A Physics-Informed Deep Learning and Probabilistic Inference Framework for Real-Time Single-Station Earthquake Detection and Magnitude Estimation

A Physics-Informed Deep Learning and Probabilistic Inference Framework for Real-Time Single-Station Earthquake Detection and Magnitude Estimation | 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 Research Article A Physics-Informed Deep Learning and Probabilistic Inference Framework for Real-Time Single-Station Earthquake Detection and Magnitude Estimation SUJAL THAPA, RAJ BASNET, ANSHUL PANWAR, SIMAR SINGH RAYAT, AKSHAT VERMA, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7479899/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 20 Feb, 2026 Read the published version in Bulletin of Earthquake Engineering → Version 1 posted 5 You are reading this latest preprint version Abstract Earthquake Early Warning (EEW) systems are important for mitigating casualties and damage to infrastructure by providing seconds of advance notice of damaging seismic waves. However, established EEW systems depend on dense seismic networks, handcrafted features, or multi-station triangulation to find an earthquake’s P-wave arrival time requiring substantial financial investment, time, and infrastructure unsuitable for resource-constrained areas. The contribution of this paper is to propose a hybrid single-station framework, which applies physics-informed preprocessing, deep learning, and probabilistic modelling. The tri-axial accelerometer signals are pre-processed via double integration and bandpass filtering and analysed via a U-Net + + encoder–decoder with dilated convolutions and Multi-Head Self-Attention (MHSA). This allows the U-Net + + architecture to simultaneously fine-tune recognition of spatial-temporal features and to model the global dependency context necessary for accurate P-wave detection. Gaussian label smoothing has been incorporated to adapt and enhance robustness to potential uncertainty in the annotation labels, while a Bayesian Markov Chain Monte Carlo (MCMC) method provides an easy procedure for obtaining probabilistic (and noise-invariant) magnitude estimation. The evaluation across two datasets: the Stanford Earthquake Dataset (STEAD), and IoT-based simulation results illustrate significant margins of improvement, e.g., approximately 10–12% greater F1-scores for P-wave detection, and an approximately 35% lower rate of magnitude-estimation errors. By demonstrating noteworthy improvements in earthquake detection and magnitude estimation, the hybrid single-station framework is a cost-effective and real-time EEW with multiple pathways for deployment at a global scale. Earthquake Early Warning Single-Station Detection Physics-Informed Deep Learning Machine Learning Based Magnitude Detection Microprocessor Embedded Systems Full Text Cite Share Download PDF Status: Published Journal Publication published 20 Feb, 2026 Read the published version in Bulletin of Earthquake Engineering → Version 1 posted Reviewers agreed at journal 17 Nov, 2025 Reviewers invited by journal 08 Sep, 2025 Editor invited by journal 06 Sep, 2025 Editor assigned by journal 06 Sep, 2025 First submitted to journal 04 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-7479899","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":512051052,"identity":"41a24743-cd80-447e-8938-927a770b864f","order_by":0,"name":"SUJAL THAPA","email":"","orcid":"","institution":"Graphic Era Hill University","correspondingAuthor":false,"prefix":"","firstName":"SUJAL","middleName":"","lastName":"THAPA","suffix":""},{"id":512051053,"identity":"17a183bf-fb64-4aa7-b46e-dfbb25e43fe6","order_by":1,"name":"RAJ BASNET","email":"","orcid":"","institution":"Graphic Era Hill University","correspondingAuthor":false,"prefix":"","firstName":"RAJ","middleName":"","lastName":"BASNET","suffix":""},{"id":512051054,"identity":"534c8dbe-538c-47f7-8988-56b124c35e3c","order_by":2,"name":"ANSHUL PANWAR","email":"","orcid":"","institution":"Graphic Era Hill University","correspondingAuthor":false,"prefix":"","firstName":"ANSHUL","middleName":"","lastName":"PANWAR","suffix":""},{"id":512051055,"identity":"59ccbe72-0f32-4921-ad0f-166539fff04f","order_by":3,"name":"SIMAR SINGH RAYAT","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5UlEQVRIiWNgGAWjYPACCSBmPgBiyBCn4QBYC1sCSAsPsVpAgMcATBJUbd5+xvDzhz8W0fyzz3x+daPGgoeB/fDRDfi0yJzJMZY42CaRO+Nc7jbrnGNAh/Gkpd3Ap0WCIcdA4mCDRG7DGd5txjlsQC0SPGb4tfC/Mf5x4I9E7vwzPM+Mc/4Ro0Uix0ziAJtE7oYzPMyPc9uI0vKszOIs0C8bz7CZMef2SfCwEfQLf/LmGxV/6nLnnWF+/DnnW50cP/vhY3i1MDBwGMBYbBJgEr9yEGB/AGMxfyCsehSMglEwCkYiAABqGkbsYB4qMgAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0009-0006-7187-1198","institution":"Graphic Era Hill University","correspondingAuthor":true,"prefix":"","firstName":"SIMAR","middleName":"SINGH","lastName":"RAYAT","suffix":""},{"id":512051056,"identity":"926bf506-7ad7-46ee-974b-d708fa56e8ce","order_by":4,"name":"AKSHAT VERMA","email":"","orcid":"","institution":"Graphic Era Hill University","correspondingAuthor":false,"prefix":"","firstName":"AKSHAT","middleName":"","lastName":"VERMA","suffix":""},{"id":512051057,"identity":"68e14676-c17e-42d7-954e-767caec99bef","order_by":5,"name":"SUSHEELA DAHIYA","email":"","orcid":"","institution":"Graphic Era Hill University","correspondingAuthor":false,"prefix":"","firstName":"SUSHEELA","middleName":"","lastName":"DAHIYA","suffix":""},{"id":512051058,"identity":"1ebe514b-4f5b-4fbb-8835-de6699533cf2","order_by":6,"name":"ARUN PRATAP SINGH RATHOD","email":"","orcid":"","institution":"Graphic Era Hill University","correspondingAuthor":false,"prefix":"","firstName":"ARUN","middleName":"PRATAP SINGH","lastName":"RATHOD","suffix":""}],"badges":[],"createdAt":"2025-08-28 11:39:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7479899/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7479899/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10518-026-02403-1","type":"published","date":"2026-02-20T15:57:08+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":103251038,"identity":"23a2af07-8f24-4baf-9ce7-a63c49e52473","added_by":"auto","created_at":"2026-02-23 16:02:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1359343,"visible":true,"origin":"","legend":"","description":"","filename":"Finalearthquake.