Harnessing Automated SEM-EDS and Machine Learning to Unlock High-Throughput Compositional Characterization of Powder Materials

Accurate SEM‑EDS Quantification, Automation, and Machine Learning Enable High‑Throughput Compositional Characterization of Powders | 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 Accurate SEM‑EDS Quantification, Automation, and Machine Learning Enable High‑Throughput Compositional Characterization of Powders Andrea Giunto, Yuxing Fei, Pragnay Nevatia, Bernardus Rendy, Nathan Szymanski, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7837297/v2 This work is licensed under a CC BY 4.0 License Status: Under Review Version 2 posted You are reading this latest preprint version Show more versions Abstract Compositional characterization is essential for understanding and optimizing material performance. For powder-based materials underpinning many modern technologies, however, accurately and rapidly resolving the composition of individual constituent phases remains an unsolved challenge, slowing materials research and limiting autonomous laboratory platforms. Scanning electron microscopy with energy dispersive X-ray spectroscopy (SEM-EDS) offers a time- and cost-effective route, but artifacts generated by irregular particle morphologies fundamentally limit its reliability for quantitative compositional analysis. Here, we introduce a scalable particle-based SEM-EDS quantification scheme that overcomes these artifacts requiring only one experimental standard per element, including light elements conventionally difficult to quantify. This approach is integrated with automated measurements and unsupervised machine-learning analysis to enable identification and extraction of phase-level compositions within multiphase samples. Implemented as a fully automated Python-based framework, AutoEMXSp consistently achieves relative errors below 5–10% across diverse chemistries, resolving primary phases and intermixed impurities. This work removes a long-standing barrier to rapid powder compositional characterization, enabling seamless integration in autonomous laboratories for accelerated discovery. Physical sciences/Materials science/Techniques and instrumentation/Characterization and analytical techniques Physical sciences/Materials science/Techniques and instrumentation/Microscopy/Scanning electron microscopy automation SEM EDS EDX powders particles composition phase machine learning self-driving clustering automated Full Text Additional Declarations The authors declare no competing interests. Supplementary Files AutoEMXSpdemo.mp4 Demonstration of AutoEMXSp AutoSEMEDSSI.pdf Supplementary Information Cite Share Download PDF Status: Under Review Version 2 posted You are reading this latest preprint version Show more versions 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-7837297","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[{"code":1,"date":"2025-10-14 11:06:22","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"articleType":"Article","associatedPublications":[],"authors":[{"id":529409451,"identity":"99747a76-a895-423d-888f-13be57291461","order_by":0,"name":"Andrea Giunto","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvElEQVRIiWNgGAWjYFACxgYQKccnwdxAipYEBmM2CUaitYBAAkNiG9Fa+PsXt0kX/rBJb5NubGD8UnGYsBaJGw/bpGckpOW2yRxsYJY5Q4QWhhsH26R5Eg7ntkkkNjBLtqUR1iEP1ZLORrQWg/ONYC0JIC2MH9tsCGsxvMHYbM2TlmYI8sthhjNEaJE7f/zhbR4bG3l+6eaDD39USBDWwiCRgGAf5iFCAzBiDiDYjD+I0jIKRsEoGAUjDQAAvJ84mNSUeeMAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0003-3363-5494","institution":"Lawrence Berkeley National Laboratory, Materials Sciences Division, Berkeley, CA, USA","correspondingAuthor":true,"prefix":"","firstName":"Andrea","middleName":"","lastName":"Giunto","suffix":""},{"id":529409452,"identity":"7ab2a592-586b-4ebf-9cd3-648379a3efd4","order_by":1,"name":"Yuxing Fei","email":"","orcid":"https://orcid.org/0000-0002-1225-2083","institution":"University of California, Berkeley","correspondingAuthor":false,"prefix":"","firstName":"Yuxing","middleName":"","lastName":"Fei","suffix":""},{"id":529409453,"identity":"62588396-637e-4d73-80b7-8742364ef9c7","order_by":2,"name":"Pragnay Nevatia","email":"","orcid":"","institution":"University of California, Berkeley","correspondingAuthor":false,"prefix":"","firstName":"Pragnay","middleName":"","lastName":"Nevatia","suffix":""},{"id":529409454,"identity":"4c03cf77-127f-4e68-9bef-a77924cb6ab2","order_by":3,"name":"Bernardus Rendy","email":"","orcid":"https://orcid.org/0000-0001-8309-6279","institution":"University of California, Berkeley","correspondingAuthor":false,"prefix":"","firstName":"Bernardus","middleName":"","lastName":"Rendy","suffix":""},{"id":529409455,"identity":"2ab7f1ae-ff7d-4b2a-954a-ce34ee01a1a8","order_by":4,"name":"Nathan Szymanski","email":"","orcid":"","institution":"University of