Machine learning interatomic potential for the structural properties iron oxides

Machine learning interatomic potential for the structural properties iron oxides | 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 Machine learning interatomic potential for the structural properties iron oxides Alberto Torres, Alan Barros de Oliveira, Mathus dos Santos Barbosa, and 8 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8031034/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 12 Feb, 2026 Read the published version in Scientific Reports → Version 1 posted 12 You are reading this latest preprint version Abstract Iron oxides constitute an important class of materials, exhibiting a rich and intricate range of behaviors. Despite their significance, the structural and mechanical properties, particularly of Hematite ($\alpha$-Fe2O3), have been scarcely investigated in the literature. At the same time, recent developments in machine learning for interatomic potentials have revolutionized computational materials science by enabling highly accurate and efficient simulations of atomic interactions. Traditional methods, such as density functional theory (DFT) and classical force fields, often struggle with high computational costs or lack the flexibility to generalize across diverse chemical environments. ML-based approaches have emerged as powerful alternatives, learning complex potential energy surfaces from quantum-mechanical data. These models can achieve DFT accuracy at a fraction of the computational cost, facilitating large-scale molecular dynamics (MD) simulations. In this work, we present a graph neural network interatomic potential for hematite. The model was trained on datasets generated from DFT+U calculations to account for strong electronic correlations, using atomic configurations sampled across a wide range of temperatures and pressures. Our potential accurately reproduces fundamental material properties, including the elastic moduli, anisotropic elastic constants, vibrational frequencies, and surface energies. Furthermore, we demonstrate its transferability to other bulk iron oxides. This work enables large-scale molecular dynamics (MD) simulations of iron-based materials with ab initio accuracy at a computational cost comparable to that of classical potentials, opening new opportunities for investigating these complex systems. Physical sciences/Chemistry Physical sciences/Materials science Physical sciences/Physics Full Text Additional Declarations Competing interest reported. The project is funded by the mining company Vale. The company did not interfere in the project design, nor were any results left out per the company's request. Supplementary Files SIFeO.pdf Cite Share Download PDF Status: Published Journal Publication published 12 Feb, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 10 Dec, 2025 Reviews received at journal 09 Dec, 2025 Reviews received at journal 28 Nov, 2025 Reviews received at journal 24 Nov, 2025 Reviewers agreed at journal 17 Nov, 2025 Reviewers agreed at journal 14 Nov, 2025 Reviewers agreed at journal 14 Nov, 2025 Reviewers invited by journal 14 Nov, 2025 Editor invited by journal 11 Nov, 2025 Editor assigned by journal 07 Nov, 2025 Submission checks completed at journal 07 Nov, 2025 First submitted to journal 04 Nov, 2025 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-8031034","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":550032716,"identity":"6c081ee8-7b05-48b5-ab0f-5fd39cd8be8d","order_by":0,"name":"Alberto Torres","email":"","orcid":"","institution":"São Paulo State University","correspondingAuthor":false,"prefix":"","firstName":"Alberto","middleName":"","lastName":"Torres","suffix":""},{"id":550032717,"identity":"8592f8ad-dd03-484f-9949-2febec026114","order_by":1,"name":"Alan Barros de Oliveira","email":"","orcid":"","institution":"Universidade Federal de Ouro Preto","correspondingAuthor":false,"prefix":"","firstName":"Alan","middleName":"Barros","lastName":"de Oliveira","suffix":""},{"id":550032718,"identity":"467416fd-28b1-4feb-a385-8aef71e8b637","order_by":2,"name":"Mathus dos Santos Barbosa","email":"","orcid":"","institution":"Universidade Federal de Ouro Preto","correspondingAuthor":false,"prefix":"","firstName":"Mathus","middleName":"dos