Physics-Informed GCN-LSTM Framework for Long-Term Forecasting of 2D and 3D Microstructure Evolution

Physics-Informed GCN-LSTM Framework for Long-Term Forecasting of 2D and 3D Microstructure Evolution | 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 Physics-Informed GCN-LSTM Framework for Long-Term Forecasting of 2D and 3D Microstructure Evolution Hamidreza Razavi, Nele Moelans This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7685800/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 03 Apr, 2026 Read the published version in npj Computational Materials → Version 1 posted 12 You are reading this latest preprint version Abstract This paper presents a physics-informed framework that integrates graph convolutional networks (GCN) with long short-term memory (LSTM) architecture to forecast microstructure evolution over long time horizons in both 2D and 3D with remarkable performance across varied metrics. The proposed framework is composition-aware, trained jointly on datasets with different compositions, and operates in latent graph space, which enables the model to capture compositions and morphological dynamics while remaining computationally efficient. Compressing and encoding phase-field simulation data with convolutional autoencoders and operating in Latent graph space facilitates efficient modeling of microstructural evolution across composition, dimensions, and long-term horizons. The framework is capable of capturing the spatial and temporal patterns in evolving microstructures, making it suitable for learning their dynamics. The framework effectively captures the spatial and temporal evolution of microstructures, enabling long-range forecasting beyond the training regime at a substantially lower computational cost than conventional phase-field simulations. Physical sciences/Materials science Physical sciences/Mathematics and computing Physical sciences/Physics Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 03 Apr, 2026 Read the published version in npj Computational Materials → Version 1 posted Editorial decision: Revision requested 29 Oct, 2025 Reviews received at journal 23 Oct, 2025 Reviews received at journal 21 Oct, 2025 Reviews received at journal 20 Oct, 2025 Reviewers agreed at journal 14 Oct, 2025 Reviewers agreed at journal 11 Oct, 2025 Reviewers agreed at journal 10 Oct, 2025 Reviewers agreed at journal 10 Oct, 2025 Reviewers invited by journal 10 Oct, 2025 Editor assigned by journal 10 Oct, 2025 Submission checks completed at journal 06 Oct, 2025 First submitted to journal 22 Sep, 2025 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-7685800","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":532829633,"identity":"840dcfe3-2681-43be-b86e-74cf5ccfc775","order_by":0,"name":"Hamidreza Razavi","email":"data:image/png;base64,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","orcid":"","institution":"KU Leuven","correspondingAuthor":true,"prefix":"","firstName":"Hamidreza","middleName":"","lastName":"Razavi","suffix":""},{"id":532829635,"identity":"4e7dab47-5d50-4162-b9d5-e177973ec350","order_by":1,"name":"Nele Moelans","email":"","orcid":"","institution":"KU Leuven","correspondingAuthor":false,"prefix":"","firstName":"Nele","middleName":"","lastName":"Moelans","suffix":""}],"badges":[],"createdAt":"2025-09-23 00:53:45","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7685800/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7685800/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41524-026-01999-x","type":"published","date":"2026-04-03T16:00:03+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":94232525,"identity":"86d13df9-bb22-4add-a9af-a4405cdbe1cb","added_by":"auto","created_at":"2025-10-23 23:41:37","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4187,"visible":true,"origin":"","legend":"","description":"","filename":"baecc5e0890b41edaa2ea9036f36f2c9.json","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/ffbb6af74a3f34ba3fcdc790.json"},{"id":94232707,"identity":"b7be3e66-08be-4145-a58d-8e1873f5d982","added_by":"auto","created_at":"2025-10-23 23:49:37","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":163011,"visible":true,"origin":"","legend":"","description":"","filename":"baecc5e0890b41edaa2ea9036f36f2c91enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/8407e2c605a3fca6efbba250.xml"},{"id":94232526,"identity":"cfc52168-2417-4d55-9969-2c69c6f227fb","added_by":"auto","created_at":"2025-10-23 23:41:37","extension":"png","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":134397,"visible":true,"origin":"","legend":"","description":"","filename":"2daeeval.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/88893687de26f7fd381868c5.png"},{"id":94232709,"identity":"1ecedfa0-edfe-4ed7-83df-d8e476598a95","added_by":"auto","created_at":"2025-10-23 23:49:37","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2432299,"visible":true,"origin":"","legend":"","description":"","filename":"2ddataset.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/ce073c65e4bf9a4bf6d2cd91.png"},{"id":94232883,"identity":"390159ec-5a89-4a3c-b69c-f4df8b0159ef","added_by":"auto","created_at":"2025-10-23 23:57:37","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":47903,"visible":true,"origin":"","legend":"","description":"","filename":"2deval.