A sparse representation method for seismic data: adaptive multilayered dictionary learning (AMDL)
YONG Hao1,2, HAN Duo1,2, ZHANG Junjie1,2, WANG Junqiu1,2
1. College of Instrumentation and Electrical Engineering, Jilin University, Changchun, Jilin 130026 China; 2. Key Laboratory of Geophysical Exploration Equipment, Ministry of Education, Changchun, Jilin 130000, China
Abstract:The accuracy of seismic data reconstruction by compressed sensing (CS) largely depends on the performance of the dictionary used for sparse representation. The sparsity level of each training sample in the K-singular value decomposition (K-SVD) is fixed, which may lead to under-fitting or over-fitting of the original sample. Moreover, it only uses the features of the original samples as the training dictionary and cannot utilize the implicit features generated in the dictionary learning process, which affects the reconstruction accuracy. In this paper, we adopt the adaptive multilayered dictionary learning (AMDL) method for the sparse representation of seismic data to improve the K-SVD method. It not only makes full use of the features at different levels in the dictionary learning process but also adaptively determines the number of atoms chosen for each layer. The experimental results show that the method can provide a more accurate sparse representation for CS-based reconstruction of seismic data than the K-SVD method.
DONOHO D L. Compressed sensing[J]. IEEE Transactions on Information Theory, 2006, 52(4):1289-1306.
[2]
CANDES E J, WAKIN M B. An introduction to compressive sampling[J]. IEEE Signal Processing Ma-gazine, 2008, 25(2):21-30.
[3]
HERRMANN F J. Randomized sampling and sparsity:getting more information from fewer samples[J]. Geophysics, 2010, 75(6):WB173-WB187.
[4]
HERRMANN F J, FRIEDLANDER M P, YILMAZ O. Fighting the curse of dimensionality:compressive sensing in exploration seismology[J]. IEEE Signal Processing Magazine, 2012, 29(3):88-100.
[5]
黄小刚. 海上压缩感知地震仿真采集设计与处理[J]. 石油地球物理勘探, 2020, 55(2):248-256.HUANG Xiaogang. A simulation of acquisition design and data processing for offshore compressive sensing seismic[J]. Oil Geophysical Prospecting, 2020, 55(2):248-256.
[6]
宋维琪, 吴彩端. 利用压缩感知方法提高地震资料分辨率[J]. 石油地球物理勘探, 2017, 52(2):214-219.SONG Weiqi, WU Caiduan. Seismic data resolution improvement based on compressed sensing[J]. Oil Geophysical Prospecting, 2017, 52(2):214-219.
[7]
MA J W, PLONKA G, CHAURIS H. A new sparse representation of seismic data using adaptive easy-path wavelet transform[J]. IEEE Geoscience and Remote Sensing Letters, 2010, 7(3):540-544.
[8]
陈祖斌, 王丽芝, 宋杨, 等. 基于压缩感知的小波域地震数据实时压缩与高精度重构[J]. 石油地球物理勘探, 2018, 53(4):674-681, 693.CHEN Zubin, WANG Lizhi, SONG Yang, et al. Seismic data real-time compression and high-precision reconstruction in the wavelet domain based on the compressed sensing[J]. Oil Geophysical Prospecting, 2018, 53(4):674-681, 693.
[9]
TIAN X, ABDI A, LIU E T, et al. Memory-assisted seismic signal compression based on dictionary lear-ning and sparse coding[C]//2017 IEEE Global Conference on Signal and Information Processing (Global SIP), 2017:358-362.
[10]
赵子越, 李振春, 张敏. 利用压缩感知技术的离散正交S变换地震数据重建[J]. 石油地球物理勘探, 2020, 55(1):29-35.ZHAO Ziyue, LI Zhenchun, ZHANG Min. Seismic data Reconstruction using discrete orthonormal S-Transform based on compressive sensing[J]. Oil Geo-physical Prospecting, 2020, 55(1):29-35.
[11]
AHARON M, ELAD M, BRