Adversarial Augmented Fields for Efficient Geophysical Analysis

Adversarial Augmented Fields for Efficient Geophysical Analysis | 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 Adversarial Augmented Fields for Efficient Geophysical Analysis Xiaoming Cao, Zhengkui Zeng, Shike Hu, Aiman Mukhtar, KaiMing Wu, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4455025/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 and comprehensive data remain critical for modeling and understanding Earth's complex systems, directly influencing weather forecasting, climate change predictions, and disaster management strategies. However, the scarcity of data, particularly for rare or extreme events, and the inherent imbalance in datasets pose significant challenges to developing robust predictive models. These issues highlight the need for effective data augmentation techniques, a domain where existing methodologies remain underexplored for geophysical data. Addressing this gap, this study introduces a data augmentation framework for geophysical fields, employing a Generative Adversarial Network (GAN) architecture. Our GAN's generator utilizes a UNet architecture combined with depthwise separable convolutions to capture multi-scale spatial hierarchies while also reducing computational cost. The discriminator is enhanced with residual attention mechanisms to distinguish simulations from observations. Beyond the standard GAN loss, a Mean Absolute Error (MAE) regularization term is incorporated to ensure the generated data fields are distinguishable from the original dataset, promoting diversity and enhancing model training. Our approach has been validated through its application to downstream tasks including downscaling, extrapolation, and imputation. It achieves outstanding performance improvements, reducing the Mean Absolute Percentage Error (MAPE) by 25.1%, 19.6%, and 27.4% across these tasks, respectively. Earth and environmental sciences/Climate sciences/Atmospheric science Earth and environmental sciences/Climate sciences/Ocean sciences generative adversarial networks data augmentation UNet residual connection attention mechanism downscaling extrapolation imputation 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-4455025","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":310652728,"identity":"d4c94161-0dde-453e-8b96-b6959cb3929f","order_by":0,"name":"Xiaoming Cao","email":"","orcid":"","institution":"Hubei University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Xiaoming","middleName":"","lastName":"Cao","suffix":""},{"id":310652729,"identity":"d805577a-b3ff-4322-a2bf-b78410b4ad15","order_by":1,"name":"Zhengkui Zeng","email":"","orcid":"","institution":"Hefei Institutes of Physical Science，Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Zhengkui","middleName":"","lastName":"Zeng","suffix":""},{"id":310652730,"identity":"767846a9-a0c2-42d7-a910-e9ba5e387a68","order_by":2,"name":"Shike Hu","email":"","orcid":"","institution":"Hubei University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Shike","middleName":"","lastName":"Hu","suffix":""},{"id":310652731,"identity":"fa27ce0f-f63f-4d51-a8d0-6cbd7c7389d9","order_by":3,"name":"Aiman Mukhtar","email":"","orcid":"","institution":"International Research Institute for Steel Technology, Wuhan University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Aiman","middleName":"","lastName":"Mukhtar","suffix":""},{"id":310652732,"identity":"252d49bd-cd30-45fa-bb1a-94f44bfcbb9d","order_by":4,"name":"KaiMing Wu","email":"","orcid":"","institution":"International Research Institute for Steel Technology, Wuhan University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"KaiMing","middleName":"","lastName":"Wu","suffix":""},{"id":310652733,"identity":"d3f5f303-45cc-4ab7-b5a0-b513322bcb38","order_by":5,"name":"Liyuan Gu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxklEQVRIiWNgGAWjYDACdgaGw38qbOTY2JsPEKmFmYHxAc+ZNGM+nmMJRGthNuBtO5Q4TyJHgTgd8s48ZhISbAfS2xhyGBh+VGwjrMXwMFCLAc+d3DaGswcYe87cJkJLM1BLgsSz3DbGvgRmxjZitRwwOJzOxsxjQJwWeWYeY8OGhMMJbGzEajFgZit8zHAgzbCNhy3hIFF+kW9v3nCY8Z+NvPz8xwcf/KggxpYDHAZwzgHC6kG2NLA/IErhKBgFo2AUjGAAALOwOWezXq8PAAAAAElFTkSuQmCC","orcid":"","institution":"Hubei University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Liyuan","middleName":"","lastName":"Gu","suffix":""}],"badges":[],"createdAt":"2024-05-21 13:03:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4455025/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4455025/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94829077,"identity":"b488004d-db9a-482b-af8a-2f1748bd72b9","added_by":"auto","created_at":"2025-10-31 07:02:33","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1212101,"visible":true,"origin":"","legend":"","description":"","filename":"ugan.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4455025/v1_covered_30a0f03b-b6b7-4b26-bf5b-d41489e16633.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Adversarial Augmented Fields for Efficient Geophysical Analysis","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":"generative adversarial networks, data augmentation, UNet, residual connection, attention mechanism, downscaling, extrapolation, imputation","lastPublishedDoi":"10.21203/rs.3.rs-4455025/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4455025/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate and comprehensive data remain critical for modeling and understanding Earth's complex systems, directly influencing weather forecasting, climate change predictions, and disaster management strategies. However, the scarcity of data, particularly for rare or extreme events, and the inherent imbalance in datasets pose significant challenges to developing robust predictive models. These issues highlight the need for effective data augmentation techniques, a domain where existing methodologies remain underexplored for geophysical data. Addressing this gap, this study introduces a data augmentation framework for geophysical fields, employing a Generative Adversarial Network (GAN) architecture. Our GAN's generator utilizes a UNet architecture combined with depthwise separable convolutions to capture multi-scale spatial hierarchies while also reducing computational cost. The discriminator is enhanced with residual attention mechanisms to distinguish simulations from observations. Beyond the standard GAN loss, a Mean Absolute Error (MAE) regularization term is incorporated to ensure the generated data fields are distinguishable from the original dataset, promoting diversity and enhancing model training. Our approach has been validated through its application to downstream tasks including downscaling, extrapolation, and imputation. It achieves outstanding performance improvements, reducing the Mean Absolute Percentage Error (MAPE) by 25.1%, 19.6%, and 27.4% across these tasks, respectively.\u003c/p\u003e","manuscriptTitle":"Adversarial Augmented Fields for Efficient Geophysical Analysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-05 04:36:57","doi":"10.21203/rs.3.rs-4455025/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":"15931dd2-504e-4da9-bdef-ed8a256b2764","owner":[],"postedDate":"June 5th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":32830284,"name":"Earth and environmental sciences/Climate sciences/Atmospheric science"},{"id":32830285,"name":"Earth and environmental sciences/Climate sciences/Ocean sciences"}],"tags":[],"updatedAt":"2025-10-31T07:01:17+00:00","versionOfRecord":[],"versionCreatedAt":"2024-06-05 04:36:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4455025","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4455025","identity":"rs-4455025","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}