Three-dimensional biphase fabric estimation from 2D images by deep learning

Three-dimensional biphase fabric estimation from 2D images by 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 Article Three-dimensional biphase fabric estimation from 2D images by deep learning Daniel Chou, Matias Etcheverry, Chloe Arson This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2531479/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 18 Apr, 2024 Read the published version in Scientific Reports → Version 1 posted 7 You are reading this latest preprint version Abstract A pruned VGG19 model subjected to Axial Coronal Sagittal (ACS) convolutions and a custom VGG16 model are benchmarked to predict 3D fabric descriptors from a set of 2D images. The data used for training and testing are extracted from a set of 600 3D biphase microstructures created numerically. Fabric descriptors calculated from the 3D microstructures constitute the ground truth, while the input data are obtained by slicing the 3D microstructures in each direction of space at regular intervals. The computational cost to train the custom ACS-VGG19 model increases linearly with p (the number of images extracted in each direction of space), and increasing p does not improve the performance of the model - or only does so marginally. The best performing ACS-VGG19 model provides a MAPE of 2 to 5% for the means of aggregate size, aspect ratios and solidity, but cannot be used to estimate orientations. The custom VGG16 yields a MAPE of 2% or less for the means of aggregate size, distance to nearest neighbor, aspect ratios and solidity. The MAPE is less than 3% for the mean roundness, and in the range of 5-7% for the aggregate volume fraction and the mean diagonal components of the orientation matrix. Increasing p improves the performance of the custom VGG16 model, but becomes cost ineffective beyond 3 images per direction. For both models, the aggregate volume fraction is predicted with less accuracy than higher order descriptors, which is attributed to the bias given by the loss function towards highly-correlated descriptors. Both models perform better to predict means than standard deviations, which are noisy quantities. The custom VGG16 model performs better than the pruned version of the ACS-VGG19 model, likely because it contains 3 times (p = 1) to 28 times (p = 10) less parameters than the ACS-VGG19 model, allowing better and faster cnvergence, with less data. The custom VGG16 model predicts the second and third invariants of the orientation matrix with a MAPE of 2.8% and 8.9%, respectively, which suggests that the model can predict orientation descriptors regardless of the orientation of the input images. Physical sciences/Engineering/Civil engineering Physical sciences/Mathematics and computing/Computational science Physical sciences/Materials science/Structural materials/Composites Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 18 Apr, 2024 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 25 Jan, 2024 Reviewers agreed at journal 21 Oct, 2023 Reviewers invited by journal 13 Sep, 2023 Editor assigned by journal 24 Feb, 2023 Editor invited by journal 24 Feb, 2023 Submission checks completed at journal 24 Feb, 2023 First submitted to journal 30 Jan, 2023 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-2531479","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":178584186,"identity":"0031259c-360b-41d9-9d81-5da574ffb993","order_by":0,"name":"Daniel Chou","email":"","orcid":"","institution":"Georgia Institute of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Daniel","middleName":"","lastName":"Chou","suffix":""},{"id":178584188,"identity":"fba2546f-c460-4f05-a6bf-ddfee74bbc88","order_by":1,"name":"Matias Etcheverry","email":"","orcid":"","institution":"École des Ponts ParisTech","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Matias","middleName":"","lastName":"Etcheverry","suffix":""},{"id":178584189,"identity":"5a9ad870-a466-4a4b-8d0a-4fd6943d16e6","order_by":2,"name":"Chloe Arson","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCklEQVRIiWNgGAWjYDACCeYGGJPxAYzFDOI1YCqGakFIMRuAKTYStLBJEKWFf3Zj44MPDHb58u29xyp+VDDY9c9vPvi5gMFGdsMBHJbcOdhsOIMh2XLDmXNpN3vOMCTPOMaWLD2DIc0YlxYDicQ2aR6gNwwkcsxuM7YxJDMc4zFj5mE4nIhXyx+GegP5GTlmxYz/GJLlj/F/A2r5j18LA8NhA4YbOWbMQC/bGRzjYQNqOYBTi8SNxGbDHoPjBgZnzhhL9hyTSDA8lmYszWOQbDwThxb+GckHH/yoqDaQb+8x/PCjxsZe7vDhh595Kuxk+3BogToPYWtiA5oIYWBPgtpRMApGwSgYIQAAh7xWg4RF7TgAAAAASUVORK5CYII=","orcid":"","institution":"Georgia Institute of Technology","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Chloe","middleName":"","lastName":"Arson","suffix":""}],"badges":[],"createdAt":"2023-01-30 22:59:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-2531479/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2531479/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-024-59554-x","type":"published","date":"2024-04-18T22:47:49+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":55690697,"identity":"76b3497d-3335-49f6-a2f0-088fc2fa362f","added_by":"auto","created_at":"2024-05-01 22:48:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":7470941,"visible":true,"origin":"","legend":"","description":"","filename":"3Dfabricfrom2Dimages.