TOC Prediction from Well Logs Using Gradient Boosting and Neural Network in the Santos Basin, SE Brazil | 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 TOC Prediction from Well Logs Using Gradient Boosting and Neural Network in the Santos Basin, SE Brazil Bernardo S. Chede, Andre L. Belem, Victor Carreira, Ulrich G. Wortmann, and 8 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7695412/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 Accurate prediction of total organic carbon (TOC) in subsurface formations is crucial for evaluating source rock quality and optimizing exploration strategies in hydrocarbon prolific basins. Traditional methods like the ΔlogR technique often require local calibration and may fail to capture the non-linear relationships between well-log parameters and TOC, leading to inaccuracies. This study applies three machine learning (ML) models—Gradient Boosting Decision Trees (GBDT), Extreme Gradient Boosting (XGBoost), and Multi-Layer Perceptron (MLP)—to predict TOC from well-log data in the Santos Basin, Brazil's largest offshore basin. We employed robust data preprocessing techniques, including outlier detection using Density-Based Spatial Clustering and feature reduction through Principal Component Analysis. Bayesian optimization was utilized for hyperparameter tuning to enhance model performance. The results indicate that all ML models outperformed the traditional ΔlogR method, with GBDT achieving the highest prediction accuracy. This study demonstrates the potential of ML models in capturing complex, non-linear relationships in geophysical data and highlights the challenges of generalizing these models across diverse geological settings. The findings contribute to improved TOC estimation and can enhance exploration strategies in similar geological contexts. Total organic carbon Gradient Boosting Neural Network Supervised Machine learning Unsupervised Machine learning Santos Basin Full Text Additional Declarations No competing interests reported. Supplementary Files SubtitleSupplmentaryFigures.docx Supplementary.docx SupplementaryFigure4.png SupplementaryFigure1.png SupplementaryFigure3.png SupplementaryFigure2.png 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-7695412","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":540334574,"identity":"ed8f70d4-f049-416a-b69e-c3aff336065d","order_by":0,"name":"Bernardo S. Chede","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwklEQVRIiWNgGAWjYBACAwYGNhCSY2NIYGCosAGRRGoxBms5k0aClsQGorWYszc/e/ChzCa9jz2BTeJAAkOeeQMBLZY9x8wNZ5xLy23jeQDWUixzgJDDbuSwSfO2Hc5tk0hgk/74gyFxBkG/3H/DJv237X86mwTEYURoucHDJs3YdiCBeC2WPWlmkj3nkg3beB42WxxIkCiWIKTFnP3wM4kfZXby8u3JB28cSLDJI6gFCTA2AAlSNIyCUTAKRsEowAkAkKw8QoBNGfYAAAAASUVORK5CYII=","orcid":"","institution":"Universidade Federal Fluminense","correspondingAuthor":true,"prefix":"","firstName":"Bernardo","middleName":"S.","lastName":"Chede","suffix":""},{"id":540334575,"identity":"1e3f0d21-47d4-437f-9560-10664be7b044","order_by":1,"name":"Andre L. Belem","email":"","orcid":"","institution":"Universidade Federal Fluminense","correspondingAuthor":false,"prefix":"","firstName":"Andre","middleName":"L.","lastName":"Belem","suffix":""},{"id":540334576,"identity":"ab06defa-690f-4363-97c3-a65c904a85a7","order_by":2,"name":"Victor Carreira","email":"","orcid":"","institution":"Universidade Federal Fluminense","correspondingAuthor":false,"prefix":"","firstName":"Victor","middleName":"","lastName":"Carreira","suffix":""},{"id":540334577,"identity":"5bf43847-fe95-453d-847b-e5b77e9e0397","order_by":3,"name":"Ulrich G. Wortmann","email":"","orcid":"","institution":"University of Toronto","correspondingAuthor":false,"prefix":"","firstName":"Ulrich","middleName":"G.","lastName":"Wortmann","suffix":""},{"id":540334578,"identity":"aad46d3f-5b5a-4b5d-9f40-65cce1ac1c89","order_by":4,"name":"Luiz H. Cordeiro","email":"","orcid":"","institution":"Universidade Federal Fluminense","correspondingAuthor":false,"prefix":"","firstName":"Luiz","middleName":"H.","lastName":"Cordeiro","suffix":""},{"id":540334579,"identity":"b9d4bf03-de33-41ea-aa5a-b82297356913","order_by":5,"name":"Kristoffer A.T. Hallam","email":"","orcid":"","institution":"Universidade Federal Fluminense","correspondingAuthor":false,"prefix":"","firstName":"Kristoffer","middleName":"A.T.","lastName":"Hallam","suffix":""},{"id":540334580,"identity":"407964f0-ee30-4766-925e-03f56ba00e96","order_by":6,"name":"Igor M. Venancio","email":"","orcid":"","institution":"Universidade Federal Fluminense","correspondingAuthor":false,"prefix":"","firstName":"Igor","middleName":"M.","lastName":"Venancio","suffix":""},{"id":540334581,"identity":"8ae145dc-5dd0-4382-a17a-8778f5cc233a","order_by":7,"name":"Pedro V.A. Affonso","email":"","orcid":"","institution":"Universidade Federal