Santos","lastName":"Barbosa","suffix":""},{"id":550032721,"identity":"4e377147-dc43-42fb-99ad-6c06c60dfe72","order_by":3,"name":"Leonardo Villegas Lelovsky","email":"","orcid":"","institution":"Universidade Federal de Ouro Preto","correspondingAuthor":false,"prefix":"","firstName":"Leonardo","middleName":"Villegas","lastName":"Lelovsky","suffix":""},{"id":550032723,"identity":"5712a0f6-c339-4bfd-b2c3-a63dfbcecc29","order_by":4,"name":"Valdirene Resende","email":"","orcid":"","institution":"Vale","correspondingAuthor":false,"prefix":"","firstName":"Valdirene","middleName":"","lastName":"Resende","suffix":""},{"id":550032724,"identity":"fce239f2-2b14-4621-b19b-d11138d0ce61","order_by":5,"name":"Flávio Dutra","email":"","orcid":"","institution":"Vale","correspondingAuthor":false,"prefix":"","firstName":"Flávio","middleName":"","lastName":"Dutra","suffix":""},{"id":550032725,"identity":"1e657592-17c8-41da-bb47-33476f84d6bd","order_by":6,"name":"Felipe Pimenta","email":"","orcid":"","institution":"Vale","correspondingAuthor":false,"prefix":"","firstName":"Felipe","middleName":"","lastName":"Pimenta","suffix":""},{"id":550032726,"identity":"18822a26-98ee-4c93-8965-b3911e8f3ce5","order_by":7,"name":"Fabricio Parreira","email":"","orcid":"","institution":"Vale","correspondingAuthor":false,"prefix":"","firstName":"Fabricio","middleName":"","lastName":"Parreira","suffix":""},{"id":550032727,"identity":"c6a17765-94eb-486b-a715-ae334cd46eaf","order_by":8,"name":"Amaury de Mello Souza","email":"","orcid":"","institution":"Vale International","correspondingAuthor":false,"prefix":"","firstName":"Amaury","middleName":"de Mello","lastName":"Souza","suffix":""},{"id":550032728,"identity":"67e5de47-470e-41e0-875f-6ce8197abec9","order_by":9,"name":"Matheus Josué Souza Matos","email":"","orcid":"","institution":"Universidade Federal de Ouro Preto","correspondingAuthor":false,"prefix":"","firstName":"Matheus","middleName":"Josué Souza","lastName":"Matos","suffix":""},{"id":550032729,"identity":"b1784753-f781-4c9c-acfe-0e4674f1a1c7","order_by":10,"name":"Alexandre Reily Rocha","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBElEQVRIiWNgGAWjYDACdjDJDOEkFDDIQcUP4NbCjKLFgMGYRC0MBgyJDYS08DczH5P4ucM6n5+B9+GDBwaH0zfcbj78uYDhTj4uLRKH2ZINe8+kW85sYDc2SDA4nLvhzrE06RkMzywbcOk5zGP4gLftsIHBATY2CbCWGzlmzDwMhw1w6ZA/zP/h4F+gFvsDbOw/gFrSDW7kf/6MT4vBYR7Gx2BbGNjYgCF2OMHgRg6DND4thofZjI1l29INgJ5iBjos3XDmjTQz6RkGz3BqkTve/EzybZu1AX97G+PHHxXW8nw3kh9/Lqi4g1MLAkCiphnKJkIDDNQhaR8Fo2AUjIJRAAEAkoRT5OT0TF4AAAAASUVORK5CYII=","orcid":"","institution":"São Paulo State University","correspondingAuthor":true,"prefix":"","firstName":"Alexandre","middleName":"Reily","lastName":"Rocha","suffix":""}],"badges":[],"createdAt":"2025-11-04 16:38:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8031034/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8031034/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-026-38096-4","type":"published","date":"2026-02-12T15:57:31+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":96769149,"identity":"43049d5c-fc23-4ffd-81a9-c4815b0819ad","added_by":"auto","created_at":"2025-11-25 23:13:39","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11831,"visible":true,"origin":"","legend":"","description":"","filename":"ea28470c451d4b799c684362ab131736.json","url":"https://assets-eu.researchsquare.com/files/rs-8031034/v1/d0d88a61b917483dfa6bfdc8.json"},{"id":102785445,"identity":"27dc2790-e64b-4009-bd98-cdf7037aa435","added_by":"auto","created_at":"2026-02-16 16:06:42","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2701987,"visible":true,"origin":"","legend":"","description":"","filename":"PaperValescirep.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8031034/v1_covered_eb8a2ca9-9312-4e89-8445-95231e3133af.pdf"},{"id":96769150,"identity":"919215e2-a42c-4f49-88fd-508ec1adaea9","added_by":"auto","created_at":"2025-11-25 23:13:39","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":4164475,"visible":true,"origin":"","legend":"","description":"","filename":"SIFeO.