AI-Driven Feature Recognition of SEM Profiles in Deep Reactive Ion Etching Based on Physics-Constrained Variational Autoencoder

AI-Driven Feature Recognition of SEM Profiles in Deep Reactive Ion Etching Based on Physics-Constrained Variational Autoencoder | 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 AI-Driven Feature Recognition of SEM Profiles in Deep Reactive Ion Etching Based on Physics-Constrained Variational Autoencoder Yi Sun, Fang Wang, Hao Yu, Yechen Miao, Ke Sun, Heng Yang, Xinxin Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6758803/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 09 Mar, 2026 Read the published version in Microsystems & Nanoengineering → Version 1 posted 10 You are reading this latest preprint version Abstract Deep reactive ion etching (DRIE) is critical for fabricating high-aspect-ratio structures in microelectromechanical systems (MEMS), yet its complex, parameter-dependent process poses significant optimization challenges. Artificial intelligence (AI) offers an efficient optimization solution, but its implementation faces the technical challenge of acquiring large-scale data from scanning electron microscopy (SEM) images, the standard for evaluating DRIE etching outcomes. Traditional SEM analysis relies on labor-intensive manual methods, incurring 15-20% errors and hindering high-throughput manufacturing. Existing automated methods, such as CNNs and SVMs, falter with 70-80% accuracy in noisy SEM images, failing to capture the dynamic evolution of etched structures. To address these limitations, we propose a physics-constrained variational level set autoencoder (VLSet-AE) for automated SEM sectional-profile analysis. By integrating physical etching constraints and a three-dimensional framework (time, linewidth, etching depth), VLSet-AE achieves precise contour recognition and nine critical dimensions extraction—scallop depth (2.29%), scallop width (peak-to-peak: 2.05%, valley-to-valley: 6.28%), scallop radius (4.69%), profile angle (0.56%), trench depth (5.46%), bow width (4.35%), mid width (2.43%), and bottom width (4.78%)—with an average error of 3.65% an overall model accuracy of 94.3%, significantly outperforming manual annotation and state-of-the-art alternatives. Compared to seven current models (e.g., CNNs, LSTMs, ResNet), VLSet-AE achieves the shortest training time (20 s), fastest inference time (1.2 s), highest recognition accuracy (96%), and competitive memory usage (50 MB) and parameter count (4.0 million). By enabling efficient, large-scale data acquisition for AI-optimized DRIE processes, VLSet-AE empowers scalable, intelligent manufacturing, unlocking the potential for advanced microfabrication technologies. This approach provides a forward-looking framework for AI-driven MEMS process design and manufacturing, delivering innovative solutions for future AI-assisted microfabrication advancements. Physical sciences/Engineering/Electrical and electronic engineering Physical sciences/Nanoscience and technology/Other nanotechnology/Computational nanotechnology AI for Manufacturing Deep Reactive Ion Etching Scanning Electron Microscopy Artificial Intelligence Variational Autoencoder Image Recognition Full Text Additional Declarations There is no conflict of interest Supplementary Files SupplementalMaterial.zip Article supplemental material Cite Share Download PDF Status: Published Journal Publication published 09 Mar, 2026 Read the published version in Microsystems & Nanoengineering → Version 1 posted Editorial decision: revise 23 Jul, 2025 Review # 3 received at journal 21 Jul, 2025 Reviewer # 3 agreed at journal 14 Jul, 2025 Review # 1 received at journal 22 Jun, 2025 Reviewer # 2 agreed at journal 04 Jun, 2025 Reviewer # 1 agreed at journal 02 Jun, 2025 Reviewers invited by journal 30 May, 2025 Submission checks completed at journal 27 May, 2025 Editor assigned by journal 27 May, 2025 First submitted to journal 27 May, 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-6758803","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":463977085,"identity":"e519d3b4-6f4b-4c5b-9e56-2041a26a1722","order_by":0,"name":"Yi Sun","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1UlEQVRIiWNgGAWjYLCChAoGBjZ2EIN4LWeAWphJ0sLYBiSYiVUtPyP3mMTDedvk+ZgZmD88zGGQ529gfvYAnxaDG3lpEonbbhu2MTOwARkMhjMOsJkb4NUikWMG0sII0sIA1MK4gYGHTQK/w0Ba5ty2bwM5DKjFnqAWhhsgLQ23E4FaGEAOSySoxeDMG2OLhGO3k9uYGduAWiSSZxxmM8PvsPYcw5s/am7bzm9vPvzx5zYb2/725mf4HcbAwAJVwNgAJCSIiiDmD4TVjIJRMApGwYgGAEjaPynBoS3vAAAAAElFTkSuQmCC","orcid":"","institution":"Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences","correspondingAuthor":true,"prefix":"","firstName":"Yi","middleName":"","lastName":"Sun","suffix":""},{"id":463977086,"identity":"fa75513d-fff6-4787-b607-137ab37e058e","order_by":1,"name":"Fang