Comparison of Deep Learning Models for 1D Magnetotelluric Inversion

Comparison of Deep Learning Models for 1D Magnetotelluric Inversion | 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 Comparison of Deep Learning Models for 1D Magnetotelluric Inversion Hakim SAIBI, Abdelhadi Hireche, Takeshi Tsuji, Mohammed Y. Ali This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6867744/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 paper presents a comparative study of three deep learning architectures for one-dimensional magnetotelluric (MT) inversion: Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Informer models. We developed a comprehensive framework for generating realistic synthetic MT data, training the models, and evaluating their performance through multiple quantitative metrics. Our synthetic data set consisted of 10,000 samples with 25 periods spanning 10 -3 to 10 3 seconds, created using statistical parameters derived from real MT data. Each model was trained on apparent resistivity and phase responses to recover subsurface resistivity profiles. The results show that the recurrent neural network architectures (GRU and LSTM) slightly outperform the attention-based Informer model, with the GRU achieving the best overall performance (MSE of 97.67 Ohm.m 2 , R² of 0.44). Despite differences in their architectures, all models successfully captured the major resistivity contrasts in the subsurface. When applied to real MT data from the UAE, the models showed promising results in reconstructing subsurface structures. This study demonstrates the viability of deep learning approaches for MT inversion, with potential applications in subsurface imaging for efficient field interpretations. Geophysics Artificial Intelligence and Machine Learning Magnetotellurics Deep learning Neural networks Geophysical inversion LSTM GRU Informer Resistivity profiling Subsurface imaging Recurrent neural networks Full Text Additional Declarations The authors declare no competing interests. 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-6867744","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":469547313,"identity":"826891c8-383c-4163-87b7-d7cd356ac4e1","order_by":0,"name":"Hakim SAIBI","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7UlEQVRIiWNgGAWjYBACAwY2hgMgBpsEY+MDkrU0GxCtBQIkgLqI0mLOfizx0A2GOnk+6ea2ap4am8QG9sMPGH5U4NZi2ZN24HAOw2HDNpmDbbd5jqUlNvCkGTD2nMHjsAPpDUAtBxjbJBKBWtgOJzYw5DAw8Lbh0XL+OUhLnT1ISzHPv/+JDfxvGBj//sOj5QbYYcyJIC3MvG0HEhskgFzeBnxaniUczjE4nAz0S7Pk3L5k4zaJZwaHZY7hc1ia8eecijrb+bPbH354881Otp8/+eHDNzW4tUA1IrFB8XSAkIZRMApGwSgYBfgBAPo/Ujf33r4uAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0001-8803-6945","institution":"United Arab Emirates University","correspondingAuthor":true,"prefix":"","firstName":"Hakim","middleName":"","lastName":"SAIBI","suffix":""},{"id":469547314,"identity":"ff3253b7-9066-4cef-92dc-34a127f67240","order_by":1,"name":"Abdelhadi Hireche","email":"","orcid":"https://orcid.org/0009-0000-0633-9281","institution":"United Arab Emirates University","correspondingAuthor":false,"prefix":"","firstName":"Abdelhadi","middleName":"","lastName":"Hireche","suffix":""},{"id":469547315,"identity":"76a8d9a8-9f27-404b-a656-51d784362c32","order_by":2,"name":"Takeshi Tsuji","email":"","orcid":"https://orcid.org/0000-0003-0951-4596","institution":"The University of Tokyo","correspondingAuthor":false,"prefix":"","firstName":"Takeshi","middleName":"","lastName":"Tsuji","suffix":""},{"id":469547912,"identity":"aab08173-b244-4071-b594-ad6fdea8aeb0","order_by":3,"name":"Mohammed Y. Ali","email":"","orcid":"https://orcid.org/0000-0001-7502-3897","institution":"Khalifa University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Mohammed","middleName":"Y.","lastName":"Ali","suffix":""}],"badges":[],"createdAt":"2025-06-11 04:25:14","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":true,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":true},"doi":"10.21203/rs.3.rs-6867744/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6867744/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":84380466,"identity":"21778f18-b277-4d13-a1ff-fab784450db7","added_by":"auto","created_at":"2025-06-11 09:10:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3541780,"visible":true,"origin":"","legend":"","description":"","filename":"AppliedComputingandGeosciences.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6867744/v1_covered_6c60f6a3-08b2-450d-9c25-2dcb4dccc0b5.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eComparison of Deep Learning Models for 1D Magnetotelluric Inversion\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[{"identity":"015ebb4e-2a68-48b3-8dae-96f681c982d2","identifier":"10.13039/501100006013","name":"United Arab Emirates University","awardNumber":"12R178, 12R284","order_by":0}],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"United Arab Emirates University","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":"Magnetotellurics, Deep learning, Neural networks, Geophysical inversion, LSTM, GRU, Informer, Resistivity profiling, Subsurface imaging, Recurrent neural networks","lastPublishedDoi":"10.21203/rs.3.rs-6867744/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6867744/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper presents a comparative study of three deep learning architectures for one-dimensional magnetotelluric (MT) inversion: Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Informer models. We developed a comprehensive framework for generating realistic synthetic MT data, training the models, and evaluating their performance through multiple quantitative metrics. Our synthetic data set consisted of 10,000 samples with 25 periods spanning 10\u003csup\u003e-3\u003c/sup\u003e to 10\u003csup\u003e3\u003c/sup\u003e seconds, created using statistical parameters derived from real MT data. Each model was trained on apparent resistivity and phase responses to recover subsurface resistivity profiles. The results show that the recurrent neural network architectures (GRU and LSTM) slightly outperform the attention-based Informer model, with the GRU achieving the best overall performance (MSE of 97.67 Ohm.m\u003csup\u003e2\u003c/sup\u003e, R² of 0.44). Despite differences in their architectures, all models successfully captured the major resistivity contrasts in the subsurface. When applied to real MT data from the UAE, the models showed promising results in reconstructing subsurface structures. This study demonstrates the viability of deep learning approaches for MT inversion, with potential applications in subsurface imaging for efficient field interpretations.\u003c/p\u003e","manuscriptTitle":"Comparison of Deep Learning Models for 1D Magnetotelluric Inversion","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-11 09:02:28","doi":"10.21203/rs.3.rs-6867744/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":"cf56936d-83c1-4944-b0ef-47ea5e61b450","owner":[],"postedDate":"June 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":49855067,"name":"Geophysics"},{"id":49855068,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-06-11T09:02:28+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-11 09:02:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6867744","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6867744","identity":"rs-6867744","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}