File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)

Conference Paper: Joint 2D inversion of AMT and seismic traveltime data with deep learning constraint

TitleJoint 2D inversion of AMT and seismic traveltime data with deep learning constraint
Authors
Keywordsinversion
magnetotelluric
traveltime
machine learning
Issue Date2020
PublisherSociety of Exploration Geophysicists. The Journal's web site is located at http://library.seg.org/series/segeab
Citation
2020 Society of Exploration Geophysicists (SEG) International Exposition and 90th Annual Meeting, Online Conference, Houston, USA, 11-16 October 2020. Abstract in SEG Technical Program Expanded Abstracts 2020, p. 1695-1699 How to Cite?
AbstractWe apply deep learning techniques to assist the joint inversion of audio-magnetotelluric (AMT) and seismic travel time data. Based on the assumption that the resistivity-velocity relationship is known a priori, deep neural networks are used to learn the nonlinear maps between these two parameters. In this manner, the correlation between resistivity and velocity in both structure and value can be implicitly established through the neural network. During the inversion, we alternatively update resistivity and velocity using the Gauss-Newton method. Moreover, both resistivity and velocity are updated based on the reference model mapped from the other parameter by deep residual convolutional neural networks (DRCNNs). Numerical example shows that this joint inversion scheme can achieve more accurate inversion and converges faster than separate inversion.
DescriptionPoster Sessions - MLDA P4 Inversion 2
Persistent Identifierhttp://hdl.handle.net/10722/301977
ISSN

 

DC FieldValueLanguage
dc.contributor.authorGuo, R-
dc.contributor.authorLi, M-
dc.contributor.authorYang, F-
dc.contributor.authorYao, H-
dc.contributor.authorJiang, L-
dc.contributor.authorNg, KP-
dc.contributor.authorAbubakar, A-
dc.date.accessioned2021-08-21T03:29:45Z-
dc.date.available2021-08-21T03:29:45Z-
dc.date.issued2020-
dc.identifier.citation2020 Society of Exploration Geophysicists (SEG) International Exposition and 90th Annual Meeting, Online Conference, Houston, USA, 11-16 October 2020. Abstract in SEG Technical Program Expanded Abstracts 2020, p. 1695-1699-
dc.identifier.issn1949-4645-
dc.identifier.urihttp://hdl.handle.net/10722/301977-
dc.descriptionPoster Sessions - MLDA P4 Inversion 2-
dc.description.abstractWe apply deep learning techniques to assist the joint inversion of audio-magnetotelluric (AMT) and seismic travel time data. Based on the assumption that the resistivity-velocity relationship is known a priori, deep neural networks are used to learn the nonlinear maps between these two parameters. In this manner, the correlation between resistivity and velocity in both structure and value can be implicitly established through the neural network. During the inversion, we alternatively update resistivity and velocity using the Gauss-Newton method. Moreover, both resistivity and velocity are updated based on the reference model mapped from the other parameter by deep residual convolutional neural networks (DRCNNs). Numerical example shows that this joint inversion scheme can achieve more accurate inversion and converges faster than separate inversion.-
dc.languageeng-
dc.publisherSociety of Exploration Geophysicists. The Journal's web site is located at http://library.seg.org/series/segeab-
dc.relation.ispartofSEG Technical Program Expanded Abstracts (Online)-
dc.subjectinversion-
dc.subjectmagnetotelluric-
dc.subjecttraveltime-
dc.subjectmachine learning-
dc.titleJoint 2D inversion of AMT and seismic traveltime data with deep learning constraint-
dc.typeConference_Paper-
dc.identifier.emailYao, H: yaohm@hku.hk-
dc.identifier.emailNg, KP: michael.ng@hku.hk-
dc.identifier.authorityJiang, L=rp01338-
dc.identifier.authorityNg, KP=rp02578-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1190/segam2020-3426298.1-
dc.identifier.hkuros324399-
dc.identifier.spage1695-
dc.identifier.epage1699-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats