Earthquake Forecasting and Major Event Detection Using Multi-Task Deep Learning in Central Asia

preprint OA: closed
Full text JSON View at publisher
Full text 27,744 characters · extracted from preprint-html · click to expand
Earthquake Forecasting and Major Event Detection Using Multi-Task Deep Learning in Central Asia | 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 Earthquake Forecasting and Major Event Detection Using Multi-Task Deep Learning in Central Asia Bufatima Nurmakhamad kyzy, Remudin Reshid Mekuria This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7406834/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 This manuscript presents a deep learning approach for earthquake magnitude forecasting and major event detection (M\((\geq)\)5) in Central Asia, with a focus on Kyrgyzstan. A Multi-Task Learning (MTL) model with an attention-based Long-Short-Term Memory (LSTM) architecture is used to perform two tasks: (i) regression to forecast earthquake magnitude, and (ii) binary classification to determine if a big event will happen in the next 30 days. Input features are spatiotemporal, fault proximity, rolling seismic statistics and time-based indicators. Class imbalance in the binary task was handled by oversampling. Hyperparameter tuning was done using Optuna and the model was evaluated using Mean Absolute Error (MAE), F1-score, ROC AUC and PR AUC. The final model achieved MAE of 0.154 for magnitude forecasting and F1-score of 0.989 for big event detection, with ROC AUC and PR AUC of 0.993 and 0.9996 respectively. The approach was validated on historical earthquake data and tested on a real case study. The model is reliable and applicable. The proposed method is good for regional seismic risk forecasting and can be used for early warning systems and public safety in seismically active regions like Kyrgyzstan. Earthquake prediction Deep learning Multi-Task Learning LSTM Seismic forecasting Magnitude regression Binary classification Attention mechanism Central Asia Full Text Additional Declarations No competing interests reported. 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-7406834","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":532923253,"identity":"5ee0b6cd-5561-41c4-9e34-0f470f7de9af","order_by":0,"name":"Bufatima Nurmakhamad kyzy","email":"data:image/png;base64,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","orcid":"","institution":"International Alatoo University","correspondingAuthor":true,"prefix":"","firstName":"Bufatima","middleName":"Nurmakhamad","lastName":"kyzy","suffix":""},{"id":532923254,"identity":"c6c6c1c7-7638-4265-9b33-cc6da70689d5","order_by":1,"name":"Remudin Reshid Mekuria","email":"","orcid":"","institution":"International Alatoo University","correspondingAuthor":false,"prefix":"","firstName":"Remudin","middleName":"Reshid","lastName":"Mekuria","suffix":""}],"badges":[],"createdAt":"2025-08-19 09:23:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7406834/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7406834/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94148847,"identity":"9990ca99-35c8-48bb-acc1-c6e5e8689621","added_by":"auto","created_at":"2025-10-22 23:22:52","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4557,"visible":true,"origin":"","legend":"","description":"","filename":"ef00db2bcc37467184767b5aaf5762d4.json","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/7b306bdeb6ad0099b3b8f756.json"},{"id":94148848,"identity":"ebcc4676-0dc3-4490-ace6-d1248d024f1a","added_by":"auto","created_at":"2025-10-22 23:22:52","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":127128,"visible":true,"origin":"","legend":"","description":"","filename":"ef00db2bcc37467184767b5aaf5762d41enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/32ec5aa5510c6219a7d479f5.xml"},{"id":94149809,"identity":"0e2f16dc-8605-4a25-91d5-c0e52b041c49","added_by":"auto","created_at":"2025-10-22 23:38:53","extension":"png","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":77758,"visible":true,"origin":"","legend":"","description":"","filename":"c.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/08cbc53e1a03b5a2ecde8c07.png"},{"id":94148852,"identity":"984b7688-b5b2-4733-92de-7a7d8d541c55","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":544866,"visible":true,"origin":"","legend":"","description":"","filename":"caec.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/9ba0761724373e414b218772.png"},{"id":94149810,"identity":"8992770d-0777-4694-b074-bd223d958817","added_by":"auto","created_at":"2025-10-22 23:38:53","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":107706,"visible":true,"origin":"","legend":"","description":"","filename":"coverletterdiscovergeoscience.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/6bbd9d997f3d227169678b74.pdf"},{"id":94149568,"identity":"8a58c10b-4dbf-48c0-9ad9-69ed4baf9d8e","added_by":"auto","created_at":"2025-10-22 23:30:53","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":76591,"visible":true,"origin":"","legend":"","description":"","filename":"depthhist.