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2531479/v1_covered_a4520774-f5dd-4fbf-847c-ab0bff0c56a3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Three-dimensional biphase fabric estimation from 2D images by deep learning","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-2531479/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2531479/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"A pruned VGG19 model subjected to Axial Coronal Sagittal (ACS) convolutions and a custom VGG16 model are benchmarked to predict 3D fabric descriptors from a set of 2D images. The data used for training and testing are extracted from a set of 600 3D biphase microstructures created numerically. Fabric descriptors calculated from the 3D microstructures constitute the ground truth, while the input data are obtained by slicing the 3D microstructures in each direction of space at regular intervals. The computational cost to train the custom ACS-VGG19 model increases linearly with p (the number of images extracted in each direction of space), and increasing p does not improve the performance of the model - or only does so marginally. The best performing ACS-VGG19 model provides a MAPE of 2 to 5% for the means of aggregate size, aspect ratios and solidity, but cannot be used to estimate orientations. The custom VGG16 yields a MAPE of 2% or less for the means of aggregate size, distance to nearest neighbor, aspect ratios and solidity. The MAPE is less than 3% for the mean roundness, and in the range of 5-7% for the aggregate volume fraction and the mean diagonal components of the orientation matrix. Increasing p improves the performance of the custom VGG16 model, but becomes cost ineffective beyond 3 images per direction. For both models, the aggregate volume fraction is predicted with less accuracy than higher order descriptors, which is attributed to the bias given by the loss function towards highly-correlated descriptors. Both models perform better to predict means than standard deviations, which are noisy quantities. The custom VGG16 model performs better than the pruned version of the ACS-VGG19 model, likely because it contains 3 times (p = 1) to 28 times (p = 10) less parameters than the ACS-VGG19 model, allowing better and faster cnvergence, with less data. The custom VGG16 model predicts the second and third invariants of the orientation matrix with a MAPE of 2.8% and 8.9%, respectively, which suggests that the model can predict orientation descriptors regardless of the orientation of the input images.","manuscriptTitle":"Three-dimensional biphase fabric estimation from 2D images by deep learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-02-28 01:55:13","doi":"10.21203/rs.3.rs-2531479/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-01-25T08:57:15+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"a52bd472-2dcd-4fe9-9cd6-6baf29f26bda","date":"2023-10-21T05:27:29+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2023-09-13T09:09:45+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2023-02-24T10:28:19+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2023-02-24T06:27:24+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2023-02-24T06:16:50+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2023-01-30T22:51:09+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":"07f4f854-f9a8-488c-a1c0-43e0f089f69c","owner":[],"postedDate":"February 28th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":19452316,"name":"Physical sciences/Engineering/Civil engineering"},{"id":19452317,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":19452318,"name":"Physical sciences/Materials science/Structural materials/Composites"}],"tags":[],"updatedAt":"2024-05-01T22:47:49+00:00","versionOfRecord":{"articleIdentity":"rs-2531479","link":"https://doi.org/10.1038/s41598-024-59554-x","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2024-04-18 22:47:49","publishedOnDateReadable":"April 18th, 2024"},"versionCreatedAt":"2023-02-28 01:55:13","video":"","vorDoi":"10.1038/s41598-024-59554-x","vorDoiUrl":"https://doi.org/10.1038/s41598-024-59554-x","workflowStages":[]},"version":"v1","identity":"rs-2531479","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2531479","identity":"rs-2531479","version":["v1"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}