Conditional Generative Adversarial Networks for Subsurface Scenario-Based Uncertainty

preprint OA: closed
Full text JSON View at publisher
AI-generated deep summary by claude@2026-07, 2026-07-03 · read from full text

The paper proposes a conditional Wasserstein GAN with gradient penalty (WGAN-GP) to quantify scenario-based uncertainty in subsurface modeling, using a workflow that conditions on continuous geological labels such as object orientation, proportion, and width. It trains the model with conditional batch normalization and a projection discriminator so that label conditioning is learned implicitly rather than via explicit conditioning-loss terms, aiming for stable training and simpler parameter tuning. The method is demonstrated on a 2D synthetic channel reservoir and integrated into an ES-MDA data assimilation framework to condition well locations and produce conditioning labels, with quantitative/qualitative checks showing accurate reproduction and interpolation of geological parameters while maintaining geological consistency and realization-based uncertainty. The main caveat stated is that scenario-based uncertainty is computationally time-consuming in traditional iterative approaches, and the paper focuses on a synthetic 2D case rather than broader real-world validation. The paper does not explicitly discuss endometriosis or adenomyosis; it was included in the corpus via a keyword match in the upstream search index.

Read from the paper's body, not the abstract. Not a substitute for reading the paper. No clinical advice. How this works

Full text 31,022 characters · extracted from preprint-html · click to expand
Conditional Generative Adversarial Networks for Subsurface Scenario-Based Uncertainty | 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 Conditional Generative Adversarial Networks for Subsurface Scenario-Based Uncertainty Ahmed Merzoug, Michael Pyrcz This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7801111/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 Subsurface modeling workflows are critical for multi-million-dollar decisions in various subsurface resources, yet they are significantly impacted by inherent uncertainties. While realization-based uncertainty is commonly addressed, scenario-based uncertainty, which accounts for different conceptual geological models and their parameters, is often overlooked due to its time-consuming and iterative nature. Recently, generative artificial intelligence (GenAI) models, such as variational autoencoders (VAEs), generative adversarial networks (GANs), and diffusion models, have shown promise in subsurface modeling and history matching, primarily for realization-based uncertainty quantification. However, their application to scenario-based uncertainty remains limited, often relying on modifications to loss functions that introduce training instabilities. We propose a novel workflow for quantifying scenario-based uncertainty in subsurface modeling using a conditional Wasserstein generative adversarial network with a gradient penalty (WGAN-GP), integrated with conditional batch normalization and a projection discriminator. Our approach implicitly learns label conditioning, eliminating the need for explicit conditioning loss terms and promoting more stable training, and simpler parameter tuning. The proposed model supports multiple continuous conditioning labels, including object orientation, proportion, and width, and employs a trigonometric approach for parameterizing orientation. We demonstrate our workflow on a 2D synthetic channel reservoir, incorporating it into a data assimilation framework using Ensemble Smoother Multiple Data Assimilation (ES-MDA) to condition well locations and derive conditioning labels. Quantitative and qualitative checks confirm the model's ability to accurately reproduce and interpolate various geological model parameters, while maintaining geological consistency and realization-based uncertainty. subsurface modeling conditional generative adversarial networks scenario-based uncertainty Full Text Additional Declarations The authors declare no competing interests. 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-7801111","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":526071475,"identity":"dcae1adb-d5e4-426d-81e6-4829d49933b6","order_by":0,"name":"Ahmed Merzoug","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIiWNgGAWjYDADfgQzgUgtkg3MpGoxOECsFv5ph499/FFx2G7zjfyDj3lq6hj42XMM8GqRuJ2WPEPizOHkbTeSmQ1nHDvMINnzBr8Whts5xgyGbYeTzW4ks0l8YDvAYHCDgC3yt/M/MyQCtRjPSGb/kfCvjsGekBaD2znMDAfbDtsZSCSzMXxsY2YwkCCgxfB2mjFjw5n0BIkzj40lZ/Yd5pE486wArxa528mPGX9UWNvztyc+/MzzrU6Ovz15A14tMJDYAGXwEKUcBOyJVjkKRsEoGAUjDwAAbTRGpPOkdFYAAAAASUVORK5CYII=","orcid":"","institution":"The University of Texas at Austin","correspondingAuthor":true,"prefix":"","firstName":"Ahmed","middleName":"","lastName":"Merzoug","suffix":""},{"id":526071476,"identity":"977e1b78-778d-4815-9985-ddf4ee04c42e","order_by":1,"name":"Michael Pyrcz","email":"","orcid":"","institution":"The University of Texas at Austin","correspondingAuthor":false,"prefix":"","firstName":"Michael","middleName":"","lastName":"Pyrcz","suffix":""}],"badges":[],"createdAt":"2025-10-07 15:50:22","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7801111/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7801111/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93101401,"identity":"bb9934b8-336b-4e28-830f-11f3e98d9698","added_by":"auto","created_at":"2025-10-09 