Elite GA-based Feature Selection of LSTM for Earthquake Prediction

Elite GA-based Feature Selection of LSTM for Earthquake Prediction | 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 Elite GA-based Feature Selection of LSTM for Earthquake Prediction Zhiwei Ye, Wuyang Lan, Wen Zhou, Qiyi He, Liang Hong, Xinguo Xu, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3049982/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 08 Jun, 2024 Read the published version in The Journal of Supercomputing → Version 1 posted 9 You are reading this latest preprint version Abstract Earthquake magnitude prediction is an extremely difficult task that has been studied by various machine learning researchers. However, the redundant features and time series properties hinder the development of prediction models. Elite Genetic Algorithm (EGA) has the advantages in searching optimal feature subsets, meanwhile, Long Short-Term Memory (LSTM) is dedicated to processing time series and complex data. Therefore, we propose an EGA-based feature selection of LSTM model (EGA-LSTM) for time series earthquake prediction. First, the acoustic and electromagnetics data of the AETA system we developed are fused and preprocessed by EGA, aiming to find strong correlation indicators. Second, LSTM is introduced to execute magnitude prediction with the selected features. Specifically, the RMSE of LSTM and the ratio of selected features are chosen as fitness components of EGA. Finally, we test the proposed EGA-LSTM on the AETA data of Sichuan province, including the influence of data in different periods ($timePeriod$) and fitness function weights ($\omega_a$ and $\omega_F$) on the prediction results. Linear Regression (LR), Support Vector Regression (SVR), Adaboost, Random Forest (RF), standard GA (SGA), steadyGA, and three Differential Evolution Algorithms (DEs) are adopted as our baselines. Experimental results demonstrate that all the methods can get the best performance when $timePeriod = 0:00-8:00$, $\omega_a=1$, and $\omega_F=0.8$. Moreover, our proposed approach is superior to state-of-the-art approaches on the evaluation indicators MAE, MSE, RMSE, and $R_2$. Non-parametric tests reveal that EGA-LSTM is significantly different from others and outperforms the standard LSTM. Earthquake magnitude prediction Elite genetic algorithm Long short-term memory AETA Full Text Additional Declarations No competing interests reported. Supplementary Files EQTransformermaster.zip areafeature.rar Cite Share Download PDF Status: Published Journal Publication published 08 Jun, 2024 Read the published version in The Journal of Supercomputing → Version 1 posted Editorial decision: Revision requested 03 Feb, 2024 Reviews received at journal 13 Jan, 2024 Reviews received at journal 12 Jan, 2024 Reviewers agreed at journal 12 Jan, 2024 Reviewers agreed at journal 12 Jan, 2024 Reviewers invited by journal 12 Jan, 2024 Editor assigned by journal 15 Jun, 2023 Submission checks completed at journal 15 Jun, 2023 First submitted to journal 11 Jun, 2023 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-3049982","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":210256529,"identity":"b90d9531-2a5d-4d30-a10f-52eb0655d755","order_by":0,"name":"Zhiwei Ye","email":"","orcid":"","institution":"Hubei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhiwei","middleName":"","lastName":"Ye","suffix":""},{"id":210256530,"identity":"ef4c4c57-1125-41ff-9ec8-14556eb1df10","order_by":1,"name":"Wuyang Lan","email":"","orcid":"","institution":"Hubei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Wuyang","middleName":"","lastName":"Lan","suffix":""},{"id":210256531,"identity":"cf88d6a8-8376-40b8-9e25-4e55c5ff3720","order_by":2,"name":"Wen Zhou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxklEQVRIiWNgGAWjYPCCA3IGEmAGM/FajIFaGBtI0pK4gWgt8jMSWDfdbLuTvl26x/wBQ4V1YgP72QN4tTDOSGC7ndv2LHfnnDOGDQxn0hMbePIS8GphlgZp2XY4d8ONHMMGxrbDiQ0SPAZ4tbBBtaQbgLX8I0ILD1RLAkRLAxFaJOQfALX8O2y44c6xwhkJx9KN23hy8GuR7znAdjvnzGF5g9vNGz58qLGW7Wc/g18LAwP/BwQ7AeQ7AupHwSgYBaNgFBABAJ3FSh+587WOAAAAAElFTkSuQmCC","orcid":"","institution":"Hubei University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Wen","middleName":"","lastName":"Zhou","suffix":""},{"id":210256532,"identity":"e0d88e72-1013-4af5-9898-80d8415cf7db","order_by":3,"name":"Qiyi He","email":"","orcid":"","institution":"Hubei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Qiyi","middleName":"","lastName":"He","suffix":""},{"id":210256533,"identity":"5dc21aa3-394b-4d6c-9af9-4eef6361f7f1","order_by":4,"name":"Liang Hong","email":"","orcid":"","institution":"Hubei Provincial Geographical National Conditions Monitoring Center","correspondingAuthor":false,"prefix":"","firstName":"Liang","middleName":"","lastName":"Hong","suffix":""},{"id":210256534,"identity":"da9e7551-9b3c-461e-a98f-f79fc1558be8","order_by":5,"name":"Xinguo Xu","email":"","orcid":"","institution":"Hubei Provincial Geographical National Conditions Monitoring Center","correspondingAuthor":false,"prefix":"","firstName":"Xinguo","middleName":"","lastName":"Xu","suffix":""},{"id":210256535,"identity":"931556de-8270-4c15-b82c-bdda3def62b4","order_by":6,"name":"Yunxuan Gao","email":"","orcid":"","institution":"Hubei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yunxuan","middleName":"","lastName":"Gao","suffix":""}],"badges":[],"createdAt":"2023-06-11 