Appraisal of Resistivity Inversion Models with Convolutional Variational Encoder-Decoder Network

Recovering the actual subsurface electrical resistivity properties from the electrical resistivity tomography data is challenging because the inverse problem is nonlinear and ill-posed. This paper proposes a Variational Encoder-Decoder (VED) based network to obtain resistivity model, which maps the...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on geoscience and remote sensing Ročník 60; s. 1
Hlavní autoři:	Wilson, Bibin, Singh, Anand, Sethi, Amit
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithms Aquifers Coders Conductivity Conductivity Distribution Data models Deep learning Electrical resistivity Electrical Resistivity Tomography Encoders-Decoders Feature extraction Geophysical measurements Inverse Problem Inverse problems Machine learning Mathematical models Tomography
ISSN:	0196-2892, 1558-0644
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Recovering the actual subsurface electrical resistivity properties from the electrical resistivity tomography data is challenging because the inverse problem is nonlinear and ill-posed. This paper proposes a Variational Encoder-Decoder (VED) based network to obtain resistivity model, which maps the apparent resistivity data (input) to true resistivity data (output). Since deep learning (DL) models are highly dependent on training sets and providing a meaningful geological resistivity model is complex, we have first developed an algorithm to construct many realistic resistivity synthetic models. Our algorithm automatically constructs an apparent resistivity pseudo-section from these resistivity models. We further computed the resistivity from two different neural architectures for comparison - UNet, and attention UNet with and without input depth encoding apparent data. In the end, we have compared our deep learning results with traditional inversion and borewell data on apparent resistivity datasets collected for aquifer mapping in the hard rock terrain of the West Medinipur district of West Bengal, India. A detailed qualitative and quantitative evaluation reveals that our VED approach is the most effective for the inversion compared to other approaches considered.
AbstractList	Recovering the actual subsurface electrical resistivity properties from the electrical resistivity tomography data is challenging because the inverse problem is nonlinear and ill-posed. This paper proposes a Variational Encoder-Decoder (VED) based network to obtain resistivity model, which maps the apparent resistivity data (input) to true resistivity data (output). Since deep learning (DL) models are highly dependent on training sets and providing a meaningful geological resistivity model is complex, we have first developed an algorithm to construct many realistic resistivity synthetic models. Our algorithm automatically constructs an apparent resistivity pseudo-section from these resistivity models. We further computed the resistivity from two different neural architectures for comparison - UNet, and attention UNet with and without input depth encoding apparent data. In the end, we have compared our deep learning results with traditional inversion and borewell data on apparent resistivity datasets collected for aquifer mapping in the hard rock terrain of the West Medinipur district of West Bengal, India. A detailed qualitative and quantitative evaluation reveals that our VED approach is the most effective for the inversion compared to other approaches considered. Recovering the actual subsurface electrical resistivity properties from the electrical resistivity tomography data is challenging because the inverse problem is nonlinear and ill-posed. This article proposes a variational encoder-decoder (VED)-based network to obtain resistivity model, which maps the apparent resistivity data (input) to true resistivity data (output). Since deep learning (DL) models are highly dependent on training sets and providing a meaningful geological resistivity model is complex, we have first developed an algorithm to construct many realistic resistivity synthetic models. Our algorithm automatically constructs an apparent resistivity pseudo-section from these resistivity models. We further computed the resistivity from two different neural architectures for comparison–UNet, and attention UNet with and without input depth encoding apparent data. In the end, we have compared our DL results with traditional inversion and borewell data on apparent resistivity datasets collected for aquifer mapping in the hard rock terrain of the West Medinipur district of West Bengal, India. A detailed qualitative and quantitative evaluation reveals that our VED approach is the most effective for the inversion compared to other approaches considered.
