Accelerating Electron Diffraction Analysis Using Graph Neural Networks and Attention Mechanisms

Accelerating Electron Diffraction Analysis Using Graph Neural Networks and Attention Mechanisms | 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 Accelerating Electron Diffraction Analysis Using Graph Neural Networks and Attention Mechanisms Anvesh Nathani, Arthur RC McCray, Yingtao Liu, Hanping Ding, Pejman Kazempoor, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7624017/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 07 Jan, 2026 Read the published version in npj Computational Materials → Version 1 posted 9 You are reading this latest preprint version Abstract Electron diffraction(ED) often used to solve for unknown structures or refine existing ones. Existing methods for automated ED analysis often struggle with challenges such as computational expense and experimental noise. This study introduces a deep learning framework to accelerate and improve crystal structure determination from diffraction patterns. The methodology treats each diffraction pattern as a relational graph of Bragg spots. Spot features are encoded using a 1D convolutional network, from which a relational attention aggregator constructs an orientation-agnostic graph. This graph is processed by a Graphormer encoder enhanced with Mixture-of-Experts layers, allowing the model to learn complex crystallographic relationships efficiently. Trained and tested on a large dataset of simulated diffraction patterns, the model achieved a crystal system classification accuracy of 89.2% and a space group accuracy of 70.2% from single patterns, significantly outperforming a state-of-the-art random forest baseline (74.2% and 57.8%, respectively). By aggregating predictions across multiple zone axes, these accuracies improved to 96.5% and 79.5%. The model also demonstrated robust performance on experimental data of gold nanoparticles, producing plausible classifications consistent with known orientation degeneracies. By unifying relational graph reasoning with specialized expert networks, this work presents a robust and automated framework for high-throughput materials characterization. Physical sciences/Chemistry Physical sciences/Materials science Physical sciences/Mathematics and computing Physical sciences/Nanoscience and technology Physical sciences/Physics Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 07 Jan, 2026 Read the published version in npj Computational Materials → Version 1 posted Editorial decision: Revision requested 27 Oct, 2025 Reviews received at journal 24 Oct, 2025 Reviews received at journal 18 Oct, 2025 Reviewers agreed at journal 03 Oct, 2025 Reviewers agreed at journal 28 Sep, 2025 Reviewers invited by journal 27 Sep, 2025 Editor assigned by journal 21 Sep, 2025 Submission checks completed at journal 20 Sep, 2025 First submitted to journal 15 Sep, 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-7624017","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":525944719,"identity":"c24c51b9-1114-44d3-9b36-545c15da5db2","order_by":0,"name":"Anvesh Nathani","email":"","orcid":"","institution":"University of Oklahoma","correspondingAuthor":false,"prefix":"","firstName":"Anvesh","middleName":"","lastName":"Nathani","suffix":""},{"id":525944720,"identity":"9fa4bd0d-5520-4f8f-a565-e2a0e271dc6f","order_by":1,"name":"Arthur RC McCray","email":"","orcid":"","institution":"Stanford University","correspondingAuthor":false,"prefix":"","firstName":"Arthur","middleName":"RC","lastName":"McCray","suffix":""},{"id":525944722,"identity":"d6148d21-13fb-4fe5-adbb-87f489f8c707","order_by":2,"name":"Yingtao Liu","email":"","orcid":"","institution":"University of Oklahoma","correspondingAuthor":false,"prefix":"","firstName":"Yingtao","middleName":"","lastName":"Liu","suffix":""},{"id":525944723,"identity":"b9b5aaca-a016-4bbd-a08f-4088a13407f0","order_by":3,"name":"Hanping Ding","email":"","orcid":"","institution":"University of Oklahoma","correspondingAuthor":false,"prefix":"","firstName":"Hanping","middleName":"","lastName":"Ding","suffix":""},{"id":525944726,"identity":"5f548aa2-7b79-4448-b254-fbbc8e1a3605","order_by":4,"name":"Pejman Kazempoor","email":"","orcid":"","institution":"University of Oklahoma","correspondingAuthor":false,"prefix":"","firstName":"Pejman","middleName":"","lastName":"Kazempoor","suffix":""},{"id":525944728,"identity":"818f6246-9575-4cfb-9096-884a662d31df","order_by":5,"name":"Shuozhi Xu","email":"","orcid":"","institution":"University of Oklahoma","correspondingAuthor":false,"prefix":"","firstName":"Shuozhi","middleName":"","lastName":"Xu","suffix":""},{"id":525944730,"identity":"d854d532-5ee4-4235-9fcf-a6b3b0ef3467","order_by":6,"name":"Colin Ophus","email":"","orcid":"","institution":"Stanford University","correspondingAuthor":false,"prefix":"","firstName":"Colin","middleName":"","lastName":"Ophus","suffix":""},{"id":525944731,"identity":"4532f8c9-bd9a-4f47-86a1-11ce51736064","order_by":7,"name":"Iman Ghamarian","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAiklEQVRIiWNgGAWjYBACNhDxAcxMIEEL4wyStIAAMw9JWvjEDj97bFNxmIGfPceASIdJp5kb55w5zCDZ84ZoLQlm0rlthxkMbhBvS/o3aUugFnsStOSYSTOCbJEgQUuZZM+ZdB6JM88KiNMiPzt9m8SPCms5/vbkDcRpgQEe0pSPglEwCkbBKMAPAN/rIt8hbc28AAAAAElFTkSuQmCC","orcid":"","institution":"University of Oklahoma","correspondingAuthor":true,"prefix":"","firstName":"Iman","middleName":"","lastName":"Ghamarian","suffix":""}],"badges":[],"createdAt":"2025-09-15 21:08:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7624017/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7624017/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41524-025-01927-5","type":"published","date":"2026-01-07T15:58:49+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":93113058,"identity":"3a2ccf1b-1d54-4e1a-a2cb-65ab4de811d2","added_by":"auto","created_at":"2025-10-09 08:13:16","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9441,"visible":true,"origin":"","legend":"","description":"","filename":"d1971c31c9d0425d8ce93bbbb18d7b2a.json","url":"https://assets-eu.researchsquare.com/files/rs-7624017/v1/444a8c054e267941a7ee18e7.json"},{"id":100069995,"identity":"5e209ec4-2280-43a0-b71a-20367d576c5b","added_by":"auto","created_at":"2026-01-12 16:15:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2072992,"visible":true,"origin":"","legend":"","description":"","filename":"GraphNetworkforCrystalPrediction.