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/074202dd0ac9d37eda739881.png"},{"id":94149570,"identity":"a15e151a-4609-4c1b-8a51-306bc272ede2","added_by":"auto","created_at":"2025-10-22 23:30:53","extension":"pdf","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2318889,"visible":true,"origin":"","legend":"","description":"","filename":"dgarticle2025.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/b7afcf3728a51f8419703b3a.pdf"},{"id":94148849,"identity":"1ef3ab5c-1bb9-4bd7-91b1-86105c5984db","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":70187,"visible":true,"origin":"","legend":"","description":"","filename":"faultdist.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/ce65990b0eac927ca316f66c.png"},{"id":94148857,"identity":"6f43df55-8027-4d27-939b-3e4675c91aae","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":176153,"visible":true,"origin":"","legend":"","description":"","filename":"kgdensity.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/2af51f7fd3920799d6a4caea.png"},{"id":94148855,"identity":"d557f34f-b89a-48ea-8af5-e4b8dafcd33a","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":69338,"visible":true,"origin":"","legend":"","description":"","filename":"kgdepth.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/56a3fa6ece0aba4b0a91fde2.png"},{"id":94148860,"identity":"a5c79fa7-cdca-4ba3-8bef-4e54e24e1c26","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":73888,"visible":true,"origin":"","legend":"","description":"","filename":"kgfd.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/1f9dbb733ae50ff5f73ade0e.png"},{"id":94148884,"identity":"6839451d-259b-4324-8acd-c9cbb9b4be16","added_by":"auto","created_at":"2025-10-22 23:22:54","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":70987,"visible":true,"origin":"","legend":"","description":"","filename":"kgmag.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/b277e8380e76013484e598ce.png"},{"id":94148866,"identity":"04170746-9b95-44d2-a5d2-1ad53b7a4cbd","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":167194,"visible":true,"origin":"","legend":"","description":"","filename":"kgmd.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/e0b35c40cbb5648feefb340f.png"},{"id":94148861,"identity":"596bc972-a0c7-4cc6-8190-4b65f6cacacc","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":73382,"visible":true,"origin":"","legend":"","description":"","filename":"kgyearly.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/1d5673729d731c1cb2197813.png"},{"id":94148875,"identity":"cde83e50-9bef-497d-8deb-b9cc30fe588b","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":414496,"visible":true,"origin":"","legend":"","description":"","filename":"kyec.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/a0dc26aa5df460a2252b754f.png"},{"id":94149575,"identity":"f9adf169-eee8-406a-9538-1d213f0a5cda","added_by":"auto","created_at":"2025-10-22 23:30:53","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21582,"visible":true,"origin":"","legend":"","description":"","filename":"lrcm.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/01b78c6ce14f1ae03375532c.png"},{"id":94149579,"identity":"3454161f-1c5b-43f0-967e-60e46399bfb3","added_by":"auto","created_at":"2025-10-22 23:30:54","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24708,"visible":true,"origin":"","legend":"","description":"","filename":"lrprc.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/7d2589883e15a23e7235a841.png"},{"id":94149578,"identity":"709728b3-95f1-4182-a9a9-efd069cbb488","added_by":"auto","created_at":"2025-10-22 23:30:53","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":22346,"visible":true,"origin":"","legend":"","description":"","filename":"lrrc.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/ee0f165b53c4d1ceb0414974.png"},{"id":94149912,"identity":"4398e70c-92f0-4ec1-bcd6-99c651e5069d","added_by":"auto","created_at":"2025-10-22 23:46:53","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36571,"visible":true,"origin":"","legend":"","description":"","filename":"lrsc.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/158b4fff7c2626d3e1a4d9f3.png"},{"id":94148888,"identity":"05046d71-05e8-4bf8-a6c3-d77223632bdc","added_by":"auto","created_at":"2025-10-22 23:22:54","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":489857,"visible":true,"origin":"","legend":"","description":"","filename":"magdepth.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/aec7d52791b067e5da962a82.png"},{"id":94148889,"identity":"8a9134b4-effe-4e6b-bb52-0c1cf0225f02","added_by":"auto","created_at":"2025-10-22 23:22:54","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":66719,"visible":true,"origin":"","legend":"","description":"","filename":"maghist.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/599fc4319c82c6ec0e339a83.png"},{"id":94148876,"identity":"22e898eb-9895-4f84-8e41-dd576b0aa2d1","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":331256,"visible":true,"origin":"","legend":"","description":"","filename":"map.