EAC-Net: Predicting real-space charge density via equivariant atomic contributions

EAC-Net: Predicting real-space charge density via equivariant atomic contributions | 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 EAC-Net: Predicting real-space charge density via equivariant atomic contributions Zhicheng Zhong, Xuejian Qin, Taoyuze Lv This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7595498/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 Charge density is central to density functional theory (DFT), as it fully defines the ground-state properties of a material system. Obtaining it with high accuracy is a computational bottleneck. Existing machine learning models are constrained by trade-offs among accuracy, efficiency, and generalization. Here, we introduce the Equivariant Atomic Contribution Network (EAC-Net), which couples atoms and grids to integrate the strengths of grid-based and basis-function frameworks. EAC-Net achieves high accuracy (typically below 1% error), enhanced efficiency, and strong generalization across complex systems. Building on this framework, we develop EAC-mp, a universal charge density model covering the periodic table. The model demonstrates robust zero-shot performance across diverse systems, and generalizes beyond the training distribution, supporting downstream applications such as band structure calculations. By linking local chemical environments to charge densities, EAC-Net provides a scalable framework for accelerating electronic structure prediction and enabling high-throughput materials discovery. Physical sciences/Physics/Condensed-matter physics/Electronic properties and materials Physical sciences/Materials science/Theory and computation/Computational methods Physical sciences/Materials science/Theory and computation/Electronic structure Electronic structure Deep learning DFT Equivariance Full Text Additional Declarations There is NO Competing Interest. Supplementary Files si.pdf Supplementary Information 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-7595498","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":521136971,"identity":"8b320c19-9d3f-4230-baa1-4176256469bd","order_by":0,"name":"Zhicheng Zhong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0ElEQVRIiWNgGAWjYHACNhAhB+UwE6/FGKqaBC2JDURrkW8//uzBxx216RvOnz/4gaHCOrGB/ewBvFoYexLSDWeeOZ674UYyswTDmfTEBp68BLxagMqOSfO2HQNqYWZjYGw7nNggwWOA3yMSjG0gLekG5w8DtfwjQguPBDMbUEtNgsGBZKCWBiK0SPCksUnObDtgOPNGsrFEwrF04zaeHPxaQCEm8bGtTp7v/MGHHz7UWMv2s5/BrwUKDkOoBAZoNBEB6ohUNwpGwSgYBSMSAABDJT+Y5vc0kwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0003-1507-4814","institution":"University of Science and Technology of China","correspondingAuthor":true,"prefix":"","firstName":"Zhicheng","middleName":"","lastName":"Zhong","suffix":""},{"id":521136972,"identity":"da4377ef-cac2-477c-9546-19ba1225274b","order_by":1,"name":"Xuejian Qin","email":"","orcid":"https://orcid.org/0009-0003-0386-4226","institution":"Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Xuejian","middleName":"","lastName":"Qin","suffix":""},{"id":521136973,"identity":"20e90ec7-e0d4-44de-ae69-f932411fc73c","order_by":2,"name":"Taoyuze Lv","email":"","orcid":"","institution":"University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Taoyuze","middleName":"","lastName":"Lv","suffix":""}],"badges":[],"createdAt":"2025-09-12 01:40:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7595498/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7595498/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92371057,"identity":"fec6c5f2-695b-417b-88ab-36d68621a00c","added_by":"auto","created_at":"2025-09-29 02:48:59","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":341672,"visible":true,"origin":"","legend":"","description":"","filename":"figure1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7595498/v1/617fe63d54d038f39f4403eb.pdf"},{"id":92371058,"identity":"a6270124-74fe-479c-a696-f90315f60f03","added_by":"auto","created_at":"2025-09-29 02:48:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6548276,"visible":true,"origin":"","legend":"","description":"","filename":"mainarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7595498/v1/434e944119743b5a9a3ce515.pdf"},{"id":92371451,"identity":"4b4f810c-1122-43d8-b320-6a8565e0fd31","added_by":"auto","created_at":"2025-09-29 02:56:59","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":201012,"visible":true,"origin":"","legend":"","description":"","filename":"figure2new.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7595498/v1/246b0978d44454e7a5c7c99e.pdf"},{"id":92371054,"identity":"0c6d3256-b4b2-4cdc-aba5-79c399321d13","added_by":"auto","created_at":"2025-09-29 02:48:59","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":181940,"visible":true,"origin":"","legend":"","description":"","filename":"figure3new.