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7624017/v1_covered_60dfb28d-d622-455e-bd83-7ec3c6223482.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Accelerating Electron Diffraction Analysis Using Graph Neural Networks and Attention Mechanisms","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":"npj-computational-materials","isNatureJournal":false,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"npjcompumats","sideBox":"Learn more about [npj Computational Materials](http://www.nature.com/npjcompumats/)","snPcode":"41524","submissionUrl":"https://mts-npjcompumats.nature.com/","title":"npj Computational Materials","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7624017/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7624017/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Electron diffraction(ED) often used to solve for unknown structures or refine existing ones. Existing methods for automated ED analysis often struggle with challenges such as computational expense and experimental noise. This study introduces a deep learning framework to accelerate and improve crystal structure determination from diffraction patterns. The methodology treats each diffraction pattern as a relational graph of Bragg spots. Spot features are encoded using a 1D convolutional network, from which a relational attention aggregator constructs an orientation-agnostic graph. This graph is processed by a Graphormer encoder enhanced with Mixture-of-Experts layers, allowing the model to learn complex crystallographic relationships efficiently. Trained and tested on a large dataset of simulated diffraction patterns, the model achieved a crystal system classification accuracy of 89.2\\% and a space group accuracy of 70.2\\% from single patterns, significantly outperforming a state-of-the-art random forest baseline (74.2\\% and 57.8\\%, respectively). By aggregating predictions across multiple zone axes, these accuracies improved to 96.5\\% and 79.5\\%. The model also demonstrated robust performance on experimental data of gold nanoparticles, producing plausible classifications consistent with known orientation degeneracies. By unifying relational graph reasoning with specialized expert networks, this work presents a robust and automated framework for high-throughput materials characterization.","manuscriptTitle":"Accelerating Electron Diffraction Analysis Using Graph Neural Networks and Attention Mechanisms","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-09 08:13:11","doi":"10.21203/rs.3.rs-7624017/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-27T18:55:05+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-24T09:07:31+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-19T01:50:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"146781770898056379207162846772475080831","date":"2025-10-03T08:12:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"229847148626621461335535960094930390117","date":"2025-09-28T16:26:38+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-27T11:58:08+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-21T19:21:30+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-20T07:14:37+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Computational Materials","date":"2025-09-15T21:05:24+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-computational-materials","isNatureJournal":false,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"npjcompumats","sideBox":"Learn more about [npj Computational Materials](http://www.nature.com/npjcompumats/)","snPcode":"41524","submissionUrl":"https://mts-npjcompumats.nature.com/","title":"npj Computational Materials","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"51828658-e1ed-4348-b2a0-6920fece8210","owner":[],"postedDate":"October 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":55897953,"name":"Physical sciences/Chemistry"},{"id":55897954,"name":"Physical sciences/Materials science"},{"id":55897955,"name":"Physical sciences/Mathematics and computing"},{"id":55897956,"name":"Physical sciences/Nanoscience and technology"},{"id":55897957,"name":"Physical sciences/Physics"}],"tags":[],"updatedAt":"2026-01-12T16:09:03+00:00","versionOfRecord":{"articleIdentity":"rs-7624017","link":"https://doi.org/10.1038/s41524-025-01927-5","journal":{"identity":"npj-computational-materials","isVorOnly":false,"title":"npj Computational Materials"},"publishedOn":"2026-01-07 15:58:49","publishedOnDateReadable":"January 7th, 2026"},"versionCreatedAt":"2025-10-09 08:13:11","video":"","vorDoi":"10.1038/s41524-025-01927-5","vorDoiUrl":"https://doi.org/10.1038/s41524-025-01927-5","workflowStages":[]},"version":"v1","identity":"rs-7624017","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7624017","identity":"rs-7624017","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}