Seismic data reconstruction by wavelet channel attention network

被引：0

作者：

Liu P. ^{[1
]}

Wang C. ^{[1
]}

Dong A. ^{[1
]}

Zhang C. ^{[2
]}

Zhang J. ^{[2
]}

机构：

[1] School of Science, Chang’an University, Shaanxi, Xi’an

[2] School of Mathematics and Statistics, Xi’an Jiaotong University, Shaanxi, Xi’an

来源：

Shiyou Diqiu Wuli Kantan/Oil Geophysical Prospecting | 2024年 / 59卷 / 01期

关键词：

deep learning; efficient chan‑ nel attention; Haar wavelet transform; random missing; seismic data reconstruction;

D O I：

10.13810/j.cnki.issn.1000-7210.2024.01.004

中图分类号：

学科分类号：

摘要：

Missing traces reconstruction is a key step for seismic data processing. In recent years，various seis‑ mic data reconstruction methods based on deep learning theory have been proposed. However，normal convolu‑ tion operation can only capture local dependencies and make insufficient use of global information. Moreover，the operation of pooling also results in the loss of feature map information，which destroys detailed features of seismic reflections. Therefore，a seismic data reconstruction method based on wavelet channel attention net‑ work is proposed. The Haar wavelet transform effectively extracts multi ‑ scale characteristics and avoids the loss of information during the up‑sampling process. Efficient channel attention modules are introduced to model the correlations between feature maps of different channels，which can make full use of the global information. Experimental results on synthetic and field datasets illustrate that the wavelet channel attention network can pro‑ duce more accurate reconstruction results than some representative deep learning methods. © 2024 Editorial office of Oil Geophysical Prospecting. All rights reserved.

引用

页码：31 / 37

页数：6

共 23 条

[1] RONEN J., Wave‑equation trace interpolation[J], Geo‑ physics, 52, 7, (1987)
[2] FOMEL S., Seismic reflection data interpolation with differential offset and shot continuation[J], Geophysics, 68, 2, (2003)
[3] ANTONINI M, BARLAUD M, MATHIEU P, Et al., Image coding using wavelet transform[J], IEEE Transactions on Image Processing, 1, 2, (1992)
[4] GAO Jianjun, CHEN Xiaohong, LI Jingye, Study on reconstruction of seismic data based on nonuniform Fourier transform, Process in Geophysics, 24, 5, (2009)
[5] LIU Yi, LIU Cai, LIU Yang, Et al., Adaptive streaming prediction interpolation for complex seismic wavefield, Journal of Jilin University (Earth Sci‑ ence Edition), 48, 4, (2018)
[6] MA J W., Three‑dimensional irregular seismic data re‑ construction via low ‑ rank matrix completion[J], Geo‑ physics, 78, 5, (2013)
[7] CHEN Y K, ZHANG D, JIN Z Y, Et al., Simultaneous denoising and reconstruction of 5 ‑ D seismic data via damped rank ‑ reduction method[J], Geophysical Jour‑ nal International, 206, 3, (2016)
[8] DAS V, POLLACK A, WOLLNER U, Et al., Convo‑ lutional neural network for seismic impedance inversion [J], Geophysics, 84, 6, (2019)
[9] GUO Meng, ZHANG Huixing, LIU Mingzhu, Et al., Seismic data reconstruction and denoising based on dual Bregman iteration[J], Geophysical Prospecting for Petroleum, 59, 5, (2020)
[10] ZHANG Yan, LI Xinyue, WANG Bin, Et al., Random noise suppression of seismic data based on joint deep learning, Oil Geophysical Prospecting, 56, 1, (2021)

← 1 2 3 →