Development of a Convective–Diffusion Physics-Informed Neural Network for Thermal Analysis of Lithium Film Flow on the Surface of a Tokamak Divertor

Development of a Convective–Diffusion Physics-Informed Neural Network for Thermal Analysis of Lithium Film Flow on the Surface of a Tokamak Divertor | 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 Development of a Convective–Diffusion Physics-Informed Neural Network for Thermal Analysis of Lithium Film Flow on the Surface of a Tokamak Divertor Habib Ur Rahman, Abid Hussain, Muhammad ilyas, Manzoor Ahmed, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9321560/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Accurate modeling of heat transfer in nuclear engineering systems demands substantial computational resources, particularly for real-time analysis and optimization, motivating the use of artificial intelligence (AI) and deep learning (DL) as efficient alternatives. In this work, a Convective–Diffusion Physics-Informed Neural Network (CD-PINN) framework is developed to investigate steady-state heat transfer in lithium film flow along the plasma-facing surface of a tokamak divertor, where automatic differentiation is employed to evaluate residuals of the governing convection–diffusion equation and embed physical constraints directly into the training process. The model is validated using one- and two-dimensional two-layer heat conduction benchmarks, showing excellent agreement with analytical solutions, while systematic hyperparameter optimization identifies the Gaussian Error Linear Unit (GELU) activation function and the Adam optimizer as optimal for convergence and accuracy. The optimal architecture consists of 20 hidden layers with 20 neurons per layer and 5,500 collocation and boundary points, yielding steady-state temperature distributions that closely match reference solutions and demonstrate the CD-PINN’s effectiveness as a robust and computationally efficient alternative to conventional numerical solvers for complex heat transfer problems in nuclear and fusion energy systems. Physics-Informed Neural Networks (PINNs) Convective–Diffusion Equation Tokamak Divertor Lithium Film Flow Computational Modeling Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 20 Apr, 2026 Reviewers invited by journal 15 Apr, 2026 Editor assigned by journal 06 Apr, 2026 Submission checks completed at journal 06 Apr, 2026 First submitted to journal 04 Apr, 2026 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-9321560","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":617582077,"identity":"80dc3d1a-6b73-4ae5-b2cb-2189779f7b6c","order_by":0,"name":"Habib Ur Rahman","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA50lEQVRIiWNgGAWjYBACAwYehsMMDAcYJIAMhg8MDAmkaWGcQawWZpgWZh5itJiznz14uIDhTr7k7N5j0rZtdnn87A2MHz7m4NZi2ZOXcHgGwzPL2TLn0qRz25KLJXsOMEvO3IbHYQdyDA4DvWMgJ5FjBtTCnLjhRgIbMy8+LeffIGmxbKsnQssNqC3SIC2MbYeJ0fIO5JfDBpJzzhhb9pw7njiz52Azfr+czz38uQCoReJ2j+GNH2XVif3szQc/fMSjBQwY/wEJCQYWCUY2MLeBgHoYkGBg/sDwh0jFo2AUjIJRMKIAAAygVZ9fjuhFAAAAAElFTkSuQmCC","orcid":"","institution":"Pakistan Institute of Engineering and Applied Sciences","correspondingAuthor":true,"prefix":"","firstName":"Habib","middleName":"Ur","lastName":"Rahman","suffix":""},{"id":617582078,"identity":"95e483fc-37ad-4986-af07-606ac7a2296e","order_by":1,"name":"Abid Hussain","email":"","orcid":"","institution":"Pakistan Institute of Engineering and Applied Sciences","correspondingAuthor":false,"prefix":"","firstName":"Abid","middleName":"","lastName":"Hussain","suffix":""},{"id":617582079,"identity":"fc386a32-4498-4f00-94e6-aae66b24a79e","order_by":2,"name":"Muhammad ilyas","email":"","orcid":"","institution":"Pakistan Institute of Engineering and Applied Sciences","correspondingAuthor":false,"prefix":"","firstName":"Muhammad","middleName":"","lastName":"ilyas","suffix":""},{"id":617582080,"identity":"8aec4579-535e-4703-afba-41aaf57553c1","order_by":3,"name":"Manzoor Ahmed","email":"","orcid":"","institution":"Pakistan Institute of Engineering and Applied Sciences","correspondingAuthor":false,"prefix":"","firstName":"Manzoor","middleName":"","lastName":"Ahmed","suffix":""},{"id":617582081,"identity":"d449c9e3-9521-4e20-8357-6667e0601ebd","order_by":4,"name":"Muhammad Saad Qayyum","email":"","orcid":"","institution":"Pakistan Institute of Engineering and Applied Sciences","correspondingAuthor":false,"prefix":"","firstName":"Muhammad","middleName":"Saad","lastName":"Qayyum","suffix":""}],"badges":[],"createdAt":"2026-04-04 15:24:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9321560/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9321560/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106313913,"identity":"543ec1c1-9456-4398-90da-5275cb1d97a0","added_by":"auto","created_at":"2026-04-07 10:57:55","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5095639,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerCDPINN.