A Physics-Informed Foundation Model for Real-Time High-Fidelity Structural Dynamics | 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 A Physics-Informed Foundation Model for Real-Time High-Fidelity Structural Dynamics Ying Zhou, Shiqiao Meng, Qinghua Zheng, Bingxu Liao, Mushi Chang, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7126939/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 Accurate and rapid structural-dynamics modeling is critical for structural design, disaster mitigation, and resilience assessment, yet existing computational frameworks rely almost exclusively on nonlinear finite-element analysis. Conventional finite-element analysis approaches require substantial computational resources, with individual simulations typically taking hours to days to complete, making real-time or city-wide structural assessments impractical. To overcome this fundamental limitation, we introduce SeisGPT, a physics-informed foundation model designed specifically to enable high-fidelity, real-time structural response prediction across extensive building portfolios encompassing diverse structural types and topologies. SeisGPT integrates structural mechanics principles with advanced deep-learning methodologies, including a physics-informed graph neural network encoder, a simplified dynamic-response embedding module, and a generative Transformer-based decoder. The model is pretrained on a large-scale dataset comprising over 2 million nonlinear elastoplastic FEA simulations—covering 270,000 AI-generated, code-compliant structural designs created via an automated generative workflow, as well as 694 real-world buildings—totaling more than 10 billion discrete response time-steps. For previously unseen buildings subjected to external loads, SeisGPT achieves displacement and acceleration predictions with less than 5% normalized error while providing an approximately 40,000-fold computational speedup over conventional FEA methods. Furthermore, by assimilating sparse sensor measurements, SeisGPT’s physics-guided latent representations refine prediction accuracy beyond that achievable with conventional FEA simulations, enabling real-time structural-health monitoring and damage localization. By integrating physics-informed modeling with scalable inference, SeisGPT establishes a widely applicable computational paradigm, paving the way for transformative advancements in structural dynamics. Physical sciences/Engineering/Civil engineering Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Computational science Earth and environmental sciences/Natural hazards Full Text Additional Declarations There is NO Competing Interest. Supplementary Files supplementaryinformation.docx Supplementary Information for A Physics-Informed Foundation Model for Real-Time High-Fidelity Structural Dynamics 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-7126939","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":494605416,"identity":"33429147-3e6f-4238-a1e1-875edd956522","order_by":0,"name":"Ying Zhou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9ElEQVRIiWNgGAWjYDACZiBmbGBg4AfzeCSARAKRWiTbiNbCANVicAzOJaDF4Djv4Zc/d9gkbr7ffOzhFxkLBn72HAOGnzvwaDnMl2YheSYtcdsxtnRjGaDDJHveGDD2nsGnhcfMwLDtMFALj5m0BFCLwY0cA2bGNgJaEoFaNrdBtdgTocX4wUGglg1sPGaSH0C2SBDQIgm0hbGxLc14xrG0NGlgIPNInHlWcLAXjxa+82eMP/5ss5Htbz58TPJnT50cf3vyxgc/8WhROMDAJgHjMPP2MPCAGAdwa2BgkG9gYP4A4zD++IFP7SgYBaNgFIxUAACoLU19xulGWgAAAABJRU5ErkJggg==","orcid":"","institution":"Tongji University","correspondingAuthor":true,"prefix":"","firstName":"Ying","middleName":"","lastName":"Zhou","suffix":""},{"id":494605417,"identity":"4c2bfc1d-2b45-4023-aa65-23f10c5a49f3","order_by":1,"name":"Shiqiao Meng","email":"","orcid":"","institution":"Tongji University","correspondingAuthor":false,"prefix":"","firstName":"Shiqiao","middleName":"","lastName":"Meng","suffix":""},{"id":494605418,"identity":"6a9859a5-befd-4bda-b694-2b8a21e03ee4","order_by":2,"name":"Qinghua Zheng","email":"","orcid":"","institution":"Xi’an Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Qinghua","middleName":"","lastName":"Zheng","suffix":""},{"id":494605419,"identity":"50687524-3d2b-49e7-a416-4dcd257c82d3","order_by":3,"name":"Bingxu Liao","email":"","orcid":"","institution":"Tongji