FluidZero: Mastering Diverse Tasks in Fluid Systems through a Single Generative Model

FluidZero: Mastering Diverse Tasks in Fluid Systems through a Single Generative Model | 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 FluidZero: Mastering Diverse Tasks in Fluid Systems through a Single Generative Model Haodong Feng, Haoren Zheng, Peiyan Hu, Hongyuan Liu, Chenglei Yu, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6881567/v3 This work is licensed under a CC BY 4.0 License Status: Posted Version 3 posted You are reading this latest preprint version Show more versions Abstract Fluid-Structure Interaction (FSI) is one of the important cornerstones of science and engineering, such as spacecraft, submersibles, and biomedicine, which are important to understand and optimize, involving four key tasks throughout history: prediction, parameter identification, design, and control. Although each task has made significant strides individually, current approaches remain fragmented; existing models are limited to their specific domains and lack the capability to generalize across different tasks. To overcome this issue while utilizing the correlation between tasks to improve the performance on each task, we propose FluidZero , a unified deep generative model that unifies four different tasks into a joint probabilistic distribution modeling task. The key advantage of FluidZero is that it facilitates cross-modal and cross-task interactions, enabling effective learning of causality laws between physical variables, and then enhancing performance on diverse tasks in the Fluid-Structure Interaction (FSI) system. We evaluate FluidZero in a FSI system, including simulation data and real-world measured data obtained through Particle Image Velocimetry (PIV). Moreover, the designed foil is directly transferred to real-world experiments through 3D printing. FluidZero shows better generalization capabilities, achieving superior performance even in Out-Of-Bound (OOB) situations and real-world applications. Artificial Intelligence and Machine Learning Cross-task model Fluid mechanics Generative model Fluid-structure interaction Full Text Additional Declarations The authors declare no competing interests. Supplementary Files Foundation5.pdf Cite Share Download PDF Status: Posted Version 3 posted You are reading this latest preprint version Show more versions 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-6881567","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":475366026,"identity":"7249b072-7d69-4905-b019-453e65c99a79","order_by":0,"name":"Haodong Feng","email":"","orcid":"","institution":"Key Laboratory of Coastal Environment and Resources of Zhejiang Province, School of Engineering, Westlake University","correspondingAuthor":false,"prefix":"","firstName":"Haodong","middleName":"","lastName":"Feng","suffix":""},{"id":475366027,"identity":"e9a4f1ff-51ef-4257-be12-8bb7f8069d8a","order_by":1,"name":"Haoren Zheng","email":"","orcid":"","institution":"School of Mathematics and Statistics, Nanjing University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Haoren","middleName":"","lastName":"Zheng","suffix":""},{"id":475366028,"identity":"63ccc1d5-3df1-477a-acb6-06d9d597863e","order_by":2,"name":"Peiyan Hu","email":"","orcid":"","institution":"Academy of Mathematics and Systems Science, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Peiyan","middleName":"","lastName":"Hu","suffix":""},{"id":475366029,"identity":"4b9861cc-b8cf-47dd-88db-d34bc43f26a8","order_by":3,"name":"Hongyuan Liu","email":"","orcid":"","institution":"Department of Electronic and Information Engineering, School of Engineering, Westlake University","correspondingAuthor":false,"prefix":"","firstName":"Hongyuan","middleName":"","lastName":"Liu","suffix":""},{"id":475366030,"identity":"aef3852f-3de7-41f7-adb1-f46afbc618c0","order_by":4,"name":"Chenglei Yu","email":"","orcid":"","institution":"Department of Artificial Intelligence, School of Engineering, Westlake University","correspondingAuthor":false,"prefix":"","firstName":"Chenglei","middleName":"","lastName":"Yu","suffix":""},{"id":475366031,"identity":"c354ce03-adb1-4868-8137-0d5a108b8651","order_by":5,"name":"Long Wei","email":"","orcid":"","institution":"Department of Artificial Intelligence, School of Engineering, Westlake University","correspondingAuthor":false,"prefix":"","firstName":"Long","middleName":"","lastName":"Wei","suffix":""},{"id":475366032,"identity":"340106ef-d6c4-4079-a00a-e2987cfd790b","order_by":6,"name":"Ruiqi Feng","email":"","orcid":"","institution":"Department of Artificial Intelligence, School of Engineering, Westlake University","correspondingAuthor":false,"prefix":"","firstName":"Ruiqi","middleName":"","lastName":"Feng","suffix":""},{"id":475366033,"identity":"267497b3-ced2-4d6d-8cbf-7d9355bc1816","order_by":7,"name":"Jinlong Duan","email":"","orcid":"","institution":"Institute of Mechanics, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Jinlong","middleName":"","lastName":"Duan","suffix":""},{"id":475366034,"identity":"4d58d469-01e3-4bcd-a9be-1cf9106603a7","order_by":8,"name":"Dixia