17:44:03","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3049982/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3049982/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11227-024-06218-2","type":"published","date":"2024-06-08T14:48:26+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":58822093,"identity":"49f81ad8-11f1-4dd7-8c9a-b685c953adda","added_by":"auto","created_at":"2024-06-21 16:30:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5105964,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3049982/v1_covered_6385a0eb-3337-4ff0-9bbc-8fd61fca2477.pdf"},{"id":38737465,"identity":"f2392a8e-e4f1-4651-a590-c11023c1d192","added_by":"auto","created_at":"2023-06-19 03:14:53","extension":"zip","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":32882283,"visible":true,"origin":"","legend":"","description":"","filename":"EQTransformermaster.zip","url":"https://assets-eu.researchsquare.com/files/rs-3049982/v1/c8fbc62618e2de5a77bdef2c.zip"},{"id":38737464,"identity":"b73a8379-bbf5-4594-b0ef-24b7d73d1201","added_by":"auto","created_at":"2023-06-19 03:14:52","extension":"rar","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":130126,"visible":true,"origin":"","legend":"","description":"","filename":"areafeature.rar","url":"https://assets-eu.researchsquare.com/files/rs-3049982/v1/ac891faf2b8ddc2ccf846dc5.rar"}],"financialInterests":"No competing interests reported.","formattedTitle":"Elite GA-based Feature Selection of LSTM for Earthquake Prediction","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":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Earthquake magnitude prediction, Elite genetic algorithm, Long short-term memory, AETA","lastPublishedDoi":"10.21203/rs.3.rs-3049982/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3049982/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Earthquake magnitude prediction is an extremely difficult task that has been studied by various machine learning researchers. However, the redundant features and time series properties hinder the development of prediction models. Elite Genetic Algorithm (EGA) has the advantages in searching optimal feature subsets, meanwhile, Long Short-Term Memory (LSTM) is dedicated to processing time series and complex data. Therefore, we propose an EGA-based feature selection of LSTM model (EGA-LSTM) for time series earthquake prediction. First, the acoustic and electromagnetics data of the AETA system we developed are fused and preprocessed by EGA, aiming to find strong correlation indicators. Second, LSTM is introduced to execute magnitude prediction with the selected features. Specifically, the RMSE of LSTM and the ratio of selected features are chosen as fitness components of EGA. Finally, we test the proposed EGA-LSTM on the AETA data of Sichuan province, including the influence of data in different periods ($timePeriod$) and fitness function weights ($\\omega_a$ and $\\omega_F$) on the prediction results. Linear Regression (LR), Support Vector Regression (SVR), Adaboost, Random Forest (RF), standard GA (SGA), steadyGA, and three Differential Evolution Algorithms (DEs) are adopted as our baselines. Experimental results demonstrate that all the methods can get the best performance when $timePeriod = 0:00-8:00$, $\\omega_a=1$, and $\\omega_F=0.8$. Moreover, our proposed approach is superior to state-of-the-art approaches on the evaluation indicators MAE, MSE, RMSE, and $R_2$. Non-parametric tests reveal that EGA-LSTM is significantly different from others and outperforms the standard LSTM.","manuscriptTitle":"Elite GA-based Feature Selection of LSTM for Earthquake Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-06-19 03:14:47","doi":"10.21203/rs.3.rs-3049982/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-02-03T16:49:25+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-01-13T06:53:18+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-01-13T04:09:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"601cdf8c-fd2e-46ab-9930-76f3b4cbfec5","date":"2024-01-13T01:35:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"f716dc73-2913-4d0e-9a4d-7b9781724b55","date":"2024-01-12T19:57:59+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-01-12T19:53:58+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2023-06-15T15:11:11+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2023-06-15T15:11:11+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Journal of Supercomputing","date":"2023-06-11T17:30:00+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"0e732a31-3e4e-4668-a502-4de8609007da","owner":[],"postedDate":"June 19th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-06-21T14:48:26+00:00","versionOfRecord":{"articleIdentity":"rs-3049982","link":"https://doi.org/10.1007/s11227-024-06218-2","journal":{"identity":"the-journal-of-supercomputing","isVorOnly":false,"title":"The Journal of Supercomputing"},"publishedOn":"2024-06-08 14:48:26","publishedOnDateReadable":"June 8th, 2024"},"versionCreatedAt":"2023-06-19 03:14:47","video":"","vorDoi":"10.1007/s11227-024-06218-2","vorDoiUrl":"https://doi.org/10.1007/s11227-024-06218-2","workflowStages":[]},"version":"v1","identity":"rs-3049982","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3049982","identity":"rs-3049982","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}