University","correspondingAuthor":false,"prefix":"","firstName":"Bingxu","middleName":"","lastName":"Liao","suffix":""},{"id":494605420,"identity":"79a612bb-59d9-44ed-bbb6-b3d368c3a437","order_by":4,"name":"Mushi Chang","email":"","orcid":"","institution":"Tongji University","correspondingAuthor":false,"prefix":"","firstName":"Mushi","middleName":"","lastName":"Chang","suffix":""},{"id":494605421,"identity":"70d73647-5588-4508-a625-ba5c62a132d2","order_by":5,"name":"Tianshu Zhang","email":"","orcid":"","institution":"Tongji University","correspondingAuthor":false,"prefix":"","firstName":"Tianshu","middleName":"","lastName":"Zhang","suffix":""},{"id":494605422,"identity":"e946e073-9d18-4860-a2d1-a85c490ca5a0","order_by":6,"name":"Abouzar Jafari","email":"","orcid":"","institution":"Tongji University","correspondingAuthor":false,"prefix":"","firstName":"Abouzar","middleName":"","lastName":"Jafari","suffix":""},{"id":494605423,"identity":"1685ea9e-6174-46ba-b407-62a919a43fcf","order_by":7,"name":"Abderrahim Djerrad","email":"","orcid":"","institution":"Tongji University","correspondingAuthor":false,"prefix":"","firstName":"Abderrahim","middleName":"","lastName":"Djerrad","suffix":""}],"badges":[],"createdAt":"2025-07-15 06:25:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7126939/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7126939/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92164780,"identity":"2abc17f9-c9c9-41a5-98f2-79fa15c8a287","added_by":"auto","created_at":"2025-09-25 10:47:16","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20299767,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/cbfe8addbaac2ff8738a6772.docx"},{"id":92164335,"identity":"ad40faec-c962-4881-bd77-e50068e20169","added_by":"auto","created_at":"2025-09-25 10:39:12","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":342,"visible":true,"origin":"","legend":"","description":"","filename":"rs7126939.json","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/bcbec64efa8101c4084ddc65.json"},{"id":92164355,"identity":"f1927f75-83ff-4084-80c3-c8ac0c02482c","added_by":"auto","created_at":"2025-09-25 10:39:15","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":191215,"visible":true,"origin":"","legend":"","description":"","filename":"rs71269392enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/59dfb2bd118fdc6fbc2a6935.xml"},{"id":92164369,"identity":"0f314d72-ba11-4017-bd7e-f6b0f66b6836","added_by":"auto","created_at":"2025-09-25 10:39:19","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1879935,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/e39903af50abb375cc386f08.png"},{"id":92164361,"identity":"c6030e7b-6f09-453c-aa1c-71ed0472b3cb","added_by":"auto","created_at":"2025-09-25 10:39:16","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5557919,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/3041db7fc1e124ec46695f0e.png"},{"id":92164347,"identity":"cd925aed-5547-438c-a576-c9b5758ef3e3","added_by":"auto","created_at":"2025-09-25 10:39:14","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":132690,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/4159f6d53e91daa6ff6f4235.png"},{"id":92164360,"identity":"cdfd66f4-cd76-4558-81bb-39c0d9ce0e75","added_by":"auto","created_at":"2025-09-25 10:39:16","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1338463,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/18814b9a319e1bcac063bf54.png"},{"id":92164386,"identity":"dbb72a1e-4973-4ea4-b3a2-11b88198f8e5","added_by":"auto","created_at":"2025-09-25 10:39:20","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":779917,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/a861d7ad83f7685671c67fd7.jpeg"},{"id":92164341,"identity":"0caaba69-81aa-4291-bf1e-5e04a560c2f7","added_by":"auto","created_at":"2025-09-25 10:39:13","extension":"jpeg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":523395,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/6bfe932a7ecc92ef05de94e3.jpeg"},{"id":92164348,"identity":"b805db5a-3358-4f22-bf25-61f54c57c79d","added_by":"auto","created_at":"2025-09-25 10:39:14","extension":"jpeg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":743701,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/384e689f20431d1f58a5e325.jpeg"},{"id":92164373,"identity":"06f436d4-3e4e-4489-9ad4-0b8a0d4d2e80","added_by":"auto","created_at":"2025-09-25 