NEP89: Universal neuroevolution potential for inorganic and organic materials across 89 elements

NEP89: Universal neuroevolution potential for inorganic and organic materials across 89 elements | 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 NEP89: Universal neuroevolution potential for inorganic and organic materials across 89 elements Jianbin Xu, Ting Liang, Ke Xu, Eric Lindgren, Zherui Chen, Rui Zhao, and 13 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7058411/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract While machine-learned interatomic potentials offer near-quantum-mechanical accuracy for atomistic simulations, many are material-specific or computationally intensive, limiting their broader use. Here we introduce NEP89, a foundation model based on neuroevolution potential architecture, delivering empirical-potential-like speed and high accuracy across 89 elements. A compact yet comprehensive training dataset covering inorganic and organic materials was curated through descriptor-space subsampling and iterative refinement across multiple datasets. NEP89 achieves competitive accuracy compared to representative foundation models while being three to four orders of magnitude more computationally efficient, enabling previously impractical large-scale atomistic simulations of inorganic and organic systems. In addition to its out-of-the-box applicability to diverse scenarios, including million-atom-scale compression of compositionally complex alloys, ion diffusion in solid-state electrolytes and water, rocksalt dissolution, methane combustion, and protein-ligand dynamics, NEP89 also supports fine-tuning for rapid adaptation to user-specific applications, such as mechanical, thermal, structural, and spectral properties of two-dimensional materials, metallic glasses, and organic crystals. Physical sciences/Materials science/Theory and computation/Atomistic models Physical sciences/Materials science/Theory and computation/Computational methods Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SupplementaryInformation.pdf Supplementary Information Cite Share Download PDF Status: Under Review 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-7058411","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":497310867,"identity":"9b56e803-06b7-4741-87ae-1724659f9746","order_by":0,"name":"Jianbin Xu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1klEQVRIiWNgGAWjYBACxhlA4gOYycMMJIBYgo2wFrA24rUwSACV8ZCkhXl2j5m0TYUNA/+M3MMGDBXWiQ3SbQn4HTbnWJp0zpk0BokbeckJDGfSExtkjh0g4JfkY9K5bYcZDCRyjA8wth1ObJBIbyCgJbFN2vLff6iWf0RpAdrC2HAArCWBsQGkJY2Aw+YcS7bsOZbMI3HmjbFBwrF04zaJtAS8Wgxn9xje+FFjJ8ffnmMs8aHGWrZfIs0AvxaouyFRAzKeUEQyyBNSMApGwSgYBaOAAQD1Oz/xZrbDwAAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0003-0509-9508","institution":"The Chinese University of Hong Kong","correspondingAuthor":true,"prefix":"","firstName":"Jianbin","middleName":"","lastName":"Xu","suffix":""},{"id":497310868,"identity":"2f41c152-abfd-45cb-8b2c-c58802d812b6","order_by":1,"name":"Ting Liang","email":"","orcid":"https://orcid.org/0000-0002-3116-365X","institution":"The Chinese University of Hong Kong","correspondingAuthor":false,"prefix":"","firstName":"Ting","middleName":"","lastName":"Liang","suffix":""},{"id":497310869,"identity":"ddc06516-da3c-4b86-af13-d6213a288e15","order_by":2,"name":"Ke Xu","email":"","orcid":"","institution":"The Chinese University of Hong Kong","correspondingAuthor":false,"prefix":"","firstName":"Ke","middleName":"","lastName":"Xu","suffix":""},{"id":497310870,"identity":"b28c9e5b-2afc-4251-a3cf-ef13948f4ca4","order_by":3,"name":"Eric Lindgren","email":"","orcid":"https://orcid.org/0000-0002-8549-6839","institution":"Chalmers University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Eric","middleName":"","lastName":"Lindgren","suffix":""},{"id":497310871,"identity":"6516f787-2a86-497e-8f96-e200dfa7fa9c","order_by":4,"name":"Zherui Chen","email":"","orcid":"","institution":"Shenzhen Technology University","correspondingAuthor":false,"prefix":"","firstName":"Zherui","middleName":"","lastName":"Chen","suffix":""},{"id":497310872,"identity":"9b7aca04-3de9-43ed-b96c-63f0c6ed3ad0","order_by":5,"name":"Rui Zhao","email":"","orcid":"","institution":"Xinyu University","correspondingAuthor":false,"prefix":"","firstName":"Rui","middleName":"","lastName":"Zhao","suffix":""},{"id":497310873,"identity":"d4365f3f-696c-451e-ba5e-c34d00cba54e","order_by":6,"name":"Jiahui Liu","email":"","orcid":"","institution":"University of Science and Technology Beijing","correspondingAuthor":false,"prefix":"","firstName":"Jiahui","middleName":"","lastName":"Liu","suffix":""},{"id":497310874,"identity":"eb840120-688c-4ade-afd2-7e8597be851f","order_by":7,"name":"Esmée Berger","email":"","orcid":"","institution":"Chalmers University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Esmée","middleName":"","lastName":"Berger","suffix":""},{"id":497310875,"identity":"2560a854-4388-4e29-8c1b-0adabd83b0ce","order_by":8,"name":"Benrui Tang","email":"","orcid":"","institution":"Bohai University","correspondingAuthor":false,"prefix":"","firstName":"Benrui","middleName":"","lastName":"Tang","suffix":""},{"id":497310876,"identity":"6c9efe94-b38e-4dda-934c-68389ad6f383","order_by":9,"name":"Bohan Zhang","email":"","orcid":"","institution":"Bohai University","correspondingAuthor":false,"prefix":"","firstName":"Bohan","middleName":"","lastName":"Zhang","suffix":""},{"id":497310877,"identity":"6d6390b1-391f-4736-9df6-1c6fe40b0aae","order_by":10,"name":"Yanzhou Wang","email":"","orcid":"","institution":"Aalto University","correspondingAuthor":false,"prefix":"","firstName":"Yanzhou","middleName":"","lastName":"Wang","suffix":""},{"id":497310878,"identity":"3bc6da9c-73f8-4dce-ac25-cf1fd2cfe153","order_by":11,"name":"Keke Song","email":"","orcid":"","institution":"Fuzhou