05:19:23","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3153827,"visible":true,"origin":"","legend":"","description":"","filename":"AhmedScenarioCGANpaperv31.docx","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/32d53e9c949b28ad8ed0584e.docx"},{"id":93101995,"identity":"2bb677b9-928c-4dcd-a758-b5696c59f156","added_by":"auto","created_at":"2025-10-09 05:27:23","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":342,"visible":true,"origin":"","legend":"","description":"","filename":"rs7801111.json","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/63302a46ba6e79cf7bc14b33.json"},{"id":93101393,"identity":"7ef7a1ac-f2c6-4189-8f98-2bee7b8ca1dd","added_by":"auto","created_at":"2025-10-09 05:19:23","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":155271,"visible":true,"origin":"","legend":"","description":"","filename":"rs78011110enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/d095f058fca341896d833a84.xml"},{"id":93101994,"identity":"0511ec56-b402-49ee-912c-707a4cf72647","added_by":"auto","created_at":"2025-10-09 05:27:23","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":45293,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/916645eca3df1e8b5c546b22.png"},{"id":93101997,"identity":"d7e5b95d-a53a-404e-94ad-73fc7af2a92e","added_by":"auto","created_at":"2025-10-09 05:27:23","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":142077,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/dfdbf35902e3f6039ab2fcf7.png"},{"id":93101395,"identity":"05080804-eddb-4aa0-9cd5-a64bb3fda97c","added_by":"auto","created_at":"2025-10-09 05:19:23","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":31050,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/50365dd989dd86215bdbe142.png"},{"id":93101996,"identity":"5f383b6d-68d7-430e-8b65-daf370c053ec","added_by":"auto","created_at":"2025-10-09 05:27:23","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":134851,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/04cb6d64720a5cff4cb5e05b.png"},{"id":93101998,"identity":"ef89b487-fa59-467d-8d4e-8ef07b9c7de5","added_by":"auto","created_at":"2025-10-09 05:27:23","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":90346,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/fcd3af3934eae928b58ca8b1.png"},{"id":93101412,"identity":"88388cfa-01ce-4ed0-8e01-731560a571c0","added_by":"auto","created_at":"2025-10-09 05:19:23","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91804,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/65cbbe05f4719698082968ea.png"},{"id":93101411,"identity":"09fe1a44-fd5b-4758-bc46-6d8b04b43741","added_by":"auto","created_at":"2025-10-09 05:19:23","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":273596,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage15.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/b625322e0aa11d38581c8ede.png"},{"id":93101396,"identity":"22d0eeba-9f12-4d5d-9add-9e61f6846f91","added_by":"auto","created_at":"2025-10-09 05:19:23","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":268471,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage16.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/ccbcd4b42bbc02db37c70247.png"},{"id":93101999,"identity":"a04ef79c-64ef-4862-879b-94783ff505ad","added_by":"auto","created_at":"2025-10-09 05:27:23","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":159653,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage17.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/5bdb212746c2b826174190cd.png"},{"id":93101398,"identity":"a2a22acf-0c69-42d4-b69d-334258ab0ae8","added_by":"auto","created_at":"2025-10-09 05:19:23","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":83948,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage18.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/9e2a45941600e383eaebd11f.png"},{"id":93101422,"identity":"26a7bd33-f6ba-4a67-9281-14311ecc979b","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":85656,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage19.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/ee4e90663854500b9cefebb8.png"},{"id":93101410,"identity":"7fe7ee12-077f-4a90-9b4f-e452579007d9","added_by":"auto","created_at":"2025-10-09 05:19:23","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":131602,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/d028d63bb590150ca2c2e9fa.png"},{"id":93101405,"identity":"da101155-20b7-4c51-bb9f-43cf7da3edd3","added_by":"auto","created_at":"2025-10-09 05:19:23","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":257975,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage20.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/601d0b206c63039309561d29.png"},{"id":93101400,"identity":"010400a3-29bc-4324-a8df-528cf84a5818","added_by":"auto","created_at":"2025-10-09 05:19:23","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":294531,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage21.