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/03f46714c76eacef3ced597d.png"},{"id":94232527,"identity":"b76aadef-e4d2-46c9-a32d-1547bfc2ffd6","added_by":"auto","created_at":"2025-10-23 23:41:37","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":214085,"visible":true,"origin":"","legend":"","description":"","filename":"2dfilters.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/a0ca00b229aa6d9d8b1878de.png"},{"id":94232529,"identity":"7e908db4-13d0-4e06-b19f-12e1e3088af4","added_by":"auto","created_at":"2025-10-23 23:41:37","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":189311,"visible":true,"origin":"","legend":"","description":"","filename":"2dforecast.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/0c23a343d3b9b48015da8fcf.png"},{"id":94232538,"identity":"fbf2bc71-5eb1-4c39-80ae-1cc886fe1f70","added_by":"auto","created_at":"2025-10-23 23:41:37","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2427702,"visible":true,"origin":"","legend":"","description":"","filename":"2dgraph.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/66df53ad873721d21c89bea8.png"},{"id":94232544,"identity":"7f91cbec-4e21-4175-90de-8ab17dc69db9","added_by":"auto","created_at":"2025-10-23 23:41:38","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":364498,"visible":true,"origin":"","legend":"","description":"","filename":"2dvalidationmargin.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/b1d0f1f59554b030fb5640a2.png"},{"id":94232540,"identity":"375b62cb-9ed9-4147-9034-085d80795fab","added_by":"auto","created_at":"2025-10-23 23:41:37","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":71151,"visible":true,"origin":"","legend":"","description":"","filename":"3daeevaluation.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/d9888bedf9f03e5f4115cd56.png"},{"id":94232884,"identity":"24cf17de-4b16-406b-9401-323c22461bca","added_by":"auto","created_at":"2025-10-23 23:57:37","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":431739,"visible":true,"origin":"","legend":"","description":"","filename":"3daerecon.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/b04b9c1e46996650e526290b.png"},{"id":94232710,"identity":"5e9b3212-e23b-47b1-8095-7de4a6993b2a","added_by":"auto","created_at":"2025-10-23 23:49:37","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2165301,"visible":true,"origin":"","legend":"","description":"","filename":"3daereconstruction.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/3ba6e62364545897d2b77cfb.png"},{"id":94232712,"identity":"681c1d0f-f8a5-4a6f-9358-46a2fae0c13a","added_by":"auto","created_at":"2025-10-23 23:49:37","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2251153,"visible":true,"origin":"","legend":"","description":"","filename":"3ddataset.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/e49da4c7b077f29f70695369.png"},{"id":94232554,"identity":"f76875c7-560e-4cd1-8470-4491f2afbd53","added_by":"auto","created_at":"2025-10-23 23:41:38","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":51444,"visible":true,"origin":"","legend":"","description":"","filename":"3deval.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/2897847ab0d13696f5bc1f60.png"},{"id":94232543,"identity":"9dcd2797-9596-4487-970e-0c15fc467fb1","added_by":"auto","created_at":"2025-10-23 23:41:37","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2999771,"visible":true,"origin":"","legend":"","description":"","filename":"3dforecast.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/8d9df5e3bd9a39f5a9872492.png"},{"id":94232530,"identity":"df2ff503-db85-41b0-a52a-a8bb2153efbd","added_by":"auto","created_at":"2025-10-23 23:41:37","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1857563,"visible":true,"origin":"","legend":"","description":"","filename":"3dgraph.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/f63693363c26d947b405863e.png"},{"id":94232536,"identity":"6dbc71e5-eed0-4359-973f-67376ef62952","added_by":"auto","created_at":"2025-10-23 23:41:37","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1932601,"visible":true,"origin":"","legend":"","description":"","filename":"3dsamples.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/a2a11fb90f5be43b54c4f993.png"},{"id":94232533,"identity":"17af2099-0c9a-4f96-966e-3996bb79ad35","added_by":"auto","created_at":"2025-10-23 23:41:37","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":708163,"visible":true,"origin":"","legend":"","description":"","filename":"3dvalidation.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/2730923d90cedd4179c96c74.png"},{"id":94232556,"identity":"06f231fe-3c0b-4b98-98c2-a9a62d12a5aa","added_by":"auto","created_at":"2025-10-23 23:41:38","extension":"bbl","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20281,"visible":true,"origin":"","legend":"","description":"","filename":"GCNLSTMPI.bbl","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/7b4b36c331e5dacdfa9e6bbc.bbl"},{"id":94232552,"identity":"5a0da5a2-5e45-4e05-b6ba-9e25f2eca983","added_by":"auto","created_at":"2025-10-23 23:41:38","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":62388,"visible":true,"origin":"","legend":"","description":"","filename":"Newphase.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/f0c81a53aa57b18fba1027a3.png"},{"id":94232537,"identity":"9cf1eceb-9b0b-4da1-9e58-c66e9bd22b8b","added_by":"auto","created_at":"2025-10-23 23:41:37","extension":"pdf","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":186161,"visible":true,"origin":"","legend":"","description":"","filename":"npjCoverLetter.