Geology-Constrained Time Series Generative Adversarial Network for Well Log Curve Reconstruction

Geology-Constrained Time Series Generative Adversarial Network for Well Log Curve Reconstruction | 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 Geology-Constrained Time Series Generative Adversarial Network for Well Log Curve Reconstruction Guo Haifeng, Liao Wenlong, Zhao Bin, Cheng Xiaodong, Wang Kun This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7568898/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 Complex geological and downhole engineering conditions—such as borehole enlargement, fracture development, and mud invasion—often induce anomalous logging responses, leading to missing key curves and compromising reservoir evaluation accuracy. Traditional interpolation and statistical methods struggle to capture the non-stationarity and strong nonlinearity of log curves; conventional models often neglect sequential dependencies along depth, while deep sequence models are limited to point-by-point regression, restricting their ability to maintain overall geological consistency. To address these challenges, this study proposes a Geology-Constrained Time Series Conditional Generative Adversarial Network (GC-TSGAN). Lithological information is embedded as prior conditions into both the generator and discriminator. The model leverages LSTM to capture sequential dependencies along depth, while an LSGAN-based adversarial loss enforces distributional consistency and local morphological fidelity. Random search and Bayesian optimization are applied for efficient hyperparameter tuning. Experiments on logging data from 41 wells in the B Basin, Chad, show that GC-TSGAN outperforms baseline models including RF, XGBoost, LSTM, and ANN across RMSE, MAE, and R². Results confirm that the proposed model achieves high-precision log curve reconstruction under complex geological conditions, providing a reliable data foundation for geological modeling and reservoir evaluation. Physical sciences/Mathematics and computing Earth and environmental sciences/Solid earth sciences 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-7568898","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":524775034,"identity":"6deb41fd-d3a0-4a2a-bd09-154e180b61db","order_by":0,"name":"Guo Haifeng","email":"","orcid":"","institution":"China National Logging Corporation","correspondingAuthor":false,"prefix":"","firstName":"Guo","middleName":"","lastName":"Haifeng","suffix":""},{"id":524775036,"identity":"b4ce1a35-bf9f-4e2b-a141-8795438e42ac","order_by":1,"name":"Liao Wenlong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCUlEQVRIie2RMUvEMBTHUwIpwrveGjlRP8KTwE3h/CAuKYVMVgouDh0KwjkouOZjKAXnQqAuPfwKB52FcxcxPTchPW67Ib/h8Yb8eHnvT0ggcIAk24pycWmpXW/uytMpdc2Ywra10Bl5X+oL07Xi+IFp3K1sbFR1Hc6OljTFDzjno0r8mPYFahoZrQRhTAkLBEkpr7wKrGphUCaUZ01fwMnN3E6aNWl1XvkUnr/NwE1h3E0xnN3ObaIwqqxfOfscFBs98Wt0DU3re0A+qvDJn2LArQ+Kpi90lwJ5LdzHMoyHIzet4NYdWY3sMo1Xrz18ywUOCX79uCifrcu0lF7Fg9rveSAQCAT+8QusklbDRhH3BgAAAABJRU5ErkJggg==","orcid":"","institution":"Yangtze University","correspondingAuthor":true,"prefix":"","firstName":"Liao","middleName":"","lastName":"Wenlong","suffix":""},{"id":524775037,"identity":"960fd53d-6a04-436f-9c2a-c8cce6dacefe","order_by":2,"name":"Zhao Bin","email":"","orcid":"","institution":"Yangtze University","correspondingAuthor":false,"prefix":"","firstName":"Zhao","middleName":"","lastName":"Bin","suffix":""},{"id":524775040,"identity":"1ba11d8a-f3d8-455f-8368-0efa33cea7ad","order_by":3,"name":"Cheng Xiaodong","email":"","orcid":"","institution":"China National Logging Corporation","correspondingAuthor":false,"prefix":"","firstName":"Cheng","middleName":"","lastName":"Xiaodong","suffix":""},{"id":524775043,"identity":"d098d3ae-c8ef-4bda-b550-a383c4402d59","order_by":4,"name":"Wang Kun","email":"","orcid":"","institution":"China National Logging Corporation","correspondingAuthor":false,"prefix":"","firstName":"Wang","middleName":"","lastName":"Kun","suffix":""}],"badges":[],"createdAt":"2025-09-09 03:38:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7568898/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7568898/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92923476,"identity":"1a8d4e29-6592-4d6c-bb1c-57bf908e628d","added_by":"auto","created_at":"2025-10-07 07:27:36","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7250,"visible":true,"origin":"","legend":"","description":"","filename":"c764a30998264f1d857a39e439b9ab1f.json","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/20ae4b30daf67df0dcc59aed.json"},{"id":92923474,"identity":"cf62f402-dcb2-43f7-ba31-8cb1e7e3d15d","added_by":"auto","created_at":"2025-10-07 07:27:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":46808,"visible":true,"origin":"","legend":"","description":"","filename":"PointbypointResponsetotheEditor.