Fluminense","correspondingAuthor":false,"prefix":"","firstName":"Pedro","middleName":"V.A.","lastName":"Affonso","suffix":""},{"id":540334582,"identity":"29a3b1a2-74a5-4245-8e70-6c71243e249f","order_by":8,"name":"Rodrigo L. Sobrinho","email":"","orcid":"","institution":"Universidade Federal Fluminense","correspondingAuthor":false,"prefix":"","firstName":"Rodrigo","middleName":"L.","lastName":"Sobrinho","suffix":""},{"id":540334583,"identity":"bdcbadaf-f1e1-4f75-bf6a-71acc168873f","order_by":9,"name":"Lara P.C. Herculano","email":"","orcid":"","institution":"Universidade Federal Fluminense","correspondingAuthor":false,"prefix":"","firstName":"Lara","middleName":"P.C.","lastName":"Herculano","suffix":""},{"id":540334584,"identity":"f3e068c9-dee5-4059-8c36-850e488ad711","order_by":10,"name":"Andre L.D. Spigolon","email":"","orcid":"","institution":"Centro de Pesquisas e Desenvolvimento Leopoldo Americo Miguez de Mello","correspondingAuthor":false,"prefix":"","firstName":"Andre","middleName":"L.D.","lastName":"Spigolon","suffix":""},{"id":540334586,"identity":"5a23e1be-9ed1-4cf1-8fb6-b8dadd0695e8","order_by":11,"name":"Ana Luiza S. Albuquerque","email":"","orcid":"","institution":"Universidade Federal Fluminense","correspondingAuthor":false,"prefix":"","firstName":"Ana","middleName":"Luiza S.","lastName":"Albuquerque","suffix":""}],"badges":[],"createdAt":"2025-09-23 14:23:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7695412/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7695412/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95348675,"identity":"c4b9fe41-1d0e-40a2-8f83-b0b15be7c48e","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1140802,"visible":true,"origin":"","legend":"","description":"","filename":"ChedeetalManuscriptwithfigstables.docx","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/b4b1e7e15022737b000efe39.docx"},{"id":95348673,"identity":"c160a636-e22a-4edb-a70f-0a1cc64b4e9a","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11793,"visible":true,"origin":"","legend":"","description":"","filename":"48e72d3b2f004901acb86ccda9ed7e94.json","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/1b59b54664771fd75bd941dc.json"},{"id":95348679,"identity":"273ac01d-ecd3-47d6-81cc-36e04fd4dc29","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5936,"visible":true,"origin":"","legend":"","description":"","filename":"SubtitleSupplmentaryFigures.docx","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/1c56a8411f1999ed652d03d8.docx"},{"id":95348674,"identity":"011d4709-164b-46f9-a873-0c97f2cb73d7","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"docx","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20305,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementary.docx","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/687d753a92e313b202d3876e.docx"},{"id":95348681,"identity":"46fa89cf-9413-44b6-a844-9518ce5c9c43","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":776811,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFigure1.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/235f82501aafd3b6f08b01ab.png"},{"id":95348686,"identity":"598f8c8a-29cd-42f4-b280-df62e596bcb2","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":565468,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFigure2.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/876e9797c75db982959876cb.png"},{"id":95348699,"identity":"20980b4b-7355-4f16-97ac-9c0c525b9773","added_by":"auto","created_at":"2025-11-07 04:07:27","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":548568,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFigure3.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/0db8c74d3997c9efa6bc1bbc.png"},{"id":95348702,"identity":"dadf7365-cee3-4ae6-b465-f7a73aa6efe2","added_by":"auto","created_at":"2025-11-07 04:07:27","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":538439,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFigure4.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/72bd5a77321863d63f92248b.png"},{"id":95524388,"identity":"69714532-cb91-47f0-a731-9bf616f8f87d","added_by":"auto","created_at":"2025-11-10 10:02:41","extension":"xml","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":174166,"visible":true,"origin":"","legend":"","description":"","filename":"48e72d3b2f004901acb86ccda9ed7e941enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/de4b422c204812fe4e330d5f.xml"},{"id":95348677,"identity":"95b83373-ac8d-413a-82ee-2dca7bd8cf00","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"gif","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":972,"visible":true,"origin":"","legend":"","description":"","filename":"Equation16.gif","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/0a275a74c768318d9b8c1323.gif"},{"id":95348684,"identity":"f1d489fe-c93e-41ef-99a7-ca55f3d04a6d","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"gif","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":951,"visible":true,"origin":"","legend":"","description":"","filename":"Equation2.gif","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/e1c0330d5ff2d735b09fab84.gif"},{"id":95525968,"identity":"7bd9b4e1-ebd2-4982-b5f1-97e20011ad98","added_by":"auto","created_at":"2025-11-10 