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/68646cb2a53eb33ec562e540.png"},{"id":93101416,"identity":"cbb804f2-b992-46f9-b207-f299f54b6f6e","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":137370,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/d82ff96105a5ef35df9082d1.png"},{"id":93101436,"identity":"4b71452f-b5fe-4106-aea6-80997b60e6b6","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":114039,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/1c69bd0d6c734bf812879a16.png"},{"id":93101417,"identity":"8a0fc8ad-d30f-4bc0-a4c2-68958c834c2f","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":122563,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/e25a85894b02a7adbdf2bc60.png"},{"id":93101440,"identity":"b6ded0a6-31f8-4123-ac42-b390aa3b0588","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":115501,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/8997401ee4469fe42d9337bf.png"},{"id":93101402,"identity":"f6e8fcef-b579-427f-b27e-dd4d669ecd5e","added_by":"auto","created_at":"2025-10-09 05:19:23","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":84780,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/32f734293347c320e5987a5d.png"},{"id":93101404,"identity":"49b5645a-648c-4a27-a263-593bdc7dec67","added_by":"auto","created_at":"2025-10-09 05:19:23","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":167470,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/b027fcb1803b399fe23452e3.png"},{"id":93101407,"identity":"0d00751a-77a9-449e-b2b3-daeb69ae4ab1","added_by":"auto","created_at":"2025-10-09 05:19:23","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":226870,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/899993a6b88e75a3cafb217f.png"},{"id":93101406,"identity":"7518c88d-cf6e-4699-ad92-fbca7f959698","added_by":"auto","created_at":"2025-10-09 05:19:23","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13495,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/7db93388fd588d701b487948.png"},{"id":93101424,"identity":"b4edb215-475d-47af-8a0f-8cea947e2459","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35121,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/5a57f726e6069f62075d6cdc.png"},{"id":93101437,"identity":"c42aba92-4158-4399-b86b-e25773576fd8","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7249,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/99db86c5ee443ee582699fe1.png"},{"id":93102004,"identity":"7b9a4adb-5152-42de-bd1f-eb63fe684bc7","added_by":"auto","created_at":"2025-10-09 05:27:24","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30851,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/4512bb24bb118998620d05c1.png"},{"id":93102006,"identity":"912594d2-cfd5-4418-8caf-cf313494bc87","added_by":"auto","created_at":"2025-10-09 05:27:24","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":26907,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/ffb95acc8eb529735cb94c23.png"},{"id":93101414,"identity":"fc982be8-be77-4e19-93c3-1d3e90c4643d","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27511,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/e5eb4d12e3961e2d70315bd5.png"},{"id":93101413,"identity":"dc311335-c733-41b2-8e5c-f13408199765","added_by":"auto","created_at":"2025-10-09 05:19:23","extension":"png","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":50633,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage15.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/414c483588d2666542857c1f.png"},{"id":93101408,"identity":"8765573c-8ff2-4240-9e73-507c2f21c499","added_by":"auto","created_at":"2025-10-09 05:19:23","extension":"png","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":61914,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage16.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/888e6ef5fa939d40ce3d5be9.png"},{"id":93101426,"identity":"e1c8ef54-8735-4760-9c5e-66c084f35e34","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37055,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage17.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/21b3cc63f2684d9e9254d946.png"},{"id":93101433,"identity":"c5c7ff96-c108-40a2-b1c9-e7d19d10fec6","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20335,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage18.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/d874390b2ff1b671d2781d43.png"},{"id":93101425,"identity":"b07caf3f-5e15-447c-b32e-a47f0851d887","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21343,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage19.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/e040264574922ba35b0bb3b1.png"},{"id":93101423,"identity":"c8164f6a-a1f4-4a95-b3eb-16ba0161ddbf","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40968,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/52801aa3293e36104b888f1a.png"},{"id":93102121,"identity":"a7318ad2-fef6-405f-bf42-fc93190bc1ad","added_by":"auto","created_at":"2025-10-09 05:35:24","extension":"png","order_by":36,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":46812,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage20.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/5eb7976963373a718b6f34fd.png"},{"id":93101415,"identity":"f38452c0-85e0-4f19-89e1-529d83f1923b","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":37,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":66306,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage21.