Author	Singh, Anand Wilson, Bibin Sethi, Amit
Author_xml	– sequence: 1 givenname: Bibin surname: Wilson fullname: Wilson, Bibin organization: Department of Earth Sciences, Indian Institute of Technology Bombay, Maharashtra, India – sequence: 2 givenname: Anand orcidid: 0000-0003-4736-3514 surname: Singh fullname: Singh, Anand organization: Department of Earth Sciences, Indian Institute of Technology Bombay, Maharashtra, India – sequence: 3 givenname: Amit surname: Sethi fullname: Sethi, Amit organization: Department of Electrical Engineering, Indian Institute of Technology Bombay, Maharashtra, India
BookMark	eNp9kE1PAjEQhhuDiYD-AONlE8-LnXbbbY8EEUlQEyRe191uNxbXLbYFwr93-YgHD55m0rzPdObpoU5jG43QNeABAJZ3i8n8dUAwIQNKIGUCn6EuMCZizJOkg7oYJI-JkOQC9bxfYgwJg7SL3oerlcuNz-vIVtFce-OD2Ziwi6bNRjtvbBM92VLXPtqa8BGNbLOx9Tq07y3yljuTn_pxo9qci-_1oUbPOmyt-7xE51Vee311qn20eBgvRo_x7GUyHQ1nsSKShrhdRhJVgZZKlLxIeJUqTjEoIRLIQTFeQplTUVFeMJZiIoROMS6AyoJLTfvo9jh25ez3WvuQLe3atXv5jKQ0oYIDS9sUHFPKWe-drrKVM1-522WAs73HbO8x23vMTh5bJv3DKBMOR4dWXP0veXMkjdb69ycpKQAT9AfsyYLn
CODEN	IGRSD2
CitedBy_id	crossref_primary_10_1002_nsg_12332 crossref_primary_10_1109_TGRS_2025_3576680 crossref_primary_10_1016_j_seppur_2025_134115
Cites_doi	10.1088/0957-0233/17/9/006 10.1109/TGRS.2020.2969040 10.1016/j.earscirev.2014.04.002 10.1109/CVPR.2016.90 10.3997/2214-4609.201402682 10.1190/1.3273851 10.1515/acgeo-2015-0071 10.1093/gji/ggu001 10.1137/1.9780898719635 10.1190/geo2017-0040.1 10.1190/1.2348091 10.1190/1.1444302 10.3997/1873-0604.2016047 10.1137/1.9780898717921 10.1109/ICCSP.2017.8286426 10.1190/geo2018-0249.1 10.1109/TMI.2018.2833635 10.1111/j.1365-2478.1996.tb00162.x 10.1093/gji/ggab024 10.1190/1.3581356 10.1007/978-3-319-46475-6_43 10.1016/j.cageo.2011.08.029 10.1190/1.2402499 10.1093/gji/ggaa161 10.1016/j.jappgeo.2005.12.003 10.1016/j.pepi.2008.06.022 10.1109/LRA.2019.2891028
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M
DOI	10.1109/TGRS.2022.3217580
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Water Resources Abstracts Technology Research Database Environmental Sciences and Pollution Management ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Aerospace Database Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Water Resources Abstracts Environmental Sciences and Pollution Management
DatabaseTitleList	Aerospace Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Physics
EISSN	1558-0644
EndPage	1
ExternalDocumentID	10_1109_TGRS_2022_3217580 9931158
Genre	orig-research
GrantInformation_xml	– fundername: Indian Institute of Technology Bombay grantid: RD/0518-IRCCSH0-022 funderid: 10.13039/501100005808
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AASAJ AAWTH ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AETIX AFRAH AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IBMZZ ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 Y6R AAYXX CITATION 7UA 8FD AARMG ABAZT C1K F1W FR3 H8D H96 KR7 L.G L7M
ID	FETCH-LOGICAL-c293t-51792cf1e9c8d6b46f7c6301c8841a1c56d1da38f36b5570288e700b139b69e3
IEDL.DBID	RIE
ISICitedReferencesCount	8
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000880753700039&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0196-2892
IngestDate	Mon Jun 30 08:21:24 EDT 2025 Tue Nov 18 22:35:25 EST 2025 Sat Nov 29 02:50:26 EST 2025 Tue Nov 25 14:44:27 EST 2025
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c293t-51792cf1e9c8d6b46f7c6301c8841a1c56d1da38f36b5570288e700b139b69e3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-4736-3514
PQID	2734386157
PQPubID	85465
PageCount	1
ParticipantIDs	crossref_primary_10_1109_TGRS_2022_3217580 crossref_citationtrail_10_1109_TGRS_2022_3217580 ieee_primary_9931158 proquest_journals_2734386157
