A physics-informed long-range polarizable potential based on deep learning

A physics-informed long-range polarizable potential based on deep learning | 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Article A physics-informed long-range polarizable potential based on deep learning Zhi LI This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7529139/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 Machine-learning-based interatomic potentials are widely employed in atomistic simulations, but they struggle to capture long-range electrostatic correlations, which are ubiquitous in polar and in biomolecular systems. We present a physics-informed machine-learning interatomic potential that incorporates longrange electrostatic interactions through a polarizable framework. Our model combines two equivariant message-passing neural networks: one for short-range interactions and the other for environment-dependent atomic dipoles. The model is trained not only on energies and forces, but also on Born effective-charge tensors, enabling accurate predictions of field-induced properties such as infrared absorption spectra and LO–TO phonon splittings. We validate the method on ionic solids (NaCl), liquid water, and halide perovskites (MAPbI3), demonstrating improved modeling of long-range polarization effects while maintaining competitive accuracy in energy and force predictions. Our results highlight the necessity of explicit longrange electrostatics for capturing collective phenomena in insulating and polar materials. Computational Physics machine learning long-range electrostatics Full Text Additional Declarations The authors declare no competing interests. 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-7529139","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":509820684,"identity":"849e7626-8d41-4f93-8904-67ab736ab6e5","order_by":0,"name":"Zhi LI","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAlElEQVRIiWNgGAWjYDACdsbGBwkgBjPRWpgZmw0SGAyADKL1MDOwSTCAtBBtjXwzc1vFg5o/eQzs/AeI08LYzNh2I+GYQTHxDmNmBmpJbDBIbCBaCxtQSwFpWniAWhhI0yIBDGSJhGPGxWzMzAbEaZFvb3/48UeNXB4//8EHRFoDBQlspKkHaSFZxygYBaNgFIwcAABv7x+FQvGO+gAAAABJRU5ErkJggg==","orcid":"","institution":"The Abdus Salam International Centre for Theoretical Physics","correspondingAuthor":true,"prefix":"","firstName":"Zhi","middleName":"","lastName":"LI","suffix":""}],"badges":[],"createdAt":"2025-09-03 16:39:45","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7529139/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7529139/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90571767,"identity":"6c325ada-358f-4da8-abed-615a950a0b48","added_by":"auto","created_at":"2025-09-04 08:37:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":11062213,"visible":true,"origin":"","legend":"","description":"","filename":"LNET.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7529139/v1_covered_95ea0e06-17ed-4c73-92f6-553aac08363f.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eA physics-informed long-range polarizable potential based on deep learning\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"The Abdus Salam International Centre for Theoretical Physics","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":"machine learning, long-range electrostatics","lastPublishedDoi":"10.21203/rs.3.rs-7529139/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7529139/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMachine-learning-based interatomic potentials are widely employed in atomistic simulations, but they struggle to capture long-range electrostatic correlations, which are ubiquitous in polar and in biomolecular systems. We present a physics-informed machine-learning interatomic potential that incorporates longrange electrostatic interactions through a polarizable framework. Our model combines two equivariant message-passing neural networks: one for short-range interactions and the other for environment-dependent atomic dipoles. The model is trained not only on energies and forces, but also on Born effective-charge tensors, enabling accurate predictions of field-induced properties such as infrared absorption spectra and LO–TO phonon splittings. We validate the method on ionic solids (NaCl), liquid water, and halide perovskites (MAPbI3), demonstrating improved modeling of long-range polarization effects while maintaining competitive accuracy in energy and force predictions. Our results highlight the necessity of explicit longrange electrostatics for capturing collective phenomena in insulating and polar materials.\u003c/p\u003e","manuscriptTitle":"A physics-informed long-range polarizable potential based on deep learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-04 08:28:53","doi":"10.21203/rs.3.rs-7529139/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":"261e1bd6-4855-4169-9384-f6cd61866a27","owner":[],"postedDate":"September 4th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":54151507,"name":"Computational Physics"}],"tags":[],"updatedAt":"2025-09-04T08:28:53+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-04 08:28:53","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7529139","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7529139","identity":"rs-7529139","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}