Wang","email":"","orcid":"https://orcid.org/0009-0006-5073-8806","institution":"Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Fang","middleName":"","lastName":"Wang","suffix":""},{"id":463977087,"identity":"37ac9195-2027-4b70-a807-9a4320f5d35a","order_by":2,"name":"Hao Yu","email":"","orcid":"","institution":"Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Hao","middleName":"","lastName":"Yu","suffix":""},{"id":463977088,"identity":"87b6f372-6755-42c4-8230-d41020ee8eab","order_by":3,"name":"Yechen Miao","email":"","orcid":"","institution":"Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Yechen","middleName":"","lastName":"Miao","suffix":""},{"id":463977089,"identity":"b89770e9-04c2-40be-9202-ae86f1ea2c69","order_by":4,"name":"Ke Sun","email":"","orcid":"","institution":"Shanghai Institute of Microsystem and Information Technology","correspondingAuthor":false,"prefix":"","firstName":"Ke","middleName":"","lastName":"Sun","suffix":""},{"id":463977090,"identity":"8d921c69-dad9-40b5-9b0a-6ac5318bfca1","order_by":5,"name":"Heng Yang","email":"","orcid":"https://orcid.org/0000-0002-8873-9576","institution":"Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Heng","middleName":"","lastName":"Yang","suffix":""},{"id":463977091,"identity":"4a3a786d-5762-4844-9bb4-c17cbccb6d66","order_by":6,"name":"Xinxin Li","email":"","orcid":"","institution":"Shanghai Institute of Microsystem and Information Technology,CAS","correspondingAuthor":false,"prefix":"","firstName":"Xinxin","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-05-27 11:11:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6758803/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6758803/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41378-025-01105-z","type":"published","date":"2026-03-09T04:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":104292176,"identity":"be9540ee-b48a-483b-a4d1-a96a15e70264","added_by":"auto","created_at":"2026-03-10 07:11:23","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2892325,"visible":true,"origin":"","legend":"Article File","description":"","filename":"AIDrivenSEMProfileRecognitioninDRIEUsingVLSetAE.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6758803/v1_covered_404816cb-0495-489e-9e88-caf7359822e9.pdf"},{"id":83754405,"identity":"83a478bc-9b62-4304-9556-f13adeb10230","added_by":"auto","created_at":"2025-06-02 08:00:09","extension":"zip","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":91915189,"visible":true,"origin":"","legend":"Article supplemental material","description":"","filename":"SupplementalMaterial.zip","url":"https://assets-eu.researchsquare.com/files/rs-6758803/v1/e4de8d08a510beea03efbb2e.zip"}],"financialInterests":"There is no conflict of interest","formattedTitle":"AI-Driven Feature Recognition of SEM Profiles in Deep Reactive Ion Etching Based on Physics-Constrained Variational Autoencoder","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":"microsystems-and-nanoengineering","isNatureJournal":false,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"micronano","sideBox":"Learn more about [Microsystems \u0026 Nanoengineering](http://www.nature.com/micronano/)","snPcode":"41378","submissionUrl":"https://mts-micronano.nature.com/","title":"Microsystems \u0026 Nanoengineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"AI for Manufacturing, Deep Reactive Ion Etching, Scanning Electron Microscopy, Artificial Intelligence, Variational Autoencoder, Image Recognition","lastPublishedDoi":"10.21203/rs.3.rs-6758803/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6758803/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Deep reactive ion etching (DRIE) is critical for fabricating high-aspect-ratio structures in microelectromechanical systems (MEMS), yet its complex, parameter-dependent process poses significant optimization challenges. Artificial intelligence (AI) offers an efficient optimization solution, but its implementation faces the technical challenge of acquiring large-scale data from scanning electron microscopy (SEM) images, the standard for evaluating DRIE etching outcomes. Traditional SEM analysis relies on labor-intensive manual methods, incurring 15-20% errors and hindering