Efficient Nudged Elastic Band Method using Neural Network Bayesian Algorithm Execution

Efficient Nudged Elastic Band Method using Neural Network Bayesian Algorithm Execution | 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 Efficient Nudged Elastic Band Method using Neural Network Bayesian Algorithm Execution Pranav Kakhandiki, Sathya Chitturi, Daniel Ratner, Sean Gasiorowski This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8389167/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 The discovery of a minimum energy pathway (MEP) between metastable states is crucial for scientific tasks including catalyst and biomolecular design. However, the standard nudged elastic band (NEB) algorithm requires hundreds to tens of thousands of compute-intensive simulations, making applications to complex systems prohibitively expensive. We introduce Neural Network Bayesian Algorithm Execution (NN-BAX), a framework that jointly learns the energy landscape and the MEP. NN-BAX sequentially fine-tunes a foundation model by actively selecting samples targeted at improving the MEP. Tested on Lennard-Jones and Embedded Atom Method systems, our approach achieves a one to two order of magnitude reduction in energy and force evaluations with negligible loss in MEP accuracy and demonstrates scalability to >100-dimensional systems. This work is therefore a promising step towards removing the computational barrier for MEP discovery in scientifically relevant systems, suggesting that weeks-long calculations may be achieved in hours or days with minimal loss in accuracy. Physical sciences/Materials science/Theory and computation/Computational methods Physical sciences/Materials science/Materials for energy and catalysis Biological sciences/Computational biology and bioinformatics/Machine learning Nudged Elastic Band Bayesian Experimental Design Minimum Energy Pathways Active Learning Foundation Models Machine Learning Potentials Full Text Additional Declarations There is NO Competing Interest. Supplementary Files NNBAXSupp.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-8389167","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":578330220,"identity":"3ee035c6-9a20-4256-aea1-118d9d28ffe4","order_by":0,"name":"Pranav Kakhandiki","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7klEQVRIiWNgGAWjYDACHgZmZiDF2A/m2QDxAQYGCaK0zGwAUWmkaNlwgFgt5jyHHxsX1NyR3Xz+/MHPBQk2+XwHmA/e5sGjxbK3zTh5xrFnxttuJDNLz0hIs5x5gC3ZGp8Wg/MMxod52A4nbrvBzCDN++OwgcEBHjNp/FrYPx/m+Xc4cXP/YebfPAkgLfzf8Gs522OczNt2OHEDQzKbNEQLDxteLZY9Z4qNefsOG8+4kWxmzZOQZiB5mM3Ycg4eLeY86Zuleb4dlu3vP/j4Nk+CjQHf8eaHN97gcximEDMe5Ti0jIJRMApGwShAAwDmZU0zf78PfwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0001-6617-8061","institution":"Stanford University","correspondingAuthor":true,"prefix":"","firstName":"Pranav","middleName":"","lastName":"Kakhandiki","suffix":""},{"id":578330221,"identity":"ff644bdb-e8f6-41e9-a3df-2962334dc376","order_by":1,"name":"Sathya Chitturi","email":"","orcid":"","institution":"PostEra","correspondingAuthor":false,"prefix":"","firstName":"Sathya","middleName":"","lastName":"Chitturi","suffix":""},{"id":578330222,"identity":"c0d036ca-57f4-4991-9c56-7c0ec382dff1","order_by":2,"name":"Daniel Ratner","email":"","orcid":"","institution":"SLAC National Accelerator Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Daniel","middleName":"","lastName":"Ratner","suffix":""},{"id":578330223,"identity":"4f00855e-09b4-470e-85cf-9d8d98909cfb","order_by":3,"name":"Sean Gasiorowski","email":"","orcid":"https://orcid.org/0000-0002-4067-2472","institution":"SLAC National Accelerator Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Sean","middleName":"","lastName":"Gasiorowski","suffix":""}],"badges":[],"createdAt":"2025-12-17 21:10:34","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8389167/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8389167/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":103888096,"identity":"87e57644-c973-4ac2-adaf-ef0e52b70313","added_by":"auto","created_at":"2026-03-04 07:27:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1856983,"visible":true,"origin":"","legend":"Article File","description":"","filename":"NNBAXjustManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8389167/v1_covered_74ce7c58-6dd9-4d73-a8f6-ccd37da741c9.pdf"},{"id":103888094,"identity":"ef4bf105-e555-4542-95da-34b8708c2171","added_by":"auto","created_at":"2026-03-04 07:27:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":7776019,"visible":true,"origin":"","legend":"Supplementary Information","description":"","filename":"NNBAXSupp.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8389167/v1/81a67c0951ede54c66811642.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Efficient Nudged Elastic Band Method using Neural Network Bayesian Algorithm Execution","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":"Nudged Elastic Band, Bayesian Experimental Design, Minimum Energy Pathways, Active Learning, Foundation Models, Machine Learning Potentials","lastPublishedDoi":"10.21203/rs.3.rs-8389167/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8389167/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The discovery of a minimum energy pathway (MEP) between metastable states is crucial for scientific tasks including catalyst and biomolecular design. However, the standard nudged elastic band (NEB) algorithm requires hundreds to tens of thousands of compute-intensive simulations, making applications to complex systems prohibitively expensive. We introduce Neural Network Bayesian Algorithm Execution (NN-BAX), a framework that jointly learns the energy landscape and the MEP. NN-BAX sequentially fine-tunes a foundation model by actively selecting samples targeted at improving the MEP. Tested on Lennard-Jones and Embedded Atom Method systems, our approach achieves a one to two order of magnitude reduction in energy and force evaluations with negligible loss in MEP accuracy and demonstrates scalability to \u003e100-dimensional systems. This work is therefore a promising step towards removing the computational barrier for MEP discovery in scientifically relevant systems, suggesting that weeks-long calculations may be achieved in hours or days with minimal loss in accuracy.","manuscriptTitle":"Efficient Nudged Elastic Band Method using Neural Network Bayesian Algorithm Execution","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-04 07:27:05","doi":"10.21203/rs.3.rs-8389167/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"774c14c6-8291-4a25-b85c-456b0afe8060","owner":[],"postedDate":"March 4th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":61535251,"name":"Physical sciences/Materials science/Theory and computation/Computational methods"},{"id":61535252,"name":"Physical sciences/Materials science/Materials for energy and catalysis"},{"id":61535253,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"}],"tags":[],"updatedAt":"2026-03-04T07:27:05+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-04 07:27:05","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8389167","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8389167","identity":"rs-8389167","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}