PublicationCentury	2000
PublicationDate	20220000 2022-00-00 20220101
PublicationDateYYYYMMDD	2022-01-01
PublicationDate_xml	– year: 2022 text: 20220000
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on geoscience and remote sensing
PublicationTitleAbbrev	TGRS
PublicationYear	2022
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref35 ref13 bank (ref33) 2004 ref34 ref37 ref15 ref36 ref14 ref30 ref11 choi (ref23) 2018 ref32 ref10 ref2 ref1 ref17 ref38 ref16 kingma (ref24) 2013 ref18 choromanska (ref28) 2015 wu (ref29) 2018 bhunia (ref43) 2012; 2 oktay (ref41) 2018 miyashita (ref22) 2016 ref26 ref20 pati (ref42) 2013 kawaguchi (ref27) 2016; 29 günther (ref25) 2004 rücker (ref12) 2010 ref8 ref7 ref9 ref4 ref3 li (ref31) 2019 ref6 ref5 li (ref21) 2019 ref40 tikhonov (ref39) 1977 krizhevsky (ref19) 2012; 25
References_xml	– ident: ref14 doi: 10.1088/0957-0233/17/9/006 – ident: ref17 doi: 10.1109/TGRS.2020.2969040 – start-page: 192 year: 2015 ident: ref28 article-title: The loss surfaces of multilayer networks publication-title: Artificial Intelligence and Statistics – ident: ref1 doi: 10.1016/j.earscirev.2014.04.002 – ident: ref36 doi: 10.1109/CVPR.2016.90 – ident: ref7 doi: 10.3997/2214-4609.201402682 – ident: ref11 doi: 10.1190/1.3273851 – ident: ref6 doi: 10.1515/acgeo-2015-0071 – ident: ref13 doi: 10.1093/gji/ggu001 – volume: 2 start-page: 41 year: 2012 ident: ref43 article-title: Assessment of groundwater potential zone in Paschim Medinipur district, West Bengal-A meso-scale study using GIS and remote sensing approach publication-title: Assessment – ident: ref32 doi: 10.1137/1.9780898719635 – ident: ref40 doi: 10.1190/geo2017-0040.1 – ident: ref34 doi: 10.1190/1.2348091 – volume: 25 start-page: 84 year: 2012 ident: ref19 article-title: ImageNet classification with deep convolutional neural networks publication-title: Proc Adv Neural Inf Process Syst – ident: ref9 doi: 10.1190/1.1444302 – year: 2018 ident: ref41 article-title: Attention U-Net: Learning where to look for the pancreas publication-title: arXiv 1804 03999 – year: 2004 ident: ref33 publication-title: PLTMG A Software Package for Solving Elliptic Partial Differential Equations User s Guide 6 0 – volume: 29 start-page: 1 year: 2016 ident: ref27 article-title: Deep learning without poor local minima publication-title: Proc Adv Neural Inf Process Syst – ident: ref16 doi: 10.3997/1873-0604.2016047 – ident: ref2 doi: 10.1137/1.9780898717921 – year: 2013 ident: ref42 article-title: Ground water year book of West Bengal and Andaman and Nicobar islands – year: 2016 ident: ref22 article-title: Convolutional neural networks using logarithmic data representation publication-title: arXiv 1603 01025 – ident: ref35 doi: 10.1109/ICCSP.2017.8286426 – ident: ref30 doi: 10.1190/geo2018-0249.1 – ident: ref20 doi: 10.1109/TMI.2018.2833635 – year: 2004 ident: ref25 article-title: Inversion methods and resolution analysis for the 2D/3D reconstruction of resistivity structures from DC measurements – year: 1977 ident: ref39 publication-title: Solutions of Ill-posed Problems – ident: ref5 doi: 10.1111/j.1365-2478.1996.tb00162.x – year: 2010 ident: ref12 article-title: Advanced electrical resistivity modelling and inversion using unstructured discretization – ident: ref18 doi: 10.1093/gji/ggab024 – year: 2013 ident: ref24 article-title: Auto-encoding variational Bayes publication-title: arXiv 1312 6114 – ident: ref4 doi: 10.1190/1.3581356 – ident: ref38 doi: 10.1007/978-3-319-46475-6_43 – ident: ref10 doi: 10.1016/j.cageo.2011.08.029 – ident: ref8 doi: 10.1190/1.2402499 – year: 2018 ident: ref23 article-title: PACT: Parameterized