Predicting CO₂ injectivity profiles in heterogeneous reservoirs using a physics-aware deep learning framework

Predicting CO₂ injectivity profiles in heterogeneous reservoirs using a physics-aware deep learning framework | 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 Predicting CO₂ injectivity profiles in heterogeneous reservoirs using a physics-aware deep learning framework Zihao Zheng, Haoxi Shi, Xintong Liu, Xinying Song, Ziqian Hu, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9218070/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 10 You are reading this latest preprint version Abstract Accurate prediction of CO 2 injectivity profiles is essential for optimizing injection strategies and improving sweep efficiency in heterogeneous reservoirs. However, strong geological heterogeneity and complex injection regimes introduce substantial nonlinearity and temporal dependence, which limit the effectiveness of conventional numerical simulation and traditional machine learning approaches. This study presents a deep learning framework that integrates Bidirectional Long Short-Term Memory (Bi-LSTM), attention, and Feature-wise Linear Modulation (FiLM) for predicting the dynamic evolution of CO 2 injectivity profiles. A large-scale, physically consistent dataset was constructed using a three-dimensional compositional reservoir simulator (ECLIPSE) under multiple injection scenarios. The proposed model jointly learns temporal dependencies from historical injection dynamics while incorporating static geological properties through FiLM-based feature modulation. Within this framework, layer-specific injectivity is treated as an implicit dynamic state that evolves over time, enabling unified modeling of geological constraints and injection dynamics. Experimental results demonstrate that the proposed framework significantly outperforms conventional LSTM-based models. On the testing dataset, the model achieves a Mean Absolute Error (MAE) of 13.77 and a coefficient of determination = 0.9933. Ablation studies further reveal that the integration of Bi-LSTM, attention, and the FiLM module substantially enhances the model’s ability to capture transient injectivity responses under non-stationary injection conditions. In addition, the predicted injectivity profiles show strong consistency with the spatial gas distribution obtained from numerical simulation. Overall, the proposed method provides an efficient data-driven solution for dynamic injectivity profile prediction and offers a new perspective for representing reservoir flow behavior through implicit dynamic state modeling. The framework may support injection–production optimization in CO 2 -EOR and CCUS field applications. Physical sciences/Energy science and technology Physical sciences/Mathematics and computing Earth and environmental sciences/Solid earth sciences CO2 injectivity profile heterogeneous reservoirs Bi-LSTM attention mechanism Feature-wise Linear Modulation (FiLM) CO2-EOR Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 07 May, 2026 Reviews received at journal 05 May, 2026 Reviews received at journal 03 May, 2026 Reviewers agreed at journal 22 Apr, 2026 Reviewers agreed at journal 08 Apr, 2026 Reviewers invited by journal 31 Mar, 2026 Editor invited by journal 30 Mar, 2026 Editor assigned by journal 25 Mar, 2026 Submission checks completed at journal 25 Mar, 2026 First submitted to journal 25 Mar, 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-9218070","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":615271798,"identity":"ca53467e-8d9f-4e39-be7f-d6e4a145d4a6","order_by":0,"name":"Zihao Zheng","email":"","orcid":"","institution":"Yangtze University","correspondingAuthor":false,"prefix":"","firstName":"Zihao","middleName":"","lastName":"Zheng","suffix":""},{"id":615271799,"identity":"b52b7df8-76ff-4e47-a5b6-90009661ba37","order_by":1,"name":"Haoxi Shi","email":"","orcid":"","institution":"Yangtze University","correspondingAuthor":false,"prefix":"","firstName":"Haoxi","middleName":"","lastName":"Shi","suffix":""},{"id":615271800,"identity":"11f43bc6-7802-4b89-b2fa-69513baf15f4","order_by":2,"name":"Xintong Liu","email":"","orcid":"","institution":"Yangtze University","correspondingAuthor":false,"prefix":"","firstName":"Xintong","middleName":"","lastName":"Liu","suffix":""},{"id":615271801,"identity":"f08ec35f-b8e7-462f-8854-c83f869b38ec","order_by":3,"name":"Xinying Song","email":"","orcid":"","institution":"Yangtze University","correspondingAuthor":false,"prefix":"","firstName":"Xinying","middleName":"","lastName":"Song","suffix":""},{"id":615271802,"identity":"07ba20ac-ef3f-4949-91a1-261978633cb5","order_by":4,"name":"Ziqian Hu","email":"","orcid":"","institution":"Yangtze University","correspondingAuthor":false,"prefix":"","firstName":"Ziqian","middleName":"","lastName":"Hu","suffix":""},{"id":615271803,"identity":"8d8f2b82-230c-4be1-aea5-c1187532b87c","order_by":5,"name":"Xinyue Zhong","email":"","orcid":"","institution":"Yangtze University","correspondingAuthor":false,"prefix":"","firstName":"Xinyue","middleName":"","lastName":"Zhong","suffix":""},{"id":615271804,"identity":"eba84f08-b30d-4c70-acca-618385c8734c","order_by":6,"name":"Hua Xiang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABD0lEQVRIiWNgGAWjYDACZiBmbGBg4EcWlCBKi2QDiJdAjBYGqBaDA8RqMTjO/Ozh1x2H5Y1vJAMZP+rkDA4wH7zNw2CXh0uLZDObubHsmcOG226kmRvLJLAZGxxgS7bmYUguxqWFn5nBTFqy7TDjthsJZtISCTyJGw7wmEnzMBxIbMChhY2Z/RtIi/3mGenfgFok6jcc4P+GVws/M4+Z5Me2w4kbJHLMJD8kGCQYHOBhw6tFspmnTJqxLT15xpk3ZdIMaQmGMw+zGVvOMUjGqcXg/PFtkj/brG3729O3Sf6wqZPnO9788MabCjucWkCAmQdECiRAGcxgo/CoBwLGH2BfHYAyRsEoGAWjYBSgAQC0WVNaFBDN5AAAAABJRU5ErkJggg==","orcid":"","institution":"Yangtze University","correspondingAuthor":true,"prefix":"","firstName":"Hua","middleName":"","lastName":"Xiang","suffix":""}],"badges":[],"createdAt":"2026-03-25 04:40:02","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9218070/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9218070/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106094571,"identity":"46d48e00-ec63-44b4-921d-4cbdb0fd1cee","added_by":"auto","created_at":"2026-04-03 11:42:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1252192,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9218070/v1_covered_6dbae6ae-4ac6-423a-a51e-43f83ffe4cfb.