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

Cited 0 time in WEB OF SCIENCE Cited 0 time in Scopus
Title
Coarse-refine Network with Upsampling Techniques and Fourier Loss for the Reconstruction of Missing Seismic Data
Author(s)
Park, Hanjoon; Lee, Jun-Woo; Hwang, Jongha; Min, Dong-Joo
KIOST Author(s)
Hwang, Jongha(황종하)
Alternative Author(s)
황종하
Publication Year
2022-07
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
ISSN
0196-2892
URI
https://sciwatch.kiost.ac.kr/handle/2020.kiost/43103
DOI
10.1109/TGRS.2022.3190292
Bibliographic Citation
IEEE Transactions on Geoscience and Remote Sensing, v.60, pp.1 - 1, 2022
Publisher
Institute of Electrical and Electronics Engineers
Keywords
Coarse-refine network; Convergence; Convolution; Decoding; Fourier loss; Fourier transform; Image reconstruction; Interpolation; Neural networks; Seismic data interpolation; Training; UNet
Type
Article
Language
English
Document Type
Article
Publisher
Institute of Electrical and Electronics Engineers
Files in This Item:
There are no files associated with this item.

qrcode

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

Browse