Seismic data reconstruction by wavelet channel attention network
LIU Pei1, WANG Changpeng1, DONG Anguo1, ZHANG Chunxia2, ZHANG Jiangshe2
1. School of Science, Chang'an University, Xi'an, Shaanxi 710064, China; 2. School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, Shaanxi 710049, China
Abstract：Missing traces reconstruction is a key step for seismic data processing. In recent years，various seismic data reconstruction methods based on deep learning theory have been proposed. However，normal convolution 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 network 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 produce more accurate reconstruction results than some representative deep learning methods.
RONEN J. Wave-equation trace interpolation[J]. Geophysics,1987, 52(7): 973-984.
[2]
FOMEL S. Seismic reflection data interpolation with differential offset and shot continuation[J]. Geophysics,2003,68(2):733-744.
[3]
ANTONINI M,BARLAUD M,MATHIEU P,et al. Image coding using wavelet transform[J].IEEE Transactions on Image Processing,1992,1(2):205-220.
[4]
高建军,陈小宏,李景叶. 基于非均匀 Fourier 变换的地震数据重建方法研究[J]. 地球物理学进展,2009,24(5):1741-1747.GAO Jianjun,CHEN Xiaohong,LI Jingye. Study on reconstruction of seismic data based on nonuniform Fourier transform[J]. Process in Geophysics,2009,24(5):1741-1747.
[5]
刘一,刘财,刘洋,等. 复杂地震波场的自适应流预测插值方法[J]. 吉林大学学报(地球科学版),2018,48(4):1260-1267.LIU Yi,LIU Cai,LIU Yang,et al. Adaptive streaming prediction interpolation for complex seismic wavefield[J]. Journal of Jilin University (Earth Science Edition),2018,48(4):1260-1267.
[6]
MA J W. Three-dimensional irregular seismic data reconstruction via low-rank matrix completion[J]. Geophysics,2013,78(5):V181-V192.
[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 Journal International,2016,206(3):1695-1717.
[8]
DAS V,POLLACK A,WOLLNER U,et al. Convolutional neural network for seismic impedance inversion[J]. Geophysics,2019,84(6):R869-R880.
[9]
郭萌,张会星,刘明珠,等. 基于双重Bregman迭代的地震数据重构与去噪[J]. 石油物探,2020,59(5): 804-814.GUO Meng,ZHANG Huixing,LIU Mingzhu,et al. Seismic data reconstruction and denoising based on dual Bregman iteration[J]. Geophysical Prospecting for Petroleum,2020,59(5):804-814.
[10]
张岩,李新月, 王斌,等. 基于联合深度学习的地震数据随机噪声压制[J]. 石油地球物理勘探,2021,56(1):9-25,56.ZHANG Yan,LI Xinyue,WANG Bin,et al. Random noise suppression of seismic data based on joint deep learning[J]. Oil Geophysical Prospecting,2021,56(1):9-25,56.
[11]
SONG A Q,WANG C P,ZHANG C X,et al. Seismic data reconstruction via recurrent residual multiscale inference[J]. IEEE Geoscience and Remote Sensing Letters,2022,19:1-5.
[12]
张岩,李杰,王斌,等. 基于联合小波域深度学习的地震数据规则化方法[J]. 石油地球物理勘探,2022,57(4):777-788.ZHANG Yan,LI Jie,WANG Bin,et al. Seismic data regularization based on deep learning combining wavelet domain[J]. Oil Geophysical Prospecting,2022,57(4):777-788.
[13]
贾永娜,吴杰,王国伟,等. 基于Gabor纹理学习的地震数据重建算法[J]. 石油地球物理勘探,2023,58(3):617-625.JIA Yongna,WU Jie,WANG Guowei,et al. A texture feature learning method based on Gabor transform for seismic data interpolation[J]. Oil Geophysical Prospecting,2023,58(3):617-625.
[14]
MANDELLI S,BORRA F,LIPARI V,et al. Seismic data interpolation through convolutional autoencoder[C]. SEG Technical Program Expanded Abstracts,2018,37:4101-4105.
[15]
OLIVEIRA D A B,FERREIRA R S,SILVA R,et al. Interpolating seismic data with conditional generative adversarial networks[J]. IEEE Geoscience and Remote Sensing Letters,2018,15(12):1952-1956.
[16]
CHAI X T,GU H M,LI F,et al. Deep learning for irregularly and regularly missing data reconstruction[J]. Scientific Reports,2020,10(1):1-18.
[17]
PAN S L,CHEN K,CHEN J Y,et al. A partial convolution-based deep-learning network for seismic data regularization[J]. Computers & Geosciences,2020,145:104609.
[18]
FANG W Q,FU L H,ZHANG M,et al. Seismic data interpolation based on U-net with texture loss[J]. Geophysics,2021,86(1):V41-V54.
[19]
LI X Z,WU B Y,ZHU X,et al. Consecutively missing seismic data interpolation based on coordinate attention U-net[J]. IEEE Geoscience and Remote Sensing Letters,2022,19: 1-5.
[20]
LIU N H,WU L K,WANG J L,et al. Seismic data reconstruction via wavelet-based residual deep learning[J]. IEEE Transactions on Geoscience and Remote Sensing,2022,60: 1-13.
[21]
LIU P J,ZHANG H Z,ZHANG K,et al. Multi-level wavelet-CNN for image restoration[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops,2018,773-782.
[22]
WANG T W,SUN W J,QI H R,et al. Aerial image super resolution via wavelet multiscale convolutional neural networks[J]. IEEE Geoscience and Remote Sensing Letters,2018,15(5):769-773.
[23]
WANG Q L,WU B G,ZHU P F,et al. ECA-Net:Efficient channel attention for deep convolutional neural networks[C]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition,2020,11531-11539.