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/cf68711900f17cdcab700f71.pdf"},{"id":94232548,"identity":"065680e8-81a9-4691-82ef-34767318d2fc","added_by":"auto","created_at":"2025-10-23 23:41:38","extension":"pdf","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14464671,"visible":true,"origin":"","legend":"","description":"","filename":"physicsinformedgcnlstmlongtermforecasting2d3dmicrostructureevolution.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/9d0ed959734740137d6c0b21.pdf"},{"id":94232547,"identity":"ffc507da-ca02-402a-8a8b-b0993097ed86","added_by":"auto","created_at":"2025-10-23 23:41:38","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":194260,"visible":true,"origin":"","legend":"","description":"","filename":"sequence.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/e57b04e9ad12a6ba8c454856.png"},{"id":94232718,"identity":"3e6e5185-b7b3-4e42-94df-f487fe5f2454","added_by":"auto","created_at":"2025-10-23 23:49:38","extension":"bst","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":146013,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/dcc42a57ca4e38f4198afb6c.bst"},{"id":94232715,"identity":"05b16327-6cc9-40bd-b670-bb8e981a9760","added_by":"auto","created_at":"2025-10-23 23:49:38","extension":"bst","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29828,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/0452b97367e21810e9a1e30d.bst"},{"id":94232885,"identity":"f796de00-d71c-4f4a-8093-d2073b609284","added_by":"auto","created_at":"2025-10-23 23:57:37","extension":"pdf","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":421391,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/8e720f2dc2a7246f09400e9a.pdf"},{"id":94232542,"identity":"a41843b7-8e1b-455f-ac8b-4000590c1677","added_by":"auto","created_at":"2025-10-23 23:41:37","extension":"bst","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35515,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/9e11862b8e4f822bc966c902.bst"},{"id":94232558,"identity":"c0782e05-4001-4fde-b581-8099efa86fb9","added_by":"auto","created_at":"2025-10-23 23:41:38","extension":"bst","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33968,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/64087aaa96233a893400bbe4.bst"},{"id":94232714,"identity":"ae6aca8d-5727-4bf3-9b6b-a199b28cf310","added_by":"auto","created_at":"2025-10-23 23:49:38","extension":"cls","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55861,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/f1018005c9e0617a96fef550.cls"},{"id":94232550,"identity":"60424be8-f8ec-46b3-a08f-7855119e7956","added_by":"auto","created_at":"2025-10-23 23:41:38","extension":"bst","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64023,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/7b6aeb5c1754fc5aff0b74d3.bst"},{"id":94232886,"identity":"4920aac9-3bff-41d3-9a87-14ede74bbe62","added_by":"auto","created_at":"2025-10-23 23:57:38","extension":"bst","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64166,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/12ac31cd70dce2c3984c759e.bst"},{"id":94232549,"identity":"7363e43d-acd0-41db-95ec-0fd832d4e6e1","added_by":"auto","created_at":"2025-10-23 23:41:38","extension":"bst","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37333,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/447d90f8f3968ae797290c07.bst"},{"id":94232551,"identity":"4ea17420-6c5e-4ae7-badf-0aed72bae8ec","added_by":"auto","created_at":"2025-10-23 23:41:38","extension":"bst","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39951,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouveray.bst","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/06f8954ad194c306a84472a9.bst"},{"id":94232545,"identity":"29aa281c-8be1-400f-94d1-b5a53ec9cbaa","added_by":"auto","created_at":"2025-10-23 23:41:38","extension":"bst","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40758,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouvernum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/1b5163963eb953d75b47f865.bst"},{"id":94232546,"identity":"c55ff257-4a07-4d36-81e2-d89983921cea","added_by":"auto","created_at":"2025-10-23 23:41:38","extension":"png","order_by":43,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2147597,"visible":true,"origin":"","legend":"","description":"","filename":"Online3daereconstruction.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/95ba497a9c5fda7b4c987eb0.png"},{"id":94232717,"identity":"276c47c5-6b0a-41ab-9245-e18992174271","added_by":"auto","created_at":"2025-10-23 23:49:38","extension":"png","order_by":44,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2209274,"visible":true,"origin":"","legend":"","description":"","filename":"Online3ddataset.png","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/dad98ed23ea92c77f6b8f04c.png"},{"id":94232560,"identity":"1b2ba886-034d-4c58-a01e-c1d02d8b7525","added_by":"auto","created_at":"2025-10-23 23:41:38","extension":"xml","order_by":52,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":198130,"visible":true,"origin":"","legend":"","description":"","filename":"baecc5e0890b41edaa2ea9036f36f2c91structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/865081b55c83e858fd65dfc4.xml"},{"id":94232555,"identity":"6c291e9c-d2a5-4d89-b9e0-ae3224ad1ecc","added_by":"auto","created_at":"2025-10-23 23:41:38","extension":"html","order_by":53,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":200810,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1/3ff736878da4f0a3c2197283.html"},{"id":106344586,"identity":"3d529b6f-7fcf-435a-b903-6b0f63942eb1","added_by":"auto","created_at":"2026-04-07 16:15:55","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3569079,"visible":true,"origin":"","legend":"","description":"","filename":"physicsinformedgcnlstmlongtermforecasting2d3dmicrostructureevolution.