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/cac9d9eeb64d661a90aea1ad.pdf"},{"id":92923478,"identity":"43d8fc21-9079-42a6-b08d-40e31e7509f4","added_by":"auto","created_at":"2025-10-07 07:27:36","extension":"png","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":243062,"visible":true,"origin":"","legend":"","description":"","filename":"basinmap.png","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/1a6db63b4db73d60fe3893c2.png"},{"id":92923475,"identity":"2d1679c6-216c-4bb5-9ca2-f13f8636f11a","added_by":"auto","created_at":"2025-10-07 07:27:36","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":81891,"visible":true,"origin":"","legend":"","description":"","filename":"bocurve.png","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/d8089878cfb8b3970bae1415.png"},{"id":92923477,"identity":"1cac8fc1-b162-41d0-a698-777ba60ac729","added_by":"auto","created_at":"2025-10-07 07:27:36","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":340184,"visible":true,"origin":"","legend":"","description":"","filename":"boscatter.png","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/df887476b32436bc83164e4b.png"},{"id":92923480,"identity":"69f5cd9a-b913-46bf-9d79-4a3872f25dd2","added_by":"auto","created_at":"2025-10-07 07:27:36","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":548588,"visible":true,"origin":"","legend":"","description":"","filename":"cganarchitecture.png","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/a753b2232633d234eb6c943f.png"},{"id":92923485,"identity":"33027831-b62a-40dd-8ac7-98bb5e3e2031","added_by":"auto","created_at":"2025-10-07 07:27:36","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":187797,"visible":true,"origin":"","legend":"","description":"","filename":"cganresult.png","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/ea3f75284bc5744ae576465e.png"},{"id":92924081,"identity":"f3530526-a81b-4eb0-96b1-67f53d327b73","added_by":"auto","created_at":"2025-10-07 07:35:36","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":854829,"visible":true,"origin":"","legend":"","description":"","filename":"figure5.png","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/4342881531a36cb9e48cdb3c.png"},{"id":92923479,"identity":"283eef83-ef1f-43ef-a96d-431501e80d86","added_by":"auto","created_at":"2025-10-07 07:27:36","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":464168,"visible":true,"origin":"","legend":"","description":"","filename":"figure6.png","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/777616c47334c33910bea64b.png"},{"id":92923482,"identity":"24cf948b-6522-49f5-bcc6-8d74d88b30df","added_by":"auto","created_at":"2025-10-07 07:27:36","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":199963,"visible":true,"origin":"","legend":"","description":"","filename":"ganresult.png","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/85980d251fe36a6cd21a8f20.png"},{"id":92923483,"identity":"730515ec-b418-42c7-a9e4-52ce5b63c0d5","added_by":"auto","created_at":"2025-10-07 07:27:36","extension":"ldf","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":49107,"visible":true,"origin":"","legend":"","description":"","filename":"jabbrvltwaall.ldf","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/b22cd632e23af3af743dec8b.ldf"},{"id":92923484,"identity":"d86ed2f3-23e0-48fe-9daf-e026702ef2d0","added_by":"auto","created_at":"2025-10-07 07:27:36","extension":"ldf","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":268657,"visible":true,"origin":"","legend":"","description":"","filename":"jabbrvltwaen.ldf","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/a50622757d2ee6f66e74291b.ldf"},{"id":92923490,"identity":"90a7dde0-b2d7-409d-83fa-e1e26d866a58","added_by":"auto","created_at":"2025-10-07 07:27:37","extension":"sty","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15480,"visible":true,"origin":"","legend":"","description":"","filename":"jabbrv.sty","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/a5166699f9b367941ccbbb1c.sty"},{"id":92923495,"identity":"7220bf02-b5ec-4488-bf1f-65723f965c55","added_by":"auto","created_at":"2025-10-07 07:27:37","extension":"pdf","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4936704,"visible":true,"origin":"","legend":"","description":"","filename":"khkrxmpqwtfmfhxnfgwndfrmqmxwyxpz.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/59e05dd2bd38b4fb28d367e3.pdf"},{"id":92923494,"identity":"fc575c01-7610-4c5e-9fb6-20bb0b15b6f6","added_by":"auto","created_at":"2025-10-07 07:27:37","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":290558,"visible":true,"origin":"","legend":"","description":"","filename":"lstmstructure.png","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/44eb2bdf550de60acd8be70c.png"},{"id":92923488,"identity":"039c6c7a-e1c4-4809-8124-cc99aa8459f8","added_by":"auto","created_at":"2025-10-07 07:27:37","extension":"bbl","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16618,"visible":true,"origin":"","legend":"","description":"","filename":"main.bbl","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/7ee748e9fc46c1eac97f5335.bbl"},{"id":92923491,"identity":"acd57bc4-0727-4fbf-96be-8145443912eb","added_by":"auto","created_at":"2025-10-07 