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9321560/v1_covered_366e1c57-6fdd-4e50-bbfb-b8d7ff5cf2d5.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eDevelopment of a Convective–Diffusion Physics-Informed Neural Network for Thermal Analysis of Lithium Film Flow on the Surface of a Tokamak Divertor\u003c/p\u003e","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":"journal-of-fusion-energy","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jofe","sideBox":"Learn more about [Journal of Fusion Energy](http://link.springer.com/journal/10894)","snPcode":"10894","submissionUrl":"https://submission.nature.com/new-submission/10894/3","title":"Journal of Fusion Energy","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Physics-Informed Neural Networks (PINNs), Convective–Diffusion Equation, Tokamak Divertor, Lithium Film Flow, Computational Modeling","lastPublishedDoi":"10.21203/rs.3.rs-9321560/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9321560/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate modeling of heat transfer in nuclear engineering systems demands substantial computational resources, particularly for real-time analysis and optimization, motivating the use of artificial intelligence (AI) and deep learning (DL) as efficient alternatives. In this work, a Convective–Diffusion Physics-Informed Neural Network (CD-PINN) framework is developed to investigate steady-state heat transfer in lithium film flow along the plasma-facing surface of a tokamak divertor, where automatic differentiation is employed to evaluate residuals of the governing convection–diffusion equation and embed physical constraints directly into the training process. The model is validated using one- and two-dimensional two-layer heat conduction benchmarks, showing excellent agreement with analytical solutions, while systematic hyperparameter optimization identifies the Gaussian Error Linear Unit (GELU) activation function and the Adam optimizer as optimal for convergence and accuracy. The optimal architecture consists of 20 hidden layers with 20 neurons per layer and 5,500 collocation and boundary points, yielding steady-state temperature distributions that closely match reference solutions and demonstrate the CD-PINN’s effectiveness as a robust and computationally efficient alternative to conventional numerical solvers for complex heat transfer problems in nuclear and fusion energy systems.","manuscriptTitle":"Development of a Convective–Diffusion Physics-Informed Neural Network for Thermal Analysis of Lithium Film Flow on the Surface of a Tokamak Divertor","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-07 10:54:57","doi":"10.21203/rs.3.rs-9321560/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"277034818403939416259530136083042773327","date":"2026-04-20T10:25:14+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-15T09:37:43+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-07T02:55:23+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-07T02:55:08+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Fusion Energy","date":"2026-04-04T15:16:09+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-fusion-energy","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jofe","sideBox":"Learn more about [Journal of Fusion Energy](http://link.springer.com/journal/10894)","snPcode":"10894","submissionUrl":"https://submission.nature.com/new-submission/10894/3","title":"Journal of Fusion Energy","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"2e165802-8a3e-4356-b67a-b2c6f7a445c9","owner":[],"postedDate":"April 7th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-15T09:59:06+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-07 10:54:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9321560","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9321560","identity":"rs-9321560","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}