California, Berkeley","correspondingAuthor":false,"prefix":"","firstName":"Nathan","middleName":"","lastName":"Szymanski","suffix":""},{"id":529409456,"identity":"99fd2f9b-9bde-4c67-9871-450f268ec080","order_by":5,"name":"Gerbrand Ceder","email":"","orcid":"https://orcid.org/0000-0001-9275-3605","institution":"University of California, Berkeley","correspondingAuthor":false,"prefix":"","firstName":"Gerbrand","middleName":"","lastName":"Ceder","suffix":""}],"badges":[],"createdAt":"2025-10-11 20:20:13","currentVersionCode":2,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7837297/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-7837297/v2","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100356963,"identity":"a63a2fc3-a667-4a09-a2cf-e4311fde667c","added_by":"auto","created_at":"2026-01-16 07:18:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5605391,"visible":true,"origin":"","legend":"","description":"","filename":"AutoSEMEDSv1.10.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7837297/v2_covered_cc856255-c04f-496e-875b-db0ac33d9bf4.pdf"},{"id":99838105,"identity":"79cf3e8a-285c-42c3-9bc4-beba9a16e036","added_by":"auto","created_at":"2026-01-08 19:57:42","extension":"mp4","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":133674221,"visible":true,"origin":"","legend":"Demonstration of AutoEMXSp","description":"","filename":"AutoEMXSpdemo.mp4","url":"https://assets-eu.researchsquare.com/files/rs-7837297/v2/9d510e234833d7b94520e85c.mp4"},{"id":99838104,"identity":"09e59a09-e8c7-4132-803a-7941d5a25436","added_by":"auto","created_at":"2026-01-08 19:57:40","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":14341099,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary Information\u003c/p\u003e","description":"","filename":"AutoSEMEDSSI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7837297/v2/eedbb918a1177a495e802d77.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eAccurate SEM‑EDS Quantification, Automation, and Machine Learning Enable High‑Throughput Compositional Characterization of Powders\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":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"automation, SEM, EDS, EDX, powders, particles, composition, phase, machine learning, self-driving, clustering, automated","lastPublishedDoi":"10.21203/rs.3.rs-7837297/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7837297/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCompositional characterization is essential for understanding and optimizing material performance. For powder-based materials underpinning many modern technologies, however, accurately and rapidly resolving the composition of individual constituent phases remains an unsolved challenge, slowing materials research and limiting autonomous laboratory platforms. Scanning electron microscopy with energy dispersive X-ray spectroscopy (SEM-EDS) offers a time- and cost-effective route, but artifacts generated by irregular particle morphologies fundamentally limit its reliability for quantitative compositional analysis. Here, we introduce a scalable particle-based SEM-EDS quantification scheme that overcomes these artifacts requiring only one experimental standard per element, including light elements conventionally difficult to quantify. This approach is integrated with automated measurements and unsupervised machine-learning analysis to enable identification and extraction of phase-level compositions within multiphase samples. Implemented as a fully automated Python-based framework, AutoEMXSp consistently achieves relative errors below 5–10% across diverse chemistries, resolving primary phases and intermixed impurities. This work removes a long-standing barrier to rapid powder compositional characterization, enabling seamless integration in autonomous laboratories for accelerated discovery.\u003c/p\u003e","manuscriptTitle":"Accurate SEM‑EDS Quantification, Automation, and Machine Learning Enable High‑Throughput Compositional Characterization of Powders","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2026-01-08 19:57:35","doi":"10.21203/rs.3.rs-7837297/v2","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"aa93fea1-acc7-416f-9978-d2b0d5d35cb3","owner":[],"postedDate":"January 8th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":60690657,"name":"Physical sciences/Materials science/Techniques and instrumentation/Characterization and analytical techniques"},{"id":60690658,"name":"Physical sciences/Materials science/Techniques and instrumentation/Microscopy/Scanning electron microscopy"}],"tags":[],"updatedAt":"2026-02-26T21:20:26+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-08 19:57:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v2","identity":"rs-7837297","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7837297","identity":"rs-7837297","version":["v2"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}