Shot-to-Shot Neural Control of Plasma States in Laser-Driven Experiments

Shot-to-Shot Neural Control of Plasma States in Laser-Driven Experiments | 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 Shot-to-Shot Neural Control of Plasma States in Laser-Driven Experiments Derek Mariscal, Abhik Sarkar, Scott Feister, Christoph Niemann, and 8 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9275535/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 High-repetition-rate (HRR) laser-driven experiments are transforming high energy density physics by enabling rapid, data-rich exploration of complex plasma phenomena. Real-time control in these systems remains difficult because iterative optimization algorithms and linear feedback loops (e.g., PID) consume shots during convergence and adapt poorly to nonlinear, drifting operating conditions. Here we demonstrate shot-to-shot direct ML control for laser-driven plasmas, implemented with a neural setpoint controller that maps a requested plasma state and measured operating conditions directly to actuator settings. Applied to blast wave position control on a multi-joule platform, the method delivers sub-second inference compatible with 1 Hz operation and maintains the target po- sition with sub-millimeter precision while background pressure varies by more than 400% within the trained pressure bounds. Benchmarking against a hybrid neural-network plus Bayesian-optimization framework shows a substantial gain in response speed and control authority. These results establish a practical route toward retrainable autonomous control for next-generation laser-plasma platforms. Physical sciences/Physics/Plasma physics/Laser-produced plasmas Physical sciences/Energy science and technology Full Text Additional Declarations There is NO Competing Interest. 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-9275535","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":615338484,"identity":"7e5de004-6f98-4e6a-8c1b-1e2e8882f150","order_by":0,"name":"Derek Mariscal","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzElEQVRIie3PsQrCMBCA4SsFXU66pii+gZDJSdpXaRHq6ihYMOLQRXCt+DIJAbsoXesoQne3uhm6Kk27ieSH2/JxFwCT6UfjakZOf7flsOxA0N0LxoF22IS0CFuSSXK9iyr2EG53JpcUvAMJmsn0sqASz3O0TiGTKYX5MdURHoG0mI32UBFUhF64huQliBfbYM8VbUkRAR+ox0ismng0YzpSgvpLhgTrw0jgJjqSR/azitdjP5PigauZ79jN4iMSanZ8ye8sTCaT6e97A65KRQejs4bUAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0001-9502-4205","institution":"Lawrence Livermore National Lab","correspondingAuthor":true,"prefix":"","firstName":"Derek","middleName":"","lastName":"Mariscal","suffix":""},{"id":615338485,"identity":"b9430bad-70ec-4318-8960-b1a793414523","order_by":1,"name":"Abhik Sarkar","email":"","orcid":"","institution":"Lawrence Livermore National Lab","correspondingAuthor":false,"prefix":"","firstName":"Abhik","middleName":"","lastName":"Sarkar","suffix":""},{"id":615338486,"identity":"201d9ef8-e0f8-4211-8bdb-4807d6a4a121","order_by":2,"name":"Scott Feister","email":"","orcid":"","institution":"California State University Channel Islands","correspondingAuthor":false,"prefix":"","firstName":"Scott","middleName":"","lastName":"Feister","suffix":""},{"id":615338487,"identity":"9b2c6373-af1e-4d63-ab6b-2183d8c1bc0d","order_by":3,"name":"Christoph Niemann","email":"","orcid":"","institution":"University of California Los Angeles","correspondingAuthor":false,"prefix":"","firstName":"Christoph","middleName":"","lastName":"Niemann","suffix":""},{"id":615338488,"identity":"a5852472-6738-4588-9089-3890b0d24b22","order_by":4,"name":"Blagoje Djordjevic","email":"","orcid":"","institution":"Lawrence Livermore National Lab","correspondingAuthor":false,"prefix":"","firstName":"Blagoje","middleName":"","lastName":"Djordjevic","suffix":""},{"id":615338489,"identity":"c0cb6d21-600b-43f4-8928-ef51c1ffab6a","order_by":5,"name":"Peer-Timo Bremer","email":"","orcid":"https://orcid.org/0000-0003-4107-3831","institution":"Computing Directorate, Lawrence Livermore National Laboratory, Livermore, CA.","correspondingAuthor":false,"prefix":"","firstName":"Peer-Timo","middleName":"","lastName":"Bremer","suffix":""},{"id":615338490,"identity":"99842d83-348f-4f8a-b3d7-d12dec715b59","order_by":6,"name":"Brian Spears","email":"","orcid":"https://orcid.org/0000-0001-6946-8996","institution":"LLNL","correspondingAuthor":false,"prefix":"","firstName":"Brian","middleName":"","lastName":"Spears","suffix":""},{"id":615338491,"identity":"f0abc43e-80f3-4854-a1f9-378b557ab50c","order_by":7,"name":"Tammy