10:39:19","extension":"jpeg","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":269873,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/3de3d384b3552af284999395.jpeg"},{"id":92164364,"identity":"b5a15f81-c22a-4651-a241-9123cf3e02e3","added_by":"auto","created_at":"2025-09-25 10:39:17","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2921618,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/7c6ae4b898e51a45bfe8da47.png"},{"id":92164353,"identity":"5e0770b4-58a9-46e4-a16a-82c91c274998","added_by":"auto","created_at":"2025-09-25 10:39:15","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":999479,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/30a991003b69e52f8636e8cd.png"},{"id":92164390,"identity":"88f2643e-0bb8-4e2c-bdb7-4bf1b7e4d862","added_by":"auto","created_at":"2025-09-25 10:39:23","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1398406,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/f1532c3521235aab21fd3a09.png"},{"id":92164337,"identity":"a33c495d-cf13-4478-a5cd-d059d5cc3c90","added_by":"auto","created_at":"2025-09-25 10:39:13","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":454598,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/d2ca628f72eddda74789e8da.png"},{"id":92164368,"identity":"63f6016d-1188-46fe-8243-c0a4e16b75b2","added_by":"auto","created_at":"2025-09-25 10:39:17","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1323858,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/48f73f5a106882c48a11ee45.png"},{"id":92164366,"identity":"fe82203e-467d-4a7e-a8fc-c9745e503456","added_by":"auto","created_at":"2025-09-25 10:39:17","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":69176,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/be89f80d62c8281cd9491cef.png"},{"id":92164358,"identity":"d8110ef1-168a-4dae-8505-7974650be736","added_by":"auto","created_at":"2025-09-25 10:39:16","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":457038,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/d61ff1eb2959779812d609d2.png"},{"id":92164388,"identity":"3b0f0c70-a08e-4dae-a616-12db23131b40","added_by":"auto","created_at":"2025-09-25 10:39:20","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":136043,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/1e23890f1f53fd2f277c0845.png"},{"id":92164389,"identity":"4bb1295b-430c-42d5-88d2-fa600de3ce58","added_by":"auto","created_at":"2025-09-25 10:39:21","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":80521,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/c335eed52aa2933e24bd64f6.png"},{"id":92164343,"identity":"7e3c1b46-7228-4fcf-83e7-ef6be4209b87","added_by":"auto","created_at":"2025-09-25 10:39:13","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":208193,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/7cba44815f21e32facd75479.png"},{"id":92164359,"identity":"1cf40dc4-7c98-40ec-83f0-e2232cd5b16a","added_by":"auto","created_at":"2025-09-25 10:39:16","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":68505,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/c70f1ab2578060ca5fa64dd3.png"},{"id":92164362,"identity":"3e546dc2-e25f-44f4-a0a5-050561e15301","added_by":"auto","created_at":"2025-09-25 10:39:16","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":931791,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/d1ad35d688ccde071a7ba45c.png"},{"id":92164352,"identity":"925426ef-5b6e-4e9b-988a-884c39d0ab38","added_by":"auto","created_at":"2025-09-25 10:39:14","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":310293,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/c8d2d01e27ce430e3bd3684f.png"},{"id":92164339,"identity":"77c39d15-b17b-420a-952c-c8ddf0ca7288","added_by":"auto","created_at":"2025-09-25 10:39:13","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":451466,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/fac83c4e0e918990685ea9f2.png"},{"id":92164342,"identity":"f0fec331-88e1-4c54-86cd-d4c102c6a287","added_by":"auto","created_at":"2025-09-25 10:39:13","extension":"xml","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":189374,"visible":true,"origin":"","legend":"","description":"","filename":"rs71269392structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/6a9e2a804f14e3678a15a6f3.xml"},{"id":92164365,"identity":"8ba265be-f1cd-4bc9-a80a-d060782b35e9","added_by":"auto","created_at":"2025-09-25 