Generalized Machine Learning Potential Models for Elemental Nanoclusters

Generalized Machine Learning Potential Models for Elemental Nanoclusters | 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 Generalized Machine Learning Potential Models for Elemental Nanoclusters Subramanian Sankaranarayanan, Suvo Banik, Abhishek Aggarwal, Sukriti Manna, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7106351/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 Nanoclusters occupy a unique size regime between isolated atoms and bulk materials. Their electronic, structural, and thermodynamic properties are governed by quantum effects and complex many-body interactions. Accurately modeling their potential energy surfaces (PES) is essential for understanding their behavior and applications in areas such as catalysis, nanoelectronics, and energy storage. In this work, we develop Gaussian Approximation Potential (GAP) models to describe a comprehensive 54 elemental nanoclusters across the periodic table. GAP, a machine learning interatomic potential (MLIP), learns the PES directly from ab-initio data and has proven effective in accurately modeling systems with low symmetry, structural diversity, and complex energetics. Our approach utilizes a diverse training and test dataset of over 170,000 nanocluster configurations obtained with targeted sampling strategies and high-fidelity density functional theory (DFT) calculations. The GAP models are rigorously benchmarked against DFT, demonstrating strong agreement in energy and force predictions, robust structural and dynamical performance across cluster sizes and chemistries, and accurate reproduction of phase and dynamic behavior. We further assess the generalization of the model in both the cluster and the bulk regimes via performance analysis of their structural properties. Despite the wide structural diversity in the dataset, the framework achieves high accuracy and transferability by combining structural weighting with a Bayesian training approach. Our work establishes a comprehensive testbed of MLIPs for low-dimensional systems across a wide chemical space spanning s-, p-, and d-block elements, offering a path toward universal potentials with ab-initio fidelity. Physical sciences/Materials science/Theory and computation/Atomistic models Physical sciences/Materials science/Nanoscale materials/Nanoparticles Full Text Additional Declarations There is NO Competing Interest. Supplementary Files supplementary.pdf Supplementary information for Generalized Machine Learning Potential Models for Elemental Nanoclusters 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-7106351","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":500121584,"identity":"a47a07e5-1811-4bb5-abae-0c324b940846","order_by":0,"name":"Subramanian Sankaranarayanan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAu0lEQVRIiWNgGAWjYDACHghlwM/A2ACkmUnQItlAshaDA2CaCC3yPWcff/xRc8fY+EZy4weGCuvEBkJaDM62m0nzHHtmZnYjsVmC4Uw6EVr42diYGdgO2wC1tDEwth0mrEW+n435449/h22MZ4C0/CNCC8PZNgYJ3rbDZgYSIC0NRGgxOHOMTZq377CxxJmHzRIJx9KNCTusJw3osG+HDfvb0x9++FBjLUvYYSgggTTlo2AUjIJRMApwAQBGcT0Yh0qx6wAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-9708-396X","institution":"Argonne National Laboratory","correspondingAuthor":true,"prefix":"","firstName":"Subramanian","middleName":"","lastName":"Sankaranarayanan","suffix":""},{"id":500121585,"identity":"521bbdf8-cc04-4596-a33c-af1d1bdd36be","order_by":1,"name":"Suvo Banik","email":"","orcid":"","institution":"Argonne National Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Suvo","middleName":"","lastName":"Banik","suffix":""},{"id":500121586,"identity":"307c5058-7f59-4e90-8838-49c2a4585e48","order_by":2,"name":"Abhishek Aggarwal","email":"","orcid":"","institution":"Argonne National Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Abhishek","middleName":"","lastName":"Aggarwal","suffix":""},{"id":500121587,"identity":"2536faa3-df03-4599-b5e1-623f80fb153b","order_by":3,"name":"Sukriti Manna","email":"","orcid":"","institution":"University of Illinois at Chicago","correspondingAuthor":false,"prefix":"","firstName":"Sukriti","middleName":"","lastName":"Manna","suffix":""},{"id":500121588,"identity":"e3a2be21-59a8-40fb-81f1-f378f723afa9","order_by":4,"name":"Partha Dutta","email":"","orcid":"","institution":"University of Illinois at Chicago","correspondingAuthor":false,"prefix":"","firstName":"Partha","middleName":"","lastName":"Dutta","suffix":""}],"badges":[],"createdAt":"2025-07-12 07:10:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7106351/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7106351/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95656048,"identity":"e799290e-afdd-46a2-8b62-c69488cd4432","added_by":"auto","created_at":"2025-11-11 16:17:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1847007,"visible":true,"origin":"","legend":"Article File","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7106351/v1_covered_d6e2d4b9-5991-417a-9781-983c64a02537.pdf"},{"id":89245808,"identity":"73c18267-d2ee-4066-8a55-30f29e47a37d","added_by":"auto","created_at":"2025-08-18 01:39:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1244767,"visible":true,"origin":"","legend":"Supplementary information for Generalized Machine Learning Potential Models for Elemental Nanoclusters","description":"","filename":"supplementary.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7106351/v1/c08731c7e2705c13b89b4113.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Generalized Machine Learning Potential Models for Elemental Nanoclusters","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","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":"","lastPublishedDoi":"10.21203/rs.3.rs-7106351/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7106351/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Nanoclusters occupy a unique size regime between isolated atoms and bulk materials. Their electronic, structural, and thermodynamic properties are governed by quantum effects and complex many-body interactions. Accurately modeling their potential energy surfaces (PES) is essential for understanding their behavior and applications in areas such as catalysis, nanoelectronics, and energy storage. In this work, we develop Gaussian Approximation Potential (GAP) models to describe a comprehensive 54 elemental nanoclusters across the periodic table. GAP, a machine learning interatomic potential (MLIP), learns the PES directly from ab-initio data and has proven effective in accurately modeling systems with low symmetry, structural diversity, and complex energetics. Our approach utilizes a diverse training and test dataset of over 170,000 nanocluster configurations obtained with targeted sampling strategies and high-fidelity density functional theory (DFT) calculations. The GAP models are rigorously benchmarked against DFT, demonstrating strong agreement in energy and force predictions, robust structural and dynamical performance across cluster sizes and chemistries, and accurate reproduction of phase and dynamic behavior. We further assess the generalization of the model in both the cluster and the bulk regimes via performance analysis of their structural properties. Despite the wide structural diversity in the dataset, the framework achieves high accuracy and transferability by combining structural weighting with a Bayesian training approach. Our work establishes a comprehensive testbed of MLIPs for low-dimensional systems across a wide chemical space spanning s-, p-, and d-block elements, offering a path toward universal potentials with ab-initio fidelity.","manuscriptTitle":"Generalized Machine Learning Potential Models for Elemental Nanoclusters","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-18 01:39:22","doi":"10.21203/rs.3.rs-7106351/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":"3aff6c2d-043d-4675-9978-ca4146ab6fd8","owner":[],"postedDate":"August 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":53129170,"name":"Physical sciences/Materials science/Theory and computation/Atomistic models"},{"id":53129171,"name":"Physical sciences/Materials science/Nanoscale materials/Nanoparticles"}],"tags":[],"updatedAt":"2025-11-10T20:20:54+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-18 01:39:22","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7106351","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7106351","identity":"rs-7106351","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}