University","correspondingAuthor":false,"prefix":"","firstName":"Keke","middleName":"","lastName":"Song","suffix":""},{"id":497310879,"identity":"bc61a7b0-bc66-47ca-977b-f94aaff7bb96","order_by":12,"name":"Penghua Ying","email":"","orcid":"https://orcid.org/0000-0002-5758-2369","institution":"Tel Aviv University","correspondingAuthor":false,"prefix":"","firstName":"Penghua","middleName":"","lastName":"Ying","suffix":""},{"id":497310880,"identity":"752eec05-34aa-4d50-ae33-033d945a686b","order_by":13,"name":"Nan Xu","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Nan","middleName":"","lastName":"Xu","suffix":""},{"id":497310881,"identity":"dde39eaa-43c1-4930-89a0-367ee6685740","order_by":14,"name":"Haikuan Dong","email":"","orcid":"","institution":"Bohai University","correspondingAuthor":false,"prefix":"","firstName":"Haikuan","middleName":"","lastName":"Dong","suffix":""},{"id":497310882,"identity":"ce71d09c-cb48-4da0-8d13-69186a6835ae","order_by":15,"name":"Shunda Chen","email":"","orcid":"https://orcid.org/0000-0002-5506-7507","institution":"George Washington University","correspondingAuthor":false,"prefix":"","firstName":"Shunda","middleName":"","lastName":"Chen","suffix":""},{"id":497310883,"identity":"17a124cd-75e6-4106-a8b2-5d1c3f1c7127","order_by":16,"name":"Paul Erhart","email":"","orcid":"https://orcid.org/0000-0002-2516-6061","institution":"Chalmers University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Paul","middleName":"","lastName":"Erhart","suffix":""},{"id":497310884,"identity":"2e70223b-69da-42c8-b9db-f3c38b18907e","order_by":17,"name":"Zheyong Fan","email":"","orcid":"https://orcid.org/0000-0002-2253-8210","institution":"Bohai University","correspondingAuthor":false,"prefix":"","firstName":"Zheyong","middleName":"","lastName":"Fan","suffix":""},{"id":497310885,"identity":"9e4fde7f-d356-44ae-be20-c35082717731","order_by":18,"name":"Tapio Ala-Nissila","email":"","orcid":"","institution":"Aalto University","correspondingAuthor":false,"prefix":"","firstName":"Tapio","middleName":"","lastName":"Ala-Nissila","suffix":""}],"badges":[],"createdAt":"2025-07-06 14:30:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7058411/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7058411/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":88584183,"identity":"54023d3d-4666-4488-832d-74b7b7d2a20c","added_by":"auto","created_at":"2025-08-08 03:43:40","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4066689,"visible":true,"origin":"","legend":"Article File","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7058411/v1_covered_8f608b7c-abf0-4e2c-85bf-98cbbd43c9d2.pdf"},{"id":88583633,"identity":"0bfa58e9-dbd9-4de2-b443-991b2e7d8831","added_by":"auto","created_at":"2025-08-08 03:35:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":5111146,"visible":true,"origin":"","legend":"Supplementary Information","description":"","filename":"SupplementaryInformation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7058411/v1/08e3db8429b72a5b9fd40a21.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"NEP89: Universal neuroevolution potential for inorganic and organic materials across 89 elements","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":false,"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":"","lastPublishedDoi":"10.21203/rs.3.rs-7058411/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7058411/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"While machine-learned interatomic potentials offer near-quantum-mechanical accuracy for atomistic simulations, many are material-specific or computationally intensive, limiting their broader use. \r\nHere we introduce NEP89, a foundation model based on neuroevolution potential architecture, delivering empirical-potential-like speed and high accuracy across 89 elements.\r\nA compact yet comprehensive training dataset covering inorganic and organic materials was curated through descriptor-space subsampling and iterative refinement across multiple datasets.\r\nNEP89 achieves competitive accuracy compared to representative foundation models while being three to four orders of magnitude more computationally efficient, enabling previously impractical large-scale atomistic simulations of inorganic and organic systems. \r\nIn addition to its out-of-the-box applicability to diverse scenarios, including million-atom-scale compression of compositionally complex alloys, ion diffusion in solid-state electrolytes and water, rocksalt dissolution, methane combustion, and protein-ligand dynamics, NEP89 also supports fine-tuning for rapid adaptation to user-specific applications, such as mechanical, thermal, structural, and spectral properties of two-dimensional materials, metallic glasses, and organic crystals.","manuscriptTitle":"NEP89: Universal neuroevolution potential for inorganic and organic materials across 89 elements","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-08 03:35:31","doi":"10.21203/rs.3.rs-7058411/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-computational-science","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"natcomputsci","sideBox":"Learn more about [Nature Computational Science](http://www.nature.com/natcomputsci/)","snPcode":"","submissionUrl":"","title":"Nature Computational Science","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Research","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"b8a06e8a-ea58-4f6f-a944-a0426750983d","owner":[],"postedDate":"August 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":52830332,"name":"Physical sciences/Materials science/Theory and computation/Atomistic models"},{"id":52830333,"name":"Physical sciences/Materials science/Theory and computation/Computational methods"}],"tags":[],"updatedAt":"2026-04-15T12:30:41+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-08 03:35:31","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7058411","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7058411","identity":"rs-7058411","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}