10:39:17","extension":"html","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":203861,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/2a602227252d293a53df29dc.html"},{"id":92164781,"identity":"2c92a71e-538f-4bb0-be13-4c69e7e91a35","added_by":"auto","created_at":"2025-09-25 10:47:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2188626,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1_covered_fbcdf338-5a8c-4d6f-879c-0a548cacd09a.pdf"},{"id":92164387,"identity":"17a80c76-8b55-438b-a8bd-20aaf6ae341d","added_by":"auto","created_at":"2025-09-25 10:39:20","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":13718493,"visible":true,"origin":"","legend":"Supplementary Information for A Physics-Informed Foundation Model for Real-Time High-Fidelity Structural Dynamics","description":"","filename":"supplementaryinformation.docx","url":"https://assets-eu.researchsquare.com/files/rs-7126939/v1/cad6e7eb9ee55587aaf2e256.docx"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"A Physics-Informed Foundation Model for Real-Time High-Fidelity Structural Dynamics","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-7126939/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7126939/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate and rapid structural-dynamics modeling is critical for structural design, disaster mitigation, and resilience assessment, yet existing computational frameworks rely almost exclusively on nonlinear finite-element analysis. Conventional finite-element analysis approaches require substantial computational resources, with individual simulations typically taking hours to days to complete, making real-time or city-wide structural assessments impractical. To overcome this fundamental limitation, we introduce SeisGPT, a physics-informed foundation model designed specifically to enable high-fidelity, real-time structural response prediction across extensive building portfolios encompassing diverse structural types and topologies. SeisGPT integrates structural mechanics principles with advanced deep-learning methodologies, including a physics-informed graph neural network encoder, a simplified dynamic-response embedding module, and a generative Transformer-based decoder. The model is pretrained on a large-scale dataset comprising over 2\u0026nbsp;million nonlinear elastoplastic FEA simulations—covering 270,000 AI-generated, code-compliant structural designs created via an automated generative workflow, as well as 694 real-world buildings—totaling more than 10\u0026nbsp;billion discrete response time-steps. For previously unseen buildings subjected to external loads, SeisGPT achieves displacement and acceleration predictions with less than 5% normalized error while providing an approximately 40,000-fold computational speedup over conventional FEA methods. Furthermore, by assimilating sparse sensor measurements, SeisGPT’s physics-guided latent representations refine prediction accuracy beyond that achievable with conventional FEA simulations, enabling real-time structural-health monitoring and damage localization. By integrating physics-informed modeling with scalable inference, SeisGPT establishes a widely applicable computational paradigm, paving the way for transformative advancements in structural dynamics.\u003c/p\u003e","manuscriptTitle":"A Physics-Informed Foundation Model for Real-Time High-Fidelity Structural Dynamics","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-25 10:38:27","doi":"10.21203/rs.3.rs-7126939/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":"f479e338-12c6-4c2a-9adc-8b07885ebbe3","owner":[],"postedDate":"September 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":52531614,"name":"Physical sciences/Engineering/Civil engineering"},{"id":52531615,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":52531616,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":52531617,"name":"Earth and environmental sciences/Natural hazards"}],"tags":[],"updatedAt":"2026-03-24T15:16:00+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-25 10:38:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7126939","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7126939","identity":"rs-7126939","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.