10:05:58","extension":"gif","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":968,"visible":true,"origin":"","legend":"","description":"","filename":"Equation24.gif","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/2f2cadaf87fb42fa86043985.gif"},{"id":95348688,"identity":"d840c034-c868-4b79-9eb0-d8cc06d1dd8f","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"gif","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":963,"visible":true,"origin":"","legend":"","description":"","filename":"Equation33.gif","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/21ec12a796b3b53be2bb0ae5.gif"},{"id":95348697,"identity":"5a12bf9b-72c3-468d-b237-d035f926b851","added_by":"auto","created_at":"2025-11-07 04:07:27","extension":"gif","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":974,"visible":true,"origin":"","legend":"","description":"","filename":"Equation35.gif","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/2de6e236526eaaa3f838deae.gif"},{"id":95525516,"identity":"f83de2a5-b7ff-4361-9bf7-4e890fc703bb","added_by":"auto","created_at":"2025-11-10 10:05:11","extension":"gif","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":969,"visible":true,"origin":"","legend":"","description":"","filename":"Equation39.gif","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/7a2f3f49ff8f1d24af02240d.gif"},{"id":95348709,"identity":"2c24e25c-0102-4efb-a83e-0804f7c3492e","added_by":"auto","created_at":"2025-11-07 04:07:27","extension":"gif","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1012,"visible":true,"origin":"","legend":"","description":"","filename":"Equation41.gif","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/22c46ce2d8c8abedaced5f70.gif"},{"id":95525906,"identity":"e3cc6abf-e639-4d93-9676-22245dc51315","added_by":"auto","created_at":"2025-11-10 10:05:50","extension":"gif","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":967,"visible":true,"origin":"","legend":"","description":"","filename":"Equation9.gif","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/bf8a99b5acf7c060e905ae38.gif"},{"id":95525294,"identity":"04c29d28-4186-420a-b087-931534736a71","added_by":"auto","created_at":"2025-11-10 10:04:45","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":427767,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/39ab1282ad8c42fc734717ab.png"},{"id":95348690,"identity":"b26dcf60-4c63-4f56-ab07-1dad329af84e","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":74751,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/5dfa4b516675904bd3e84777.png"},{"id":95348689,"identity":"d09e0078-accd-49d4-a08e-3274422f9279","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":101245,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/4b2c1600e78b71e2d721d6fc.png"},{"id":95525092,"identity":"b3c1213c-8d53-4ed4-8faa-9e4eed15e415","added_by":"auto","created_at":"2025-11-10 10:04:14","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":38426,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/9700e0e6bb01b1000492801c.png"},{"id":95348703,"identity":"8c077f67-5cf2-4a47-8349-ed82a1054050","added_by":"auto","created_at":"2025-11-07 04:07:27","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":175541,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/948b13113141d9023f165ea2.png"},{"id":95524623,"identity":"cba96040-6607-42e8-8078-3653354b67b0","added_by":"auto","created_at":"2025-11-10 10:03:04","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":121939,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/90f04650399b094371f5154a.png"},{"id":95525943,"identity":"b6cd6786-bc69-4267-9b5e-49fe6dbf7f2b","added_by":"auto","created_at":"2025-11-10 10:05:54","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":143397,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/d48324211fad9c49a4342a0f.png"},{"id":95348708,"identity":"92add9d1-41a5-427b-b17a-d5d9091e1349","added_by":"auto","created_at":"2025-11-07 04:07:27","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":484,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineEquation16.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/35391d6081bfd78ffc9b6fb0.png"},{"id":95348707,"identity":"0f8e507b-4d8c-4efb-ac8f-2c21dbee4ab6","added_by":"auto","created_at":"2025-11-07 04:07:27","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":465,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineEquation2.