07:27:37","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":250095,"visible":true,"origin":"","legend":"","description":"","filename":"modelcomparison.png","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/397b5461af750350ac281f4c.png"},{"id":92924083,"identity":"fb141542-935f-4a3f-bb72-6021bc8ee0cd","added_by":"auto","created_at":"2025-10-07 07:35:37","extension":"bst","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36153,"visible":true,"origin":"","legend":"","description":"","filename":"naturemagdoi.bst","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/c47e9771c05ebfe5d6af4993.bst"},{"id":92923492,"identity":"141d3c1f-ba7a-4c1f-8f3e-6aa9e06b3491","added_by":"auto","created_at":"2025-10-07 07:27:37","extension":"jpg","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":379752,"visible":true,"origin":"","legend":"","description":"","filename":"stream.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/e97dd923a132288148bb2fb4.jpg"},{"id":92924082,"identity":"5acf8746-40b6-4c86-be66-8fdf0022a1f5","added_by":"auto","created_at":"2025-10-07 07:35:36","extension":"cls","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5824,"visible":true,"origin":"","legend":"","description":"","filename":"wlscirep.cls","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/c9d03a46839f34f3b21f306e.cls"},{"id":92923493,"identity":"dee31a0a-a7d2-4363-8c16-6ac9b9d945ee","added_by":"auto","created_at":"2025-10-07 07:27:37","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1804044,"visible":true,"origin":"","legend":"","description":"","filename":"workflow.png","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/1d4d0222512c042c2cae3e23.png"},{"id":92923487,"identity":"82106f5f-7a72-482e-819f-5e35c939826f","added_by":"auto","created_at":"2025-10-07 07:27:37","extension":"xml","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":65643,"visible":true,"origin":"","legend":"","description":"","filename":"c764a30998264f1d857a39e439b9ab1f1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1/e605187249b2681a5df933f5.xml"},{"id":102296936,"identity":"ee50437c-06a4-48a6-8fee-c73b48bed93d","added_by":"auto","created_at":"2026-02-10 10:23:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2070874,"visible":true,"origin":"","legend":"","description":"","filename":"khkrxmpqwtfmfhxnfgwndfrmqmxwyxpz.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7568898/v1_covered_71ec641e-46d0-44a0-8bfb-b455407e666b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Geology-Constrained Time Series Generative Adversarial Network for Well Log Curve Reconstruction","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":"","lastPublishedDoi":"10.21203/rs.3.rs-7568898/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7568898/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eComplex geological and downhole engineering conditions—such as borehole enlargement, fracture development, and mud invasion—often induce anomalous logging responses, leading to missing key curves and compromising reservoir evaluation accuracy. Traditional interpolation and statistical methods struggle to capture the non-stationarity and strong nonlinearity of log curves; conventional models often neglect sequential dependencies along depth, while deep sequence models are limited to point-by-point regression, restricting their ability to maintain overall geological consistency. To address these challenges, this study proposes a Geology-Constrained Time Series Conditional Generative Adversarial Network (GC-TSGAN). Lithological information is embedded as prior conditions into both the generator and discriminator. The model leverages LSTM to capture sequential dependencies along depth, while an LSGAN-based adversarial loss enforces distributional consistency and local morphological fidelity. Random search and Bayesian optimization are applied for efficient hyperparameter tuning. Experiments on logging data from 41 wells in the B Basin, Chad, show that GC-TSGAN outperforms baseline models including RF, XGBoost, LSTM, and ANN across RMSE, MAE, and R². Results confirm that the proposed model achieves high-precision log curve reconstruction under complex geological conditions, providing a reliable data foundation for geological modeling and reservoir evaluation.\u0026nbsp;\u003c/p\u003e","manuscriptTitle":"Geology-Constrained Time Series Generative Adversarial Network for Well Log Curve Reconstruction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-07 07:27:31","doi":"10.21203/rs.3.rs-7568898/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":"8145aa5c-97f1-46c4-853b-2370972cb322","owner":[],"postedDate":"October 7th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":55777611,"name":"Physical sciences/Mathematics and computing"},{"id":55777612,"name":"Earth and environmental sciences/Solid earth sciences"}],"tags":[],"updatedAt":"2026-02-09T09:28:39+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-07 07:27:31","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7568898","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7568898","identity":"rs-7568898","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}