Physics-informed Neural-operator Predictive Control for Drag Reduction in Turbulent Flows

Physics-informed Neural-operator Predictive Control for Drag Reduction in Turbulent Flows | 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 Physics-informed Neural-operator Predictive Control for Drag Reduction in Turbulent Flows Anima Anandkumar, ZELIN ZHAO, Zongyi Li, Kimia Hassibi, Kamyar Azizzadenesheli, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4702215/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Turbulence control for wall friction reduction poses a significant challenge due to computational costs associated with modeling turbulent dynamics. In this work, we present a learning and control scheme termed physics-informed neural-operator-based predictive control (PINO-PC). Our method uses a Neural Operator framework that enables accurate learning and control of turbulent flows. It carries out predictive control where both the policy and the observer model for turbulence control are learned jointly. We show that PINO-PC outperforms prior model-free reinforcement learning methods with a stable policy learning procedure. We experiment with various challenging generalized scenarios where flows are of unseen high Reynolds numbers, and we find that our method achieves a drag reduction of 39.0% under a bulk-velocity Reynolds number of 15k, outperforming previous fluid control methods by more than 32%. Physical sciences/Physics/Fluid dynamics Physical sciences/Mathematics and computing/Computer science Drag reduction Fluid control Neural operators Machine-learning-based control Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Under Review 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-4702215","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":338196063,"identity":"33b08ccd-4675-4b81-860b-c29db4539668","order_by":0,"name":"Anima Anandkumar","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA30lEQVRIiWNgGAWjYFACxgYGhgMgBjOIlJAhRQtbAkgLD5E2gbXwGIBJgor5Zze3bvhx5nA0/+wzn1/dqLHgYWA/fHQDPi0Sdw623ey5cTh3xrncbdY5x4AO40lLu4HXmhuJbTd4PhzObTjDu804hw2oRYLHDK8WeaCWm3+AWuaf4XlmnPOPCC0GQC23eYAO23CGh/lxbhsRWgxBWmTOpOduPMNmxpzbJ8HDRsgvcjfSn918c8w6d94Z5sefc77VyfGzHz6G3/tIgE0CTBKrHASYP5CiehSMglEwCkYOAAAhclHOjG9x/wAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-6974-6797","institution":"California Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Anima","middleName":"","lastName":"Anandkumar","suffix":""},{"id":338196064,"identity":"da5e7c7b-3fce-49bd-971c-8eeaed5e0bd4","order_by":1,"name":"ZELIN ZHAO","email":"","orcid":"https://orcid.org/0000-0002-2638-0414","institution":"Caltech","correspondingAuthor":false,"prefix":"","firstName":"ZELIN","middleName":"","lastName":"ZHAO","suffix":""},{"id":338196065,"identity":"3aba10db-15dc-42f1-b225-02c23a0db24a","order_by":2,"name":"Zongyi Li","email":"","orcid":"","institution":"California Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Zongyi","middleName":"","lastName":"Li","suffix":""},{"id":338196066,"identity":"e570c5a3-aad2-4a53-9150-699e32ff4b4a","order_by":3,"name":"Kimia Hassibi","email":"","orcid":"","institution":"California Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Kimia","middleName":"","lastName":"Hassibi","suffix":""},{"id":338196067,"identity":"dd889c8f-0794-401e-849d-433a482d7073","order_by":4,"name":"Kamyar Azizzadenesheli","email":"","orcid":"https://orcid.org/0000-0001-8507-1868","institution":"NVIDIA","correspondingAuthor":false,"prefix":"","firstName":"Kamyar","middleName":"","lastName":"Azizzadenesheli","suffix":""},{"id":338196068,"identity":"33f31d6f-4540-497d-8973-921334bb2518","order_by":5,"name":"Junchi Yan","email":"","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Junchi","middleName":"","lastName":"Yan","suffix":""},{"id":338196069,"identity":"575d3ed8-b753-4b09-bc21-ed8df156198e","order_by":6,"name":"H. Jane Bae","email":"","orcid":"https://orcid.org/0000-0001-6789-6209","institution":"California Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"H.","middleName":"Jane","lastName":"Bae","suffix":""}],"badges":[],"createdAt":"2024-07-08 02:55:48","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4702215/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4702215/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":63087679,"identity":"ac2ec9a9-bac0-412a-ab30-482a8eb9f020","added_by":"auto","created_at":"2024-08-23 03:34:23","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":9986191,"visible":true,"origin":"","legend":"","description":"","filename":"pinopcmanuscriptfinal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4702215/v1_covered_5afccd3b-65a4-467b-9eb6-c153ec103e9e.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Physics-informed Neural-operator Predictive Control for Drag Reduction in Turbulent Flows","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Drag reduction, Fluid control, Neural operators, Machine-learning-based control","lastPublishedDoi":"10.21203/rs.3.rs-4702215/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4702215/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Turbulence control for wall friction reduction poses a significant challenge due to computational costs associated with modeling turbulent dynamics. In this work, we present a learning and control scheme termed physics-informed neural-operator-based predictive control (PINO-PC). Our method uses a Neural Operator framework that enables accurate learning and control of turbulent flows. It carries out predictive control where both the policy and the observer model for turbulence control are learned jointly. We show that PINO-PC outperforms prior model-free reinforcement learning methods with a stable policy learning procedure. We experiment with various challenging generalized scenarios where flows are of unseen high Reynolds numbers, and we find that our method achieves a drag reduction of 39.0% under a bulk-velocity Reynolds number of 15k, outperforming previous fluid control methods by more than 32%.","manuscriptTitle":"Physics-informed Neural-operator Predictive Control for Drag Reduction in Turbulent Flows","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-23 03:26:06","doi":"10.21203/rs.3.rs-4702215/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"33526d57-2727-4b1f-b9d0-a7c09e4b6d44","owner":[],"postedDate":"August 23rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":35830796,"name":"Physical sciences/Physics/Fluid dynamics"},{"id":35830797,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2024-08-23T03:26:06+00:00","versionOfRecord":[],"versionCreatedAt":"2024-08-23 03:26:06","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4702215","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4702215","identity":"rs-4702215","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}