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8031034/v1/4c6dd086bc326bc0eb5271b1.pdf"}],"financialInterests":"Competing interest reported. The project is funded by the mining company Vale. The company did not interfere in the project design, nor were any results left out per the company's request.","formattedTitle":"Machine learning interatomic potential for the structural properties iron oxides","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-8031034/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8031034/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIron oxides constitute an important class of materials, exhibiting a rich and intricate range of behaviors. Despite their significance, the structural and mechanical properties, particularly of Hematite ($\\alpha$-Fe2O3), have been scarcely investigated in the literature. At the same time, recent developments in machine learning for interatomic potentials have revolutionized computational materials science by enabling highly accurate and efficient simulations of atomic interactions. Traditional methods, such as density functional theory (DFT) and classical force fields, often struggle with high computational costs or lack the flexibility to generalize across diverse chemical environments. ML-based approaches have emerged as powerful alternatives, learning complex potential energy surfaces from quantum-mechanical data. These models can achieve DFT accuracy at a fraction of the computational cost, facilitating large-scale molecular dynamics (MD) simulations.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eIn this work, we present a graph neural network interatomic potential for hematite. The model was trained on datasets generated from DFT+U calculations to account for strong electronic correlations, using atomic configurations sampled across a wide range of temperatures and pressures. Our potential accurately reproduces fundamental material properties, including the elastic moduli, anisotropic elastic constants, vibrational frequencies, and surface energies. Furthermore, we demonstrate its transferability to other bulk iron oxides. This work enables large-scale molecular dynamics (MD) simulations of iron-based materials with ab initio accuracy at a computational cost comparable to that of classical potentials, opening new opportunities for investigating these complex systems.\u003c/p\u003e","manuscriptTitle":"Machine learning interatomic potential for the structural properties iron oxides","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-25 23:13:35","doi":"10.21203/rs.3.rs-8031034/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-10T07:27:01+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-09T09:59:46+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-28T08:46:20+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-24T15:20:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"55275057581564649764706926067818180658","date":"2025-11-17T14:41:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"121767395378180400015265926911976332423","date":"2025-11-14T14:06:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"73714365915385686680727637754859366488","date":"2025-11-14T13:27:46+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-11-14T13:14:10+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-11-11T16:19:50+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-08T03:09:48+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-11-08T03:08:21+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-11-04T16:29:59+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"80da0d6e-8606-48a5-beb9-a88d08878051","owner":[],"postedDate":"November 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":58520635,"name":"Physical sciences/Chemistry"},{"id":58520638,"name":"Physical sciences/Materials science"},{"id":58520639,"name":"Physical sciences/Physics"}],"tags":[],"updatedAt":"2026-02-16T16:03:58+00:00","versionOfRecord":{"articleIdentity":"rs-8031034","link":"https://doi.org/10.1038/s41598-026-38096-4","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2026-02-12 15:57:31","publishedOnDateReadable":"February 12th, 2026"},"versionCreatedAt":"2025-11-25 23:13:35","video":"","vorDoi":"10.1038/s41598-026-38096-4","vorDoiUrl":"https://doi.org/10.1038/s41598-026-38096-4","workflowStages":[]},"version":"v1","identity":"rs-8031034","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8031034","identity":"rs-8031034","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}