreases in the order of Poisson’s ratio, porosity, permeability, pore pressure, brittleness index, density, gamma ray, shale content, and tensile strength. The model demonstrates stable convergence with a final loss of 0.0006, outperforming the best ablation model with a loss of 0.001, and exhibits superior overall performance compared with benchmark models. Furthermore, the predicted reservoir quality grades of new wells show high consistency with actual classifications, with differences in grade proportions controlled within 2% for all classes. The proposed method effectively characterizes reservoir quality variations in complex conglomerate reservoirs and provides a reliable technical approach for sweet-spot identification and fine-scale reservoir development. Physical sciences/Energy science and technology Physical sciences/Engineering Physical sciences/Mathematics and computing Earth and environmental sciences/Solid earth sciences Conglomerate reservoir Point Graph-GAT Hierarchical Transformer-based multimodal fusion Reservoir quality evaluation Geological and engineering evaluation method Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 19 Apr, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 13 Mar, 2026 Reviews received at journal 10 Mar, 2026 Reviews received at journal 07 Mar, 2026 Reviewers agreed at journal 03 Mar, 2026 Reviewers agreed at journal 28 Feb, 2026 Reviewers invited by journal 24 Feb, 2026 Editor assigned by journal 24 Feb, 2026 Editor invited by journal 24 Feb, 2026 Submission checks completed at journal 21 Feb, 2026 First submitted to journal 21 Feb, 2026 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-8928129","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":596761390,"identity":"e9953946-64b7-44fa-861e-b3202e52d842","order_by":0,"name":"Bingjin Zhao","email":"","orcid":"","institution":"Yangtze University","correspondingAuthor":false,"prefix":"","firstName":"Bingjin","middleName":"","lastName":"Zhao","suffix":""},{"id":596761391,"identity":"9ff8de62-3e19-4f40-8ecf-97defc039336","order_by":1,"name":"Shanyong Liu","email":"data:image/png;base64,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","orcid":"","institution":"Yangtze University","correspondingAuthor":true,"prefix":"","firstName":"Shanyong","middleName":"","lastName":"Liu","suffix":""},{"id":596761392,"identity":"b36fb559-b103-4d7b-8967-e4be9e1776c8","order_by":2,"name":"Yishan Lou","email":"","orcid":"","institution":"Yangtze University","correspondingAuthor":false,"prefix":"","firstName":"Yishan","middleName":"","lastName":"Lou","suffix":""},{"id":596761393,"identity":"387c5c39-fbcf-4c9c-8ab4-528a1e9c4ac8","order_by":3,"name":"Biao Yin","email":"","orcid":"","institution":"Yangtze University","correspondingAuthor":false,"prefix":"","firstName":"Biao","middleName":"","lastName":"Yin","suffix":""}],"badges":[],"createdAt":"2026-02-20 17:38:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8928129/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8928129/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-026-49175-x","type":"published","date":"2026-04-19T15:59:13+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":107350890,"identity":"027320c2-3c7e-4513-8419-f7d4e630019d","added_by":"auto","created_at":"2026-04-20 16:06:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1228332,"visible":true,"origin":"","legend":"","description":"","filename":"AnIntegratedModelforConglomerateReservoirQualityClassificationBasedonGraphAttentionandMultiscaleMultimodalFeatures.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8928129/v1_covered_20f6aca4-2dcc-4fd3-ae16-5ee0a22325eb.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An Integrated Model for Conglomerate Reservoir Quality Classification Based on Graph Attention and Multiscale Multimodal Features","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":"Conglomerate reservoir, Point Graph-GAT, Hierarchical Transformer-based multimodal fusion, Reservoir quality evaluation, Geological and engineering evaluation method","lastPublishedDoi":"10.21203/rs.3.rs-8928129/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8928129/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eConglomerate reservoirs are jointly controlled by multiscale sedimentary architectures and diagenetic processes, resulting in pronounced spatial heterogeneity and strong discontinuity in petrophysical and rock mechanical properties. This complexity substantially increases the difficulty of identifying dominant controlling factors and performing reservoir quality classification. To address this challenge, an integrated modeling framework that combines dominant factor identification with reservoir quality grading is proposed. In this study, a sample similarity graph is constructed to explicitly characterize geological relationships among reservoir samples. A Point Graph\u0026ndash;based Graph Attention Network (Point Graph-GAT) is employed to quantitatively evaluate the relative importance of geological and engineering parameters. Using production performance as a reference, a Hierarchical Transformer\u0026ndash;based Multimodal Fusion model is developed to achieve multiscale and multimodal reservoir quality classification. Through a cross-attention mechanism and hierarchical Transformer architecture, the proposed model effectively captures the complex relationships between dominant reservoir factors and production capacity, while a grade-mapping module is designed to realize reservoir quality grading. The results indicate that the importance of controlling factors for conglomerate reservoirs decreases in the order of Poisson\u0026rsquo;s ratio, porosity, permeability, pore pressure, brittleness index, density, gamma ray, shale content, and tensile strength. The model demonstrates stable convergence with a final loss of 0.0006, outperforming the best ablation model with a loss of 0.001, and exhibits superior overall performance compared with benchmark models. Furthermore, the predicted reservoir quality grades of new wells show high consistency with actual classifications, with differences in grade proportions controlled within 2% for all classes. The proposed method effectively characterizes reservoir quality variations in complex conglomerate reservoirs and provides a reliable technical approach for sweet-spot identification and fine-scale reservoir development.\u003c/p\u003e","manuscriptTitle":"An Integrated Model for Conglomerate Reservoir Quality Classification Based on Graph Attention and Multiscale Multimodal Features","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-26 04:50:47","doi":"10.21203/rs.3.rs-8928129/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-13T13:46:37+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-11T02:26:11+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-08T01:31:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"197482272817980107107957750005530576614","date":"2026-03-04T04:12:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"282293994912446258047059842848105671831","date":"2026-02-28T23:33:22+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-24T10:08:40+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-24T10:04:20+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-02-24T05:12:19+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-21T14:25:52+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-02-21T14:21:08+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":"be1566e6-9e08-45c7-a02b-077d065da15e","owner":[],"postedDate":"February 26th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":63495874,"name":"Physical sciences/Energy science and technology"},{"id":63495875,"name":"Physical sciences/Engineering"},{"id":63495876,"name":"Physical sciences/Mathematics and computing"},{"id":63495877,"name":"Earth and environmental sciences/Solid earth sciences"}],"tags":[],"updatedAt":"2026-04-20T16:03:44+00:00","versionOfRecord":{"articleIdentity":"rs-8928129","link":"https://doi.org/10.1038/s41598-026-49175-x","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2026-04-19 15:59:13","publishedOnDateReadable":"April 19th, 2026"},"versionCreatedAt":"2026-02-26 04:50:47","video":"","vorDoi":"10.1038/s41598-026-49175-x","vorDoiUrl":"https://doi.org/10.1038/s41598-026-49175-x","workflowStages":[]},"version":"v1","identity":"rs-8928129","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8928129","identity":"rs-8928129","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}