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/a659213010c2d989232fc35c.png"},{"id":93101428,"identity":"4edc125d-4373-4153-b931-f4949ddbcfa8","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":38,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35256,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/57e108ce739897d174426145.png"},{"id":93102002,"identity":"78204c5d-5b37-4013-b6a2-27088740873a","added_by":"auto","created_at":"2025-10-09 05:27:24","extension":"png","order_by":39,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27466,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/ce105ecd0215d4a4b5698137.png"},{"id":93101420,"identity":"6bbbc5f9-5ecc-442e-a04f-87a217a9e177","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":40,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32287,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/a9871a67a6fb2596614b0644.png"},{"id":93101432,"identity":"f83ee57c-d12a-493c-90ed-b9188a354d50","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":41,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":26093,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/eb46d467d1a5574a7eef2296.png"},{"id":93101438,"identity":"cd85ae57-df30-40cc-b5cb-1d46d4f99872","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"png","order_by":42,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19112,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/81f6a9c7573ccc80a3c499fe.png"},{"id":93102003,"identity":"d879c9ef-9afa-4f42-b026-9a06b7162ceb","added_by":"auto","created_at":"2025-10-09 05:27:24","extension":"png","order_by":43,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41321,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/72b83c35b1fbe24ffbd2316c.png"},{"id":93102000,"identity":"4d47bd0c-bfd6-44f7-ab9e-9af38572993e","added_by":"auto","created_at":"2025-10-09 05:27:24","extension":"png","order_by":44,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39317,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/ad9f3568855e86083ba0f36b.png"},{"id":93101439,"identity":"11fcc6ed-22d5-4989-972b-faf8682a21a3","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"xml","order_by":45,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":153950,"visible":true,"origin":"","legend":"","description":"","filename":"rs78011110structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/346fa79b8297e9cb2c964b86.xml"},{"id":93101434,"identity":"ef6c4d95-0072-4d17-827d-cc963da13668","added_by":"auto","created_at":"2025-10-09 05:19:24","extension":"html","order_by":46,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":168946,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1/298feb699cf7f9ccb0646751.html"},{"id":93102688,"identity":"74ce3b9a-644a-4075-81e0-0bd1544b0494","added_by":"auto","created_at":"2025-10-09 05:43:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1836324,"visible":true,"origin":"","legend":"","description":"","filename":"AhmedScenarioCGANpaperv31.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7801111/v1_covered_f433a39c-d1ff-440c-bec1-90e3579d137b.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eConditional Generative Adversarial Networks for Subsurface Scenario-Based Uncertainty\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"The University of Texas at Austin","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"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":"subsurface modeling, conditional generative adversarial networks, scenario-based uncertainty","lastPublishedDoi":"10.21203/rs.3.rs-7801111/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7801111/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSubsurface modeling workflows are critical for multi-million-dollar decisions in various subsurface resources, yet they are significantly impacted by inherent uncertainties. While realization-based uncertainty is commonly addressed, scenario-based uncertainty, which accounts for different conceptual geological models and their parameters, is often overlooked due to its time-consuming and iterative nature. Recently, generative artificial intelligence (GenAI) models, such as variational autoencoders (VAEs), generative adversarial networks (GANs), and diffusion models, have shown promise in subsurface modeling and history matching, primarily for realization-based uncertainty quantification. However, their application to scenario-based uncertainty remains limited, often relying on modifications to loss functions that introduce training instabilities.\u003c/p\u003e\u003cp\u003eWe propose a novel workflow for quantifying scenario-based uncertainty in subsurface modeling using a conditional Wasserstein generative adversarial network with a gradient penalty (WGAN-GP), integrated with conditional batch normalization and a projection discriminator. Our approach implicitly learns label conditioning, eliminating the need for explicit conditioning loss terms and promoting more stable training, and simpler parameter tuning. The proposed model supports multiple continuous conditioning labels, including object orientation, proportion, and width, and employs a trigonometric approach for parameterizing orientation. We demonstrate our workflow on a 2D synthetic channel reservoir, incorporating it into a data assimilation framework using Ensemble Smoother Multiple Data Assimilation (ES-MDA) to condition well locations and derive conditioning labels. Quantitative and qualitative checks confirm the model's ability to accurately reproduce and interpolate various geological model parameters, while maintaining geological consistency and realization-based uncertainty.\u003c/p\u003e","manuscriptTitle":"Conditional Generative Adversarial Networks for Subsurface Scenario-Based Uncertainty","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-09 05:19:18","doi":"10.21203/rs.3.rs-7801111/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":"be784709-9c87-43f1-a421-1e2434d50e45","owner":[],"postedDate":"October 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-10-09T05:19:18+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-09 05:19:18","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7801111","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7801111","identity":"rs-7801111","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.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00