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Predicting CO₂ injectivity profiles in heterogeneous reservoirs using a physics-aware deep learning framework","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":"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":"CO2 injectivity profile, heterogeneous reservoirs, Bi-LSTM, attention mechanism, Feature-wise Linear Modulation (FiLM), CO2-EOR","lastPublishedDoi":"10.21203/rs.3.rs-9218070/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9218070/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate prediction of CO\u003csub\u003e2\u003c/sub\u003e injectivity profiles is essential for optimizing injection strategies and improving sweep efficiency in heterogeneous reservoirs. However, strong geological heterogeneity and complex injection regimes introduce substantial nonlinearity and temporal dependence, which limit the effectiveness of conventional numerical simulation and traditional machine learning approaches. This study presents a deep learning framework that integrates Bidirectional Long Short-Term Memory (Bi-LSTM), attention, and Feature-wise Linear Modulation (FiLM) for predicting the dynamic evolution of CO\u003csub\u003e2\u003c/sub\u003e injectivity profiles. A large-scale, physically consistent dataset was constructed using a three-dimensional compositional reservoir simulator (ECLIPSE) under multiple injection scenarios. The proposed model jointly learns temporal dependencies from historical injection dynamics while incorporating static geological properties through FiLM-based feature modulation. Within this framework, layer-specific injectivity is treated as an implicit dynamic state that evolves over time, enabling unified modeling of geological constraints and injection dynamics. Experimental results demonstrate that the proposed framework significantly outperforms conventional LSTM-based models. On the testing dataset, the model achieves a Mean Absolute Error (MAE) of 13.77 and a coefficient of determination \u003cspan class=\"InlineEquation\"\u003e\u003c/span\u003e = 0.9933. Ablation studies further reveal that the integration of Bi-LSTM, attention, and the FiLM module substantially enhances the model\u0026rsquo;s ability to capture transient injectivity responses under non-stationary injection conditions. In addition, the predicted injectivity profiles show strong consistency with the spatial gas distribution obtained from numerical simulation. Overall, the proposed method provides an efficient data-driven solution for dynamic injectivity profile prediction and offers a new perspective for representing reservoir flow behavior through implicit dynamic state modeling. The framework may support injection\u0026ndash;production optimization in CO\u003csub\u003e2\u003c/sub\u003e-EOR and CCUS field applications.\u003c/p\u003e","manuscriptTitle":"Predicting CO₂ injectivity profiles in heterogeneous reservoirs using a physics-aware deep learning framework","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-03 07:35:23","doi":"10.21203/rs.3.rs-9218070/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-07T08:55:59+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-05T22:49:34+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-04T03:17:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"203762862081094309474834488385943892532","date":"2026-04-22T06:35:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"265939369730326274091157557023044678583","date":"2026-04-08T11:28:35+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-31T12:13:42+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-03-30T12:47:56+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-25T14:18:43+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-25T14:17:48+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-03-25T04:25:21+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":"892d4a34-9ed3-449b-b538-8d98bd5fa51d","owner":[],"postedDate":"April 3rd, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-07T08:55:59+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-05T22:49:34+00:00","index":34,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-04T03:17:16+00:00","index":33,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[{"id":65467439,"name":"Physical sciences/Energy science and technology"},{"id":65467440,"name":"Physical sciences/Mathematics and computing"},{"id":65467441,"name":"Earth and environmental sciences/Solid earth sciences"}],"tags":[],"updatedAt":"2026-05-07T09:08:34+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-03 07:35:23","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9218070","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9218070","identity":"rs-9218070","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}