clipping activation for quantized neural networks publication-title: arXiv 1805 06085 – year: 2019 ident: ref31 article-title: Deep-learning inversion of seismic data publication-title: arXiv 1901 07733 – ident: ref15 doi: 10.1093/gji/ggaa161 – year: 2018 ident: ref29 article-title: InversionNet: A real-time and accurate full waveform inversion with CNNs and continuous CRFs publication-title: arXiv 1811 07875 – ident: ref26 doi: 10.1016/j.jappgeo.2005.12.003 – ident: ref3 doi: 10.1016/j.pepi.2008.06.022 – ident: ref37 doi: 10.1109/LRA.2019.2891028 – year: 2019 ident: ref21 article-title: Additive powers-of-two quantization: An efficient non-uniform discretization for neural networks publication-title: arXiv 1909 13144
SSID	ssj0014517
Score	2.4208796
Snippet	Recovering the actual subsurface electrical resistivity properties from the electrical resistivity tomography data is challenging because the inverse problem...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1
SubjectTerms	Algorithms Aquifers Coders Conductivity Conductivity Distribution Data models Deep learning Electrical resistivity Electrical Resistivity Tomography Encoders-Decoders Feature extraction Geophysical measurements Inverse Problem Inverse problems Machine learning Mathematical models Tomography
Title	Appraisal of Resistivity Inversion Models with Convolutional Variational Encoder-Decoder Network
URI	https://ieeexplore.ieee.org/document/9931158 https://www.proquest.com/docview/2734386157
Volume	60
WOSCitedRecordID	wos000880753700039&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-0644 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014517 issn: 0196-2892 databaseCode: RIE dateStart: 19800101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB7aoqAHH1WxvsjBkxi7j3STPUp9HaRILdLbms1OQZCtdKu_30w2LQVF8LR7yCzLfsnON5PMNwDnVAxpabTihdaCCx0InmupuZC9BHNNndOcuv6jHAzUeJw-NeByWQuDiO7wGV7RrdvLL6bmk1JlXetLLYFRTWhKKetareWOgeiFvjQ64TaIiPwOZhik3dH98NlGglF0FVsC3iMFyBUf5Jqq_PgTO_dyt_2_F9uBLU8j2XWN-y40sGzD5oq4YBvW3eFOU-3Bq6WaM_1WWYPphA2xonVNPSMYqWy4fBmjnmjvFaO0LOtPyy8_I63Ji42mfcaQ3ZZUAj_jN-iubFAfIt-H0d3tqP_AfWcFbqx7n3PS5YrMJMTUqCLJRTKRJrFL3SglQh2aXlKEhY7VJE5y0uiKlEIZBLmli3mSYnwArXJa4iGwvNDWNC0EFii0wDRFyxFQoBJ5LGTUgWDxqTPjVcep-cV75qKPIM0InYzQyTw6HbhYmnzUkht_Dd4jOJYDPRIdOFngmflFWWWk5BMrS-Hk0e9Wx7BBz64zLCfQms8-8RTWzNf8rZqdufn2DaKB0sk
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB7WF-rB1yquzxw8idntI23To-j6wHURXcRbTdNZEKQr29XfbyaNi6AIntpDhpZ-SeebSeYbgCMqhjQ0WvJCKcGF8gTPVaK4SKIYc0Wd06y6fi_p9-XTU3rXgJNpLQwi2sNn2KZbu5dfjPQ7pco6xpcaAiNnYC4SIvDraq3pnoGIfFccHXMTRgRuD9P30s7g8v7BxIJB0A4NBY9IA_KbF7JtVX78i62DuVj936utwYojkuy0Rn4dGlhuwPI3ecENWLDHO3XVhGdDNsfqpTIGoyG7x4pWNnWNYKSzYTNmjLqivVaMErPsbFR-uDlpTB5NPO1yhqxbUhH8mJ-jvbJ-fYx8EwYX3cHZFXe9Fbg2Dn7CSZkr0EMfUy2LOBfxMNGxWexaSuErX0dx4RcqlMMwzkmlK5ASE8_LDWHM4xTDLZgtRyVuA8sLZUzTQmCBQglMUzQsAQVKkYciCVrgfX3qTDvdcWp_8ZrZ-MNLM0InI3Qyh04Ljqcmb7Xoxl-DmwTHdKBDogV7X3hmbllWGWn5hNKQuGTnd6tDWLwa3Pay3nX_ZheW6Dl1vmUPZifjd9yHef0xeanGB3bufQLBCNYQ
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Appraisal+of+Resistivity+Inversion+Models+With+Convolutional+Variational+Encoder%E2%80%93Decoder+Network&rft.jtitle=IEEE+transactions+on+geoscience+and+remote+sensing&rft.au=Wilson%2C+Bibin&rft.au=Singh%2C+Anand&rft.au=Sethi%2C+Amit&rft.date=2022&rft.issn=0196-2892&rft.eissn=1558-0644&rft.volume=60&rft.spage=1&rft.epage=10&rft_id=info:doi/10.1109%2FTGRS.2022.3217580&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TGRS_2022_3217580
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0196-2892&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0196-2892&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0196-2892&client=summon