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/b1dbed5d0d2e75ddcfc1f6a2.png"},{"id":94148881,"identity":"bbfce291-639d-46d8-8229-c28aae711809","added_by":"auto","created_at":"2025-10-22 23:22:54","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":81751,"visible":true,"origin":"","legend":"","description":"","filename":"miss.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/b8a577b94374e06be0d5d563.png"},{"id":94149580,"identity":"3086c968-4897-4e4c-8fc9-06b361400593","added_by":"auto","created_at":"2025-10-22 23:30:54","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":54037,"visible":true,"origin":"","legend":"","description":"","filename":"month.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/5146c6a639b19972b5b7495f.png"},{"id":94149574,"identity":"c6b51230-3946-4e5c-ba8a-a170aaeea2da","added_by":"auto","created_at":"2025-10-22 23:30:53","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20039,"visible":true,"origin":"","legend":"","description":"","filename":"mtlcm.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/527a1f7c1ca05a207b67de60.png"},{"id":94148862,"identity":"3be27149-f97c-4c93-8adb-129126933f7d","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15560,"visible":true,"origin":"","legend":"","description":"","filename":"mtlprc.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/7a317c7287c679085cb156cc.png"},{"id":94149573,"identity":"d91ce2d7-2aac-4fbe-a93e-6093d34f1b12","added_by":"auto","created_at":"2025-10-22 23:30:53","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16989,"visible":true,"origin":"","legend":"","description":"","filename":"mtlrc.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/3296279e132fc0a18b08b550.png"},{"id":94148870,"identity":"564737bc-92a8-43e2-86f0-c24b177c50b4","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55083,"visible":true,"origin":"","legend":"","description":"","filename":"mtlsc.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/7ab9592e6403cf3c33b6b479.png"},{"id":94148859,"identity":"3ac78457-cc31-4cb6-9b3e-3e5d9355b1ad","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40393,"visible":true,"origin":"","legend":"","description":"","filename":"pibdm.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/83b39c6bcac2de298cb3d38a.png"},{"id":94148885,"identity":"374596e8-7146-41e7-9a02-6686fc778ff2","added_by":"auto","created_at":"2025-10-22 23:22:54","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40088,"visible":true,"origin":"","legend":"","description":"","filename":"pirdm.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/e43f62a557788844d0f5662f.png"},{"id":94148869,"identity":"ab78bc3a-e244-4035-9c52-5e37cb85e34b","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"pdf","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":78959,"visible":true,"origin":"","legend":"","description":"","filename":"response.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/9c1013c682c4ba52096600c4.pdf"},{"id":94148863,"identity":"cd679cfe-4fef-4aae-ac3d-e02644be19b6","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"png","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20379,"visible":true,"origin":"","legend":"","description":"","filename":"rfcm.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/a1fca20d1edb371dd3b9996e.png"},{"id":94148867,"identity":"7d41d538-0d64-46f4-abe1-b704dccebd5a","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"png","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28128,"visible":true,"origin":"","legend":"","description":"","filename":"rfprc.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/b85fad5dfd586261d5045952.png"},{"id":94148882,"identity":"a563209a-7fff-4a15-8fed-9931045fd945","added_by":"auto","created_at":"2025-10-22 23:22:54","extension":"png","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":26363,"visible":true,"origin":"","legend":"","description":"","filename":"rfrc.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/6ad2aa75f195099ea97ee494.png"},{"id":94148865,"identity":"498b877d-eae1-4fcf-977b-dea44a321fbd","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"png","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":51986,"visible":true,"origin":"","legend":"","description":"","filename":"rfsc.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/e96855cbfeb27358e2cc843d.png"},{"id":94148874,"identity":"b287fa0f-003f-4462-8891-5ec031db4cd0","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"cls","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55857,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/3074682aeea168292d173a08.cls"},{"id":94148868,"identity":"5d3c7628-6be1-4cca-9127-4c39a5dc21aa","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"png","order_by":36,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":34369,"visible":true,"origin":"","legend":"","description":"","filename":"tvlc.