Transfer Learning Across Material Properties Using Center-Environment Features: From Energetics to Mechanical Properties in Multi-Component Mo Alloys

Transfer Learning Across Material Properties Using Center-Environment Features: From Energetics to Mechanical Properties in Multi-Component Mo Alloys | 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 Research Article Transfer Learning Across Material Properties Using Center-Environment Features: From Energetics to Mechanical Properties in Multi-Component Mo Alloys Liqin Qin, Yuchao Tang, Limin Zhang, Bin Xiao, Wenyi Huo, Yi Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9567697/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Transfer learning (TL) provides a viable approach to mitigate data scarcity in materials informatics. While conventional TL focuses on predicting identical properties across different systems, this work demonstrates, for the first time, its extension to predict distinctly different material properties—substantially improving computational efficiency given the typically higher cost of acquiring target-domain data. To accelerate computational alloy design, machine learning models using Center-Environment (CE) features were first developed to predict substitution energies of alloying elements in molybdenum (Mo)-based alloys. The Random Forest models achieved the optimal performance and transferability—R 2 = 0.97, = 0.11 eV, and = 0.16 eV—against the density functional theory (DFT) benchmark. The model dependency of feature selection and importance analysis were discussed. The transferability of the energy models was validated on unknown systems with new elements. Subsequently, the energy models were fine-tuned using limited mechanical property data to construct energy-to-property (E2P) TL models capable of predicting elastic properties, including bulk modulus, Young’s modulus, shear modulus, and elastic constants, achieving an improved accuracy over the non-transferred ML by ~ 10–30%, with its transferability verified by additional DFT calculations. This cross-property E2P transfer learning framework opens a new avenue for accelerating computational materials discovery and is generally applicable to other multi-property predictions governed by similar physical principles. Transfer machine learning Center-environment feature Intelligent alloy design Mechanical property Multi-component Mo-based alloys Full Text Additional Declarations The authors declare no competing interests. Supplementary Files MoMLSupMat.docx Supplementary Materials of Transfer Learning Across Material Properties Using Center-Environment Features: From Energetics to Mechanical Properties in Multi-Component Mo Alloys Cite Share Download PDF Status: Posted Version 1 posted 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-9567697","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":631890645,"identity":"cac4584e-6e07-4f61-aa54-8be28d2c6417","order_by":0,"name":"Liqin Qin","email":"","orcid":"","institution":"Materials Genome Institute \u0026 State Key Laboratory of Materials for Advanced Nuclear Energy, Shanghai University, Shanghai 200444, China","correspondingAuthor":false,"prefix":"","firstName":"Liqin","middleName":"","lastName":"Qin","suffix":""},{"id":631890919,"identity":"121317aa-09de-4ce9-9b31-293a4fde58f6","order_by":1,"name":"Yuchao Tang","email":"","orcid":"","institution":"Materials Genome Institute \u0026 State Key Laboratory of Materials for Advanced Nuclear Energy, Shanghai University, Shanghai 200444, China","correspondingAuthor":false,"prefix":"","firstName":"Yuchao","middleName":"","lastName":"Tang","suffix":""},{"id":631890920,"identity":"0717bf08-646c-4823-8d05-15b962684b14","order_by":2,"name":"Limin Zhang","email":"","orcid":"","institution":"Materials Genome Institute \u0026 State Key Laboratory of Materials for Advanced Nuclear Energy, Shanghai University, Shanghai 200444, China","correspondingAuthor":false,"prefix":"","firstName":"Limin","middleName":"","lastName":"Zhang","suffix":""},{"id":631890921,"identity":"0c9845c6-436c-44fa-9f3c-ac418d885898","order_by":3,"name":"Bin Xiao","email":"","orcid":"","institution":"Materials Genome Institute \u0026 State Key Laboratory of Materials for Advanced Nuclear Energy, Shanghai University, Shanghai 200444, China","correspondingAuthor":false,"prefix":"","firstName":"Bin","middleName":"","lastName":"Xiao","suffix":""},{"id":631890922,"identity":"c916933d-6bd7-4155-a671-cb49259b1d4b","order_by":4,"name":"Wenyi Huo","email":"","orcid":"","institution":"NOMATEN Centre of Excellence, National Centre for Nuclear Research, Otwock 05-400, Poland","correspondingAuthor":false,"prefix":"","firstName":"Wenyi","middleName":"","lastName":"Huo","suffix":""},{"id":631890923,"identity":"f682f89d-1fa0-4b30-9aa0-d287fc8d28ab","order_by":5,"name":"Yi Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAsUlEQVRIiWNgGAWjYDACZuaGAwwVDAkgtgSRWhiBWs6QpIWBsYGBsY0ULQbHGRsP886ryzM4wHzwNg+DXR5hLYcZGw7zbjtcbHCALdmahyG5mFgtBxI3HOAxk+ZhOJDYQJyWOXVALfzfSNHSwAyyhY04LZJALQfnHDucOPMwm7HlHINkwlr4zh8+/OFNTV1i3/HmhzfeVNgR1qJwAMZiBruTkHogkCdo6CgYBaNgFIwCANEiP+R3O7JxAAAAAElFTkSuQmCC","orcid":"","institution":"Materials Genome Institute \u0026 State Key Laboratory of Materials for Advanced Nuclear Energy, Shanghai University, Shanghai 200444, China","correspondingAuthor":true,"prefix":"","firstName":"Yi","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2026-04-29 15:17:08","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9567697/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9567697/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108381999,"identity":"325989c1-5d33-4944-9eb4-967488476bec","added_by":"auto","created_at":"2026-05-04 05:12:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1540478,"visible":true,"origin":"","legend":"","description":"","filename":"MoMLMs.