Fan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/0lEQVRIiWNgGAWjYBAC9gYGBokEBgkGfjC3gMEAREng08JzAKpFEqiX4YABsVpADIMDRGthP3vwxsM2C3njG8mHP38wsDPmZ2A+eJuHwS4PpxaevGSLhDMShttupKVJHDBINpNsYEu25mFILsalxZ4hx0wioUKCcdvtHDOgw5htDA7wmEnzMBxIbMBlC/8boBYDCfvNs/M/fzhgUG9jf4D/G34tEhBbEjdI5zAAHXbYzICBh42AljfGIL8kz7j/zEzijMFxY4nDbMaWcwyS8Tgsx/Dmz7Y62/6ew48/VFRUG/a3Nz+88abCDqcWLIAZRBgQr34UjIJRMApGASYAALleUWQaTMSpAAAAAElFTkSuQmCC","orcid":"","institution":"Key Laboratory of Coastal Environment and Resources of Zhejiang Province, School of Engineering, Westlake University","correspondingAuthor":true,"prefix":"","firstName":"Dixia","middleName":"","lastName":"Fan","suffix":""},{"id":475366035,"identity":"bb2fb319-00a9-4c7d-8b3d-0746b064f3d8","order_by":9,"name":"Tailin Wu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA90lEQVRIiWNgGAWjYLCChAIJBn4wq4DBAERJ4FfPDNRiIMEg2QBkHzAgVgtIncEBYrUY3Mg/+OGBgUWe8Y3kw58/GNgZ8zMwH7zNw2CXh1tLMrME0GHFZjfS0iQOGCSbSTawJVvzMCQX49JidiOZAaQlcdvtHDOgw5htDA7wmEnzMBxIbMCthfkHSMvm2fmfPxwwqLexP8D/jZAWNrAtG6RzGIAOO2xmwMDDhleL/ZnHZhYgLTPuPzOTOGNw3FjiMJux5RyDZJxaJNsTH9/8UVGX2N9z+PGHiopqw/725oc33lTY4dSCBYAiChI9o2AUjIJRMArIBQCvAFPTXLtBHwAAAABJRU5ErkJggg==","orcid":"","institution":"Department of Artificial Intelligence, School of Engineering, Westlake University","correspondingAuthor":true,"prefix":"","firstName":"Tailin","middleName":"","lastName":"Wu","suffix":""}],"badges":[],"createdAt":"2025-06-12 14:57:24","currentVersionCode":3,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6881567/v3","doiUrl":"https://doi.org/10.21203/rs.3.rs-6881567/v3","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104397891,"identity":"cf8987b2-9358-414f-8f12-34ffb4f997d9","added_by":"auto","created_at":"2026-03-11 11:58:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":7706579,"visible":true,"origin":"","legend":"","description":"","filename":"Foundation4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6881567/v3_covered_b8a0bae3-2e3c-4bc3-aeae-18540ff0a558.pdf"},{"id":103534601,"identity":"2749b0e4-4acc-43ea-95de-433e0a34a9dc","added_by":"auto","created_at":"2026-02-26 18:02:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":8976921,"visible":true,"origin":"","legend":"","description":"","filename":"Foundation5.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6881567/v3/67623f7f50a7cd70d6045021.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"FluidZero: Mastering Diverse Tasks in Fluid Systems through a Single Generative Model","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Westlake University","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":"Cross-task model, Fluid mechanics, Generative model, Fluid-structure interaction","lastPublishedDoi":"10.21203/rs.3.rs-6881567/v3","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6881567/v3","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFluid-Structure Interaction (FSI) is one of the important cornerstones of science and engineering, such as spacecraft, submersibles, and biomedicine, which are important to understand and optimize, involving four key tasks throughout history: prediction, parameter identification, design, and control. \u0026nbsp;Although each task has made significant strides individually, current approaches remain fragmented; existing models are limited to their specific domains and lack the capability to generalize across different tasks. To overcome this issue while utilizing the correlation between tasks to improve the performance on each task, we propose \u003cstrong\u003eFluidZero\u003c/strong\u003e, a unified deep generative model that unifies four different tasks into a joint probabilistic distribution modeling task. The key advantage of FluidZero is that it facilitates cross-modal and cross-task interactions, enabling effective learning of causality laws between physical variables, and then enhancing performance on diverse tasks in the Fluid-Structure Interaction (FSI) system. We evaluate FluidZero in a FSI system, including simulation data and real-world measured data obtained through Particle Image Velocimetry (PIV). \u0026nbsp;Moreover, the designed foil is directly transferred to real-world experiments through 3D printing. FluidZero shows better generalization capabilities, achieving superior performance even in Out-Of-Bound (OOB) situations and real-world applications.\u003c/p\u003e","manuscriptTitle":"FluidZero: Mastering Diverse Tasks in Fluid Systems through a Single Generative Model","msid":"","msnumber":"","nonDraftVersions":[{"code":3,"date":"2026-02-26 18:01:55","doi":"10.21203/rs.3.rs-6881567/v3","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}},{"code":2,"date":"2025-06-23 19:23:51","doi":"10.21203/rs.3.rs-6881567/v2","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}},{"code":1,"date":"2025-06-13 04:36:18","doi":"10.21203/rs.3.rs-6881567/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":"21629647-8fd1-411d-93e6-43e1dc0db873","owner":[],"postedDate":"February 26th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":50477991,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-06-13T04:36:18+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-26 18:01:55","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v3","identity":"rs-6881567","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6881567","identity":"rs-6881567","version":["v3"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}