high-throughput manufacturing. Existing automated methods, such as CNNs and SVMs, falter with 70-80% accuracy in noisy SEM images, failing to capture the dynamic evolution of etched structures. To address these limitations, we propose a physics-constrained variational level set autoencoder (VLSet-AE) for automated SEM sectional-profile analysis. By integrating physical etching constraints and a three-dimensional framework (time, linewidth, etching depth), VLSet-AE achieves precise contour recognition and nine critical dimensions extraction—scallop depth (2.29%), scallop width (peak-to-peak: 2.05%, valley-to-valley: 6.28%), scallop radius (4.69%), profile angle (0.56%), trench depth (5.46%), bow width (4.35%), mid width (2.43%), and bottom width (4.78%)—with an average error of 3.65% an overall model accuracy of 94.3%, significantly outperforming manual annotation and state-of-the-art alternatives. Compared to seven current models (e.g., CNNs, LSTMs, ResNet), VLSet-AE achieves the shortest training time (20 s), fastest inference time (1.2 s), highest recognition accuracy (96%), and competitive memory usage (50 MB) and parameter count (4.0 million). By enabling efficient, large-scale data acquisition for AI-optimized DRIE processes, VLSet-AE empowers scalable, intelligent manufacturing, unlocking the potential for advanced microfabrication technologies. This approach provides a forward-looking framework for AI-driven MEMS process design and manufacturing, delivering innovative solutions for future AI-assisted microfabrication advancements.","manuscriptTitle":"AI-Driven Feature Recognition of SEM Profiles in Deep Reactive Ion Etching Based on Physics-Constrained Variational Autoencoder","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-02 08:00:03","doi":"10.21203/rs.3.rs-6758803/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"revise","date":"2025-07-24T00:37:32+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"This content is not available.","date":"2025-07-22T02:16:21+00:00","index":3,"fulltext":"This content is not available."},{"type":"reviewerAgreed","content":"This content is not available.","date":"2025-07-14T07:01:38+00:00","index":3,"fulltext":"This content is not available."},{"type":"editorInvitedReview","content":"This content is not available.","date":"2025-06-22T08:15:10+00:00","index":1,"fulltext":"This content is not available."},{"type":"reviewerAgreed","content":"This content is not available.","date":"2025-06-04T13:30:47+00:00","index":2,"fulltext":"This content is not available."},{"type":"reviewerAgreed","content":"This content is not available.","date":"2025-06-03T01:34:06+00:00","index":1,"fulltext":"This content is not available."},{"type":"reviewersInvited","content":"","date":"2025-05-30T06:06:35+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-28T03:04:05+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-27T11:07:16+00:00","index":"","fulltext":""},{"type":"submitted","content":"Microsystems \u0026 Nanoengineering","date":"2025-05-27T11:07:15+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"microsystems-and-nanoengineering","isNatureJournal":false,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"micronano","sideBox":"Learn more about [Microsystems \u0026 Nanoengineering](http://www.nature.com/micronano/)","snPcode":"41378","submissionUrl":"https://mts-micronano.nature.com/","title":"Microsystems \u0026 Nanoengineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"1699f200-1ad2-4698-b2b7-90753e8724e0","owner":[],"postedDate":"June 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":49267154,"name":"Physical sciences/Engineering/Electrical and electronic engineering"},{"id":49267155,"name":"Physical sciences/Nanoscience and technology/Other nanotechnology/Computational nanotechnology"}],"tags":[],"updatedAt":"2026-03-10T07:10:25+00:00","versionOfRecord":{"articleIdentity":"rs-6758803","link":"https://doi.org/10.1038/s41378-025-01105-z","journal":{"identity":"microsystems-and-nanoengineering","isVorOnly":false,"title":"Microsystems \u0026 Nanoengineering"},"publishedOn":"2026-03-09 04:00:00","publishedOnDateReadable":"March 9th, 2026"},"versionCreatedAt":"2025-06-02 08:00:03","video":"","vorDoi":"10.1038/s41378-025-01105-z","vorDoiUrl":"https://doi.org/10.1038/s41378-025-01105-z","workflowStages":[]},"version":"v1","identity":"rs-6758803","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6758803","identity":"rs-6758803","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}