Coarse-refine Network with Upsampling Techniques and Fourier Loss for the Reconstruction of Missing Seismic Data SCIE SCOPUS

DC Field Value Language Park, Hanjoon - Lee, Jun-Woo - Hwang, Jongha - Min, Dong-Joo - 2022-07-25T04:30:00Z - 2022-07-25T04:30:00Z - 2022-07-25 - 2022-07 -
dc.identifier.issn 0196-2892 -
dc.identifier.uri -
dc.description.abstract Seismic data are often irregularly or insufficiently sampled along the spatial direction due to malfunctioning of receivers and limited survey budgets. Recently, machine learning techniques have begun to be used to effectively reconstruct missing traces and obtain densely sampled seismic gathers. One of the most widely used machine learning techniques for seismic trace interpolation is UNet with the mean-squared error (MSE). However, seismic trace interpolation with the UNet architecture suffers from aliasing, and the MSE used as a loss function causes an oversmoothing problem. To mitigate those problems in seismic trace interpolation, we propose a new strategy of using coarse-refine UNet (CFunet) and the Fourier loss. CFunet consists of two UNets and an upsampling process between them. The upsampling process is done by padding zeroes in the Fourier domain. We design the new loss function by combining the MSE and the Fourier loss. Unlike the MSE, the Fourier loss is not a pixelwise loss but plays a role in capturing relations between pixels. Synthetic and field data experiments show that the proposed method reduces aliased features and precisely reconstructs missing traces while accelerating the convergence of the network. By applying our strategy to realistic cases, we show that our strategy can be applied to obtain more densely sampled data from acquired data. IEEE -
dc.description.uri 1 -
dc.language English -
dc.publisher Institute of Electrical and Electronics Engineers -
dc.title Coarse-refine Network with Upsampling Techniques and Fourier Loss for the Reconstruction of Missing Seismic Data -
dc.type Article -
dc.citation.endPage 1 -
dc.citation.startPage 1 -
dc.citation.title IEEE Transactions on Geoscience and Remote Sensing -
dc.citation.volume 60 -
dc.contributor.alternativeName 황종하 -
dc.identifier.bibliographicCitation IEEE Transactions on Geoscience and Remote Sensing, v.60, pp.1 - 1 -
dc.identifier.doi 10.1109/TGRS.2022.3190292 -
dc.identifier.scopusid 2-s2.0-85134201571 -
dc.identifier.wosid 000829062600015 -
dc.type.docType Article -
dc.description.journalClass 1 -
dc.description.isOpenAccess N -
dc.subject.keywordAuthor Coarse-refine network -
dc.subject.keywordAuthor Convergence -
dc.subject.keywordAuthor Convolution -
dc.subject.keywordAuthor Decoding -
dc.subject.keywordAuthor Fourier loss -
dc.subject.keywordAuthor Fourier transform -
dc.subject.keywordAuthor Image reconstruction -
dc.subject.keywordAuthor Interpolation -
dc.subject.keywordAuthor Neural networks -
dc.subject.keywordAuthor Seismic data interpolation -
dc.subject.keywordAuthor Training -
dc.subject.keywordAuthor UNet -
dc.relation.journalWebOfScienceCategory Geochemistry & Geophysics -
dc.relation.journalWebOfScienceCategory Engineering, Electrical & Electronic -
dc.relation.journalWebOfScienceCategory Remote Sensing -
dc.relation.journalWebOfScienceCategory Imaging Science & Photographic Technology -
dc.description.journalRegisteredClass scie -
dc.description.journalRegisteredClass scopus -
dc.relation.journalResearchArea Geochemistry & Geophysics -
dc.relation.journalResearchArea Engineering -
dc.relation.journalResearchArea Remote Sensing -
dc.relation.journalResearchArea Imaging Science & Photographic Technology -
Appears in Collections:
Marine Environmental & Climate Research Division > Marine Active Fault Research Unit > 1. Journal Articles
Files in This Item:
There are no files associated with this item.


Items in ScienceWatch@KIOST are protected by copyright, with all rights reserved, unless otherwise indicated.