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/8bfc3fe481b6eabb3658b28b.png"},{"id":94149812,"identity":"d99e0313-e5b6-4cc6-b694-e5a2241a43d2","added_by":"auto","created_at":"2025-10-22 23:38:53","extension":"png","order_by":37,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":79572,"visible":true,"origin":"","legend":"","description":"","filename":"yearly.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/f7f28b0c59561ec485b92e43.png"},{"id":94148879,"identity":"57cc62e0-37c6-489d-95b5-a61179096c35","added_by":"auto","created_at":"2025-10-22 23:22:54","extension":"png","order_by":38,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":66979,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinec.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/ebc0abc538ff27ea53df4ee3.png"},{"id":94148886,"identity":"777837ea-aee0-49d0-9e10-2e8442a675f9","added_by":"auto","created_at":"2025-10-22 23:22:54","extension":"png","order_by":39,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":490685,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinecaec.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/2f4aa661431d88d3761da011.png"},{"id":94148880,"identity":"4aa849fa-7e49-442b-8674-7a037d9fd1d4","added_by":"auto","created_at":"2025-10-22 23:22:54","extension":"png","order_by":48,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":370418,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinekyec.png","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/7428898a8f0525df1f7ceb20.png"},{"id":94148877,"identity":"062f1c11-98b6-4b0c-9e04-fc23cbe87c1b","added_by":"auto","created_at":"2025-10-22 23:22:53","extension":"xml","order_by":70,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":142946,"visible":true,"origin":"","legend":"","description":"","filename":"ef00db2bcc37467184767b5aaf5762d41structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/13e23d03eea8ab0c2e659c7d.xml"},{"id":94149577,"identity":"d4eb36b0-28a9-43b0-b2f6-6d7436767e85","added_by":"auto","created_at":"2025-10-22 23:30:53","extension":"html","order_by":71,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":156404,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1/e0b34976870308f4c3c457e9.html"},{"id":98383709,"identity":"fc29f4ee-69ac-4777-94da-94ecb77e79ad","added_by":"auto","created_at":"2025-12-17 08:10:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1963623,"visible":true,"origin":"","legend":"","description":"","filename":"dgarticle2025.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7406834/v1_covered_6ca15bbb-656b-4c8d-a372-28bfca0431a2.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Earthquake Forecasting and Major Event Detection Using Multi-Task Deep Learning in Central Asia","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Earthquake prediction, Deep learning, Multi-Task Learning, LSTM, Seismic forecasting, Magnitude regression, Binary classification, Attention mechanism, Central Asia","lastPublishedDoi":"10.21203/rs.3.rs-7406834/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7406834/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis manuscript presents a deep learning approach for earthquake magnitude forecasting and major event detection (M\\((\\geq)\\)5) in Central Asia, with a focus on Kyrgyzstan. A Multi-Task Learning (MTL) model with an attention-based Long-Short-Term Memory (LSTM) architecture is used to perform two tasks: (i) regression to forecast earthquake magnitude, and (ii) binary classification to determine if a big event will happen in the next 30 days.\u003c/p\u003e\n\u003cp\u003eInput features are spatiotemporal, fault proximity, rolling seismic statistics and time-based indicators. Class imbalance in the binary task was handled by oversampling. Hyperparameter tuning was done using Optuna and the model was evaluated using Mean Absolute Error (MAE), F1-score, ROC AUC and PR AUC. The final model achieved MAE of 0.154 for magnitude forecasting and F1-score of 0.989 for big event detection, with ROC AUC and PR AUC of 0.993 and 0.9996 respectively.\u003c/p\u003e\n\u003cp\u003eThe approach was validated on historical earthquake data and tested on a real case study. The model is reliable and applicable. The proposed method is good for regional seismic risk forecasting and can be used for early warning systems and public safety in seismically active regions like Kyrgyzstan.\u003c/p\u003e","manuscriptTitle":"Earthquake Forecasting and Major Event Detection Using Multi-Task Deep Learning in Central Asia","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-22 23:22:46","doi":"10.21203/rs.3.rs-7406834/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":"b94f8d5a-e8a2-4dad-aa4a-526166520405","owner":[],"postedDate":"October 22nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-12-17T08:10:14+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-22 23:22:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7406834","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7406834","identity":"rs-7406834","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","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.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00