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9567697/v1_covered_f631db46-cff6-42de-8dc2-0c1197f2ff8b.pdf"},{"id":108381990,"identity":"4db7d43d-8f88-4fa3-9471-a68a9d99e16b","added_by":"auto","created_at":"2026-05-04 05:12:00","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":5931033,"visible":true,"origin":"","legend":"\u003ch1\u003e\u003cstrong\u003eSupplementary Materials of Transfer Learning Across Material Properties Using Center-Environment Features: From Energetics to Mechanical Properties in Multi-Component Mo Alloys\u003c/strong\u003e\u003c/h1\u003e","description":"","filename":"MoMLSupMat.docx","url":"https://assets-eu.researchsquare.com/files/rs-9567697/v1/afc71dc8457dc959a7a8f7df.docx"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eTransfer Learning Across Material Properties Using Center-Environment Features: From Energetics to Mechanical Properties in Multi-Component Mo Alloys\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[{"identity":"7b313d47-5253-4a66-bfa7-9e80179c0ad2","identifier":"10.13039/501100001809","name":"National Natural Science Foundation of China","awardNumber":"No. 52373227","order_by":0},{"identity":"340928dc-c927-44de-8ddf-85d4219f844e","identifier":"10.13039/501100012166","name":"National Key Research and Development Program of China","awardNumber":"Nos. 2017YFB0701502 and 2017YFB0702901","order_by":1}],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Materials Genome Institute \u0026 State Key Laboratory of Materials for Advanced Nuclear Energy, Shanghai University, Shanghai 200444, China","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Transfer machine learning, Center-environment feature, Intelligent alloy design, Mechanical property, Multi-component Mo-based alloys","lastPublishedDoi":"10.21203/rs.3.rs-9567697/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9567697/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTransfer learning (TL) provides a viable approach to mitigate data scarcity in materials informatics. While conventional TL focuses on predicting identical properties across different systems, this work demonstrates, for the first time, its extension to predict distinctly different material properties\u0026mdash;substantially improving computational efficiency given the typically higher cost of acquiring target-domain data. To accelerate computational alloy design, machine learning models using Center-Environment (CE) features were first developed to predict substitution energies of alloying elements in molybdenum (Mo)-based alloys. The Random Forest models achieved the optimal performance and transferability\u0026mdash;R\u003csup\u003e2\u003c/sup\u003e= 0.97, \u0026lt;MAE\u0026thinsp;\u0026gt;\u0026thinsp;=\u0026thinsp;0.11 eV, and \u0026lt;RMSE\u0026thinsp;\u0026gt;\u0026thinsp;=\u0026thinsp;0.16 eV\u0026mdash;against the density functional theory (DFT) benchmark. The model dependency of feature selection and importance analysis were discussed. The transferability of the energy models was validated on unknown systems with new elements. Subsequently, the energy models were fine-tuned using limited mechanical property data to construct energy-to-property (E2P) TL models capable of predicting elastic properties, including bulk modulus, Young\u0026rsquo;s modulus, shear modulus, and elastic constants, achieving an improved accuracy over the non-transferred ML by ~\u0026thinsp;10\u0026ndash;30%, with its transferability verified by additional DFT calculations. This cross-property E2P transfer learning framework opens a new avenue for accelerating computational materials discovery and is generally applicable to other multi-property predictions governed by similar physical principles.\u003c/p\u003e","manuscriptTitle":"Transfer Learning Across Material Properties Using Center-Environment Features: From Energetics to Mechanical Properties in Multi-Component Mo Alloys","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-04 05:11:46","doi":"10.21203/rs.3.rs-9567697/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"b287f69b-1cf9-4251-9714-a1f5d147f67d","owner":[],"postedDate":"May 4th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-04T05:11:46+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-04 05:11:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9567697","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9567697","identity":"rs-9567697","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}