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/09f28bf70a4ce01104fe8197.png"},{"id":95524051,"identity":"f1a00e38-6af4-4164-9504-5d3054c63b70","added_by":"auto","created_at":"2025-11-10 10:02:03","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":479,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineEquation24.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/6b9ded6f336bf6f83f4c5b03.png"},{"id":95348713,"identity":"da201b3d-d72e-4c17-b21a-1a8b1245cb37","added_by":"auto","created_at":"2025-11-07 04:07:27","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":473,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineEquation33.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/45212987cff8164d2060388f.png"},{"id":95348691,"identity":"8dde18b6-c33a-4597-81b7-1115f409d3ce","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":484,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineEquation35.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/c742be6c24341965b205a1cc.png"},{"id":95348720,"identity":"2f820608-3e6b-4fb3-96af-9158357cd107","added_by":"auto","created_at":"2025-11-07 04:07:28","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":491,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineEquation39.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/87c54ce9b0c484044557ee8d.png"},{"id":95348705,"identity":"7b7c22b2-63e5-4768-ab4a-6aae4cca1a58","added_by":"auto","created_at":"2025-11-07 04:07:27","extension":"png","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":511,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineEquation41.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/64b0b9da81a4cdf7b7185533.png"},{"id":95348716,"identity":"bb8cb053-0656-42cc-9eb3-8950f5c68699","added_by":"auto","created_at":"2025-11-07 04:07:27","extension":"png","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":479,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineEquation9.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/f4121dbd2fc38b2a10d2f564.png"},{"id":95348712,"identity":"bd5d988b-9087-4290-9e68-5f9a3aa0a938","added_by":"auto","created_at":"2025-11-07 04:07:27","extension":"png","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":82733,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/10fd92896c3f5b9e938f67f0.png"},{"id":95348694,"identity":"5fe6479f-c186-4c2a-81d4-83be6648c8f2","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"png","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":71798,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/6cd52cd92e8e8926071acef7.png"},{"id":95348698,"identity":"9bc1f94f-3b80-4b84-81b8-ea7a4c97b543","added_by":"auto","created_at":"2025-11-07 04:07:27","extension":"png","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30426,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/f7a836904c22cc09b226ec89.png"},{"id":95348700,"identity":"fd470aec-9504-4801-91b0-cc2ddf08197e","added_by":"auto","created_at":"2025-11-07 04:07:27","extension":"png","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14979,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/7a8d6bb386e88af0bd955cb1.png"},{"id":95348711,"identity":"d67aa55c-948d-438d-bd81-f2381d00f515","added_by":"auto","created_at":"2025-11-07 04:07:27","extension":"png","order_by":36,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":63661,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/720fb638d6506e29fc4dfe11.png"},{"id":95348701,"identity":"fd65ac8e-948a-46c5-8a79-6e6bb6372fa7","added_by":"auto","created_at":"2025-11-07 04:07:27","extension":"png","order_by":37,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":51535,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/bc51318fb184f1103d5cb5a0.png"},{"id":95348693,"identity":"1e8d3d82-64be-45d9-8c6f-e24bc4c6b442","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"png","order_by":38,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":50827,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/962bb854753455f99983fccb.png"},{"id":95348717,"identity":"bc473908-fa96-43d6-8200-5f6b8c12225f","added_by":"auto","created_at":"2025-11-07 04:07:28","extension":"xml","order_by":39,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":174610,"visible":true,"origin":"","legend":"","description":"","filename":"48e72d3b2f004901acb86ccda9ed7e941structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/34bed7659e38ff9e897299fa.xml"},{"id":95348710,"identity":"f8d783ea-1446-4068-bff4-ab1c685d5e10","added_by":"auto","created_at":"2025-11-07 04:07:27","extension":"html","order_by":40,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":186404,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/7df4f4f20ec22aeed8aac30e.html"},{"id":98947508,"identity":"737ca518-b7f9-4b49-9014-62aba54ba5a8","added_by":"auto","created_at":"2025-12-24 12:40:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1131248,"visible":true,"origin":"","legend":"","description":"","filename":"ChedeetalManuscriptwithfigstables.