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7595498/v1/428bdddfa7ff7fd8f2e13deb.pdf"},{"id":92371055,"identity":"7846dbf3-a3b9-471a-a794-34d96cb694f0","added_by":"auto","created_at":"2025-09-29 02:48:59","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1971489,"visible":true,"origin":"","legend":"","description":"","filename":"figure4new.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7595498/v1/3047f99fc68ee05065c2a751.pdf"},{"id":92371060,"identity":"f3c37aae-c868-4481-bbee-5598cf74678e","added_by":"auto","created_at":"2025-09-29 02:48:59","extension":"pdf","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3531281,"visible":true,"origin":"","legend":"","description":"","filename":"figure5new.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7595498/v1/c2258f5a6d6962cfe1c04c91.pdf"},{"id":92371053,"identity":"ab9f0d6d-e10a-4957-9a1b-463bb1359385","added_by":"auto","created_at":"2025-09-29 02:48:58","extension":"json","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4773,"visible":true,"origin":"","legend":"","description":"","filename":"NCOMMS2572762.json","url":"https://assets-eu.researchsquare.com/files/rs-7595498/v1/dcc060258c60a85f98aec31f.json"},{"id":92371061,"identity":"788a6d64-7dcd-4048-b702-8f293650baed","added_by":"auto","created_at":"2025-09-29 02:48:59","extension":"pdf","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4161813,"visible":true,"origin":"","legend":"","description":"","filename":"si.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7595498/v1/f399ca9b33d83009e01d9dcc.pdf"},{"id":97671650,"identity":"557ddf28-8ba8-4bcb-9e81-68cb4b17ba18","added_by":"auto","created_at":"2025-12-08 09:32:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2787241,"visible":true,"origin":"","legend":"Article File","description":"","filename":"mainarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7595498/v1_covered_eabd0789-4cd1-4787-a1da-7de6efa0ce6b.pdf"},{"id":92371059,"identity":"15e9b535-34b0-43de-9cc3-c86d95a72ad6","added_by":"auto","created_at":"2025-09-29 02:48:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":4161813,"visible":true,"origin":"","legend":"Supplementary Information","description":"","filename":"si.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7595498/v1/6f5e907f8cc263d37f3d8493.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"EAC-Net: Predicting real-space charge density via equivariant atomic contributions","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":"Electronic structure, Deep learning, DFT, Equivariance","lastPublishedDoi":"10.21203/rs.3.rs-7595498/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7595498/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Charge density is central to density functional theory (DFT), as it fully defines the ground-state properties of a material system. Obtaining it with high accuracy is a computational bottleneck. Existing machine learning models are constrained by trade-offs among accuracy, efficiency, and generalization. Here, we introduce the Equivariant Atomic Contribution Network (EAC-Net), which couples atoms and grids to integrate the strengths of grid-based and basis-function frameworks. EAC-Net achieves high accuracy (typically below 1% error), enhanced efficiency, and strong generalization across complex systems. Building on this framework, we develop EAC-mp, a universal charge density model covering the periodic table. The model demonstrates robust zero-shot performance across diverse systems, and generalizes beyond the training distribution, supporting downstream applications such as band structure calculations. By linking local chemical environments to charge densities, EAC-Net provides a scalable framework for accelerating electronic structure prediction and enabling high-throughput materials discovery.","manuscriptTitle":"EAC-Net: Predicting real-space charge density via equivariant atomic contributions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-29 02:48:54","doi":"10.21203/rs.3.rs-7595498/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":"7e719212-6d9b-4040-9b62-4550a9ebf1dd","owner":[],"postedDate":"September 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":55398534,"name":"Physical sciences/Physics/Condensed-matter physics/Electronic properties and materials"},{"id":55398535,"name":"Physical sciences/Materials science/Theory and computation/Computational methods"},{"id":55398536,"name":"Physical sciences/Materials science/Theory and computation/Electronic structure"}],"tags":[],"updatedAt":"2025-12-05T13:55:38+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-29 02:48:54","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7595498","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7595498","identity":"rs-7595498","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}