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7479899/v1_covered_72941a4e-350f-410b-b336-dd982be57e51.pdf"}],"financialInterests":"","formattedTitle":"A Physics-Informed Deep Learning and Probabilistic Inference Framework for Real-Time Single-Station Earthquake Detection and Magnitude Estimation","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":"bulletin-of-earthquake-engineering","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"beee","sideBox":"Learn more about [Bulletin of Earthquake Engineering](https://www.springer.com/journal/10518)","snPcode":"10518","submissionUrl":"https://submission.nature.com/new-submission/10518/3","title":"Bulletin of Earthquake Engineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Earthquake Early Warning, Single-Station Detection, Physics-Informed Deep Learning, Machine Learning Based Magnitude Detection, Microprocessor Embedded Systems","lastPublishedDoi":"10.21203/rs.3.rs-7479899/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7479899/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eEarthquake Early Warning (EEW) systems are important for mitigating casualties and damage to infrastructure by providing seconds of advance notice of damaging seismic waves. However, established EEW systems depend on dense seismic networks, handcrafted features, or multi-station triangulation to find an earthquake’s P-wave arrival time requiring substantial financial investment, time, and infrastructure unsuitable for resource-constrained areas. The contribution of this paper is to propose a hybrid single-station framework, which applies physics-informed preprocessing, deep learning, and probabilistic modelling. The tri-axial accelerometer signals are pre-processed via double integration and bandpass filtering and analysed via a U-Net + + encoder–decoder with dilated convolutions and Multi-Head Self-Attention (MHSA). This allows the U-Net + + architecture to simultaneously fine-tune recognition of spatial-temporal features and to model the global dependency context necessary for accurate P-wave detection. Gaussian label smoothing has been incorporated to adapt and enhance robustness to potential uncertainty in the annotation labels, while a Bayesian Markov Chain Monte Carlo (MCMC) method provides an easy procedure for obtaining probabilistic (and noise-invariant) magnitude estimation. The evaluation across two datasets: the Stanford Earthquake Dataset (STEAD), and IoT-based simulation results illustrate significant margins of improvement, e.g., approximately 10–12% greater F1-scores for P-wave detection, and an approximately 35% lower rate of magnitude-estimation errors. By demonstrating noteworthy improvements in earthquake detection and magnitude estimation, the hybrid single-station framework is a cost-effective and real-time EEW with multiple pathways for deployment at a global scale.\u003c/p\u003e","manuscriptTitle":"A Physics-Informed Deep Learning and Probabilistic Inference Framework for Real-Time Single-Station Earthquake Detection and Magnitude Estimation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-15 06:57:48","doi":"10.21203/rs.3.rs-7479899/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"","date":"2025-11-17T15:31:01+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-08T16:24:35+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"Bulletin of Earthquake Engineering","date":"2025-09-06T20:47:05+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-06T06:13:16+00:00","index":"","fulltext":""},{"type":"submitted","content":"Bulletin of Earthquake Engineering","date":"2025-09-04T17:20:36+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bulletin-of-earthquake-engineering","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"beee","sideBox":"Learn more about [Bulletin of Earthquake Engineering](https://www.springer.com/journal/10518)","snPcode":"10518","submissionUrl":"https://submission.nature.com/new-submission/10518/3","title":"Bulletin of Earthquake Engineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"0a27f922-42f2-4f75-bcec-0858aa800306","owner":[],"postedDate":"September 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-02-23T16:00:31+00:00","versionOfRecord":{"articleIdentity":"rs-7479899","link":"https://doi.org/10.1007/s10518-026-02403-1","journal":{"identity":"bulletin-of-earthquake-engineering","isVorOnly":false,"title":"Bulletin of Earthquake Engineering"},"publishedOn":"2026-02-20 15:57:08","publishedOnDateReadable":"February 20th, 2026"},"versionCreatedAt":"2025-09-15 06:57:48","video":"","vorDoi":"10.1007/s10518-026-02403-1","vorDoiUrl":"https://doi.org/10.1007/s10518-026-02403-1","workflowStages":[]},"version":"v1","identity":"rs-7479899","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7479899","identity":"rs-7479899","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}