Ma","email":"","orcid":"https://orcid.org/0000-0002-6657-9604","institution":"Lawrence Livermore National Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Tammy","middleName":"","lastName":"Ma","suffix":""},{"id":615338492,"identity":"a2be73fd-2e71-4642-83f2-fae8cbd463a8","order_by":8,"name":"Robert Dorst","email":"","orcid":"","institution":"Lawrence Livermore National Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Robert","middleName":"","lastName":"Dorst","suffix":""},{"id":615338493,"identity":"662b3ffa-2767-4d01-bea7-594c65fb6cde","order_by":9,"name":"Carmen Constantin","email":"","orcid":"","institution":"University of California Los Angeles","correspondingAuthor":false,"prefix":"","firstName":"Carmen","middleName":"","lastName":"Constantin","suffix":""},{"id":615338494,"identity":"56140885-85d8-42f4-b8ab-6349c894ff3b","order_by":10,"name":"Jackson Roth","email":"","orcid":"","institution":"University of California Los Angeles","correspondingAuthor":false,"prefix":"","firstName":"Jackson","middleName":"","lastName":"Roth","suffix":""},{"id":615338495,"identity":"c35f258e-172a-4559-a2df-19061147a8e5","order_by":11,"name":"Enrique Cisneros","email":"","orcid":"","institution":"University of California Los Angeles","correspondingAuthor":false,"prefix":"","firstName":"Enrique","middleName":"","lastName":"Cisneros","suffix":""}],"badges":[],"createdAt":"2026-03-31 06:42:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9275535/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9275535/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106959066,"identity":"bf265178-3c76-485c-83dc-35b5464061be","added_by":"auto","created_at":"2026-04-15 08:44:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2077885,"visible":true,"origin":"","legend":"Article File","description":"","filename":"realtimecontrolsmanuscriptv6submission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9275535/v1_covered_964a3817-f73b-4833-a128-e1416aabc936.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Shot-to-Shot Neural Control of Plasma States in Laser-Driven Experiments","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"","lastPublishedDoi":"10.21203/rs.3.rs-9275535/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9275535/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"High-repetition-rate (HRR) laser-driven experiments are transforming high energy density physics\r\nby enabling rapid, data-rich exploration of complex plasma phenomena. Real-time control in these\r\nsystems remains difficult because iterative optimization algorithms and linear feedback loops (e.g.,\r\nPID) consume shots during convergence and adapt poorly to nonlinear, drifting operating conditions.\r\nHere we demonstrate shot-to-shot direct ML control for laser-driven plasmas, implemented with a\r\nneural setpoint controller that maps a requested plasma state and measured operating conditions\r\ndirectly to actuator settings. Applied to blast wave position control on a multi-joule platform, the\r\nmethod delivers sub-second inference compatible with 1 Hz operation and maintains the target po-\r\nsition with sub-millimeter precision while background pressure varies by more than 400% within the\r\ntrained pressure bounds. Benchmarking against a hybrid neural-network plus Bayesian-optimization\r\nframework shows a substantial gain in response speed and control authority. These results establish\r\na practical route toward retrainable autonomous control for next-generation laser-plasma platforms.","manuscriptTitle":"Shot-to-Shot Neural Control of Plasma States in Laser-Driven Experiments","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-03 10:26:32","doi":"10.21203/rs.3.rs-9275535/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":"d5951c8f-e4f3-4a5a-b8f9-f6b5a6f557b6","owner":[],"postedDate":"April 3rd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":65474348,"name":"Physical sciences/Physics/Plasma physics/Laser-produced plasmas"},{"id":65474349,"name":"Physical sciences/Energy science and technology"}],"tags":[],"updatedAt":"2026-04-10T21:40:24+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-03 10:26:32","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9275535","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9275535","identity":"rs-9275535","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}