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7685800/v1_covered_570ef0e4-9c2d-4813-806d-75c83f70aae4.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Physics-Informed GCN-LSTM Framework for Long-Term Forecasting of 2D and 3D Microstructure Evolution","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"npj-computational-materials","isNatureJournal":false,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"npjcompumats","sideBox":"Learn more about [npj Computational Materials](http://www.nature.com/npjcompumats/)","snPcode":"41524","submissionUrl":"https://mts-npjcompumats.nature.com/","title":"npj Computational Materials","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7685800/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7685800/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper presents a physics-informed framework that integrates graph convolutional networks (GCN) with long short-term memory (LSTM) architecture to forecast microstructure evolution over long time horizons in both 2D and 3D with remarkable performance across varied metrics. The proposed framework is composition-aware, trained jointly on datasets with different compositions, and operates in latent graph space, which enables the model to capture compositions and morphological dynamics while remaining computationally efficient. Compressing and encoding phase-field simulation data with convolutional autoencoders and operating in Latent graph space facilitates efficient modeling of microstructural evolution across composition, dimensions, and long-term horizons. The framework is capable of capturing the spatial and temporal patterns in evolving microstructures, making it suitable for learning their dynamics. The framework effectively captures the spatial and temporal evolution of microstructures, enabling long-range forecasting beyond the training regime at a substantially lower computational cost than conventional phase-field simulations.\u003c/p\u003e","manuscriptTitle":"Physics-Informed GCN-LSTM Framework for Long-Term Forecasting of 2D and 3D Microstructure Evolution","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-23 23:41:32","doi":"10.21203/rs.3.rs-7685800/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-29T09:37:46+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-23T16:38:57+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-21T11:45:10+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-20T23:14:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"260518779737241553312096047588297696368","date":"2025-10-14T09:05:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"1188276646204240017390370389978642972","date":"2025-10-11T06:17:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"213974332196645067060110340988417280165","date":"2025-10-10T15:05:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"225550160269263148866334347175269495397","date":"2025-10-10T10:18:24+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-10T08:18:09+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-10T08:16:18+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-06T12:09:52+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Computational Materials","date":"2025-09-22T14:04:47+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-computational-materials","isNatureJournal":false,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"npjcompumats","sideBox":"Learn more about [npj Computational Materials](http://www.nature.com/npjcompumats/)","snPcode":"41524","submissionUrl":"https://mts-npjcompumats.nature.com/","title":"npj Computational Materials","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"e1f7743e-410f-4c23-a278-0bafbce8aeb3","owner":[],"postedDate":"October 23rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":56640493,"name":"Physical sciences/Materials science"},{"id":56640494,"name":"Physical sciences/Mathematics and computing"},{"id":56640495,"name":"Physical sciences/Physics"}],"tags":[],"updatedAt":"2026-04-07T16:12:18+00:00","versionOfRecord":{"articleIdentity":"rs-7685800","link":"https://doi.org/10.1038/s41524-026-01999-x","journal":{"identity":"npj-computational-materials","isVorOnly":false,"title":"npj Computational Materials"},"publishedOn":"2026-04-03 16:00:03","publishedOnDateReadable":"April 3rd, 2026"},"versionCreatedAt":"2025-10-23 23:41:32","video":"","vorDoi":"10.1038/s41524-026-01999-x","vorDoiUrl":"https://doi.org/10.1038/s41524-026-01999-x","workflowStages":[]},"version":"v1","identity":"rs-7685800","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7685800","identity":"rs-7685800","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}