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1_covered_740304df-ff21-449b-b9a4-71fe6e327a5d.pdf"},{"id":95348678,"identity":"919aa229-1e13-4a95-a20a-c76cd2454125","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":5936,"visible":true,"origin":"","legend":"","description":"","filename":"SubtitleSupplmentaryFigures.docx","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/fe382cba35208cb82f54352c.docx"},{"id":95348680,"identity":"93de18e1-06bb-4368-88c1-e2a1895f68a3","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":20305,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementary.docx","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/95d27ac6ba7e9fc9d2c18583.docx"},{"id":95348676,"identity":"8a4794b3-9776-4eb2-830d-7e369ab63835","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"png","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":538439,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFigure4.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/cdf374b0622e8f0e1b2863a4.png"},{"id":95348692,"identity":"b959f277-f3d3-42f3-8d5d-8ac5b1648d61","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":776811,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFigure1.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/af4077579a5321dadfb7c356.png"},{"id":95525565,"identity":"37451378-c072-43e9-bce2-4b829ffb19f8","added_by":"auto","created_at":"2025-11-10 10:05:18","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":548568,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFigure3.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/c8a5cf5af2c2550eeb269acc.png"},{"id":95348695,"identity":"b062e6ee-3f29-4ab7-a629-e16a81f3c385","added_by":"auto","created_at":"2025-11-07 04:07:26","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":565468,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFigure2.png","url":"https://assets-eu.researchsquare.com/files/rs-7695412/v1/1e854123d7610adb97d46c50.png"}],"financialInterests":"No competing interests reported.","formattedTitle":"TOC Prediction from Well Logs Using Gradient Boosting and Neural Network in the Santos Basin, SE Brazil","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":"Total organic carbon, Gradient Boosting, Neural Network, Supervised Machine learning, Unsupervised Machine learning, Santos Basin","lastPublishedDoi":"10.21203/rs.3.rs-7695412/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7695412/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate prediction of total organic carbon (TOC) in subsurface formations is crucial for evaluating source rock quality and optimizing exploration strategies in hydrocarbon prolific basins. Traditional methods like the ΔlogR technique often require local calibration and may fail to capture the non-linear relationships between well-log parameters and TOC, leading to inaccuracies. This study applies three machine learning (ML) models\u0026mdash;Gradient Boosting Decision Trees (GBDT), Extreme Gradient Boosting (XGBoost), and Multi-Layer Perceptron (MLP)\u0026mdash;to predict TOC from well-log data in the Santos Basin, Brazil's largest offshore basin. We employed robust data preprocessing techniques, including outlier detection using Density-Based Spatial Clustering and feature reduction through Principal Component Analysis. Bayesian optimization was utilized for hyperparameter tuning to enhance model performance. The results indicate that all ML models outperformed the traditional ΔlogR method, with GBDT achieving the highest prediction accuracy. This study demonstrates the potential of ML models in capturing complex, non-linear relationships in geophysical data and highlights the challenges of generalizing these models across diverse geological settings. The findings contribute to improved TOC estimation and can enhance exploration strategies in similar geological contexts.\u003c/p\u003e","manuscriptTitle":"TOC Prediction from Well Logs Using Gradient Boosting and Neural Network in the Santos Basin, SE Brazil","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-07 04:07:21","doi":"10.21203/rs.3.rs-7695412/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":"7c2b7a25-0c93-42af-9314-80c99d0681f1","owner":[],"postedDate":"November 7th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-12-24T12:39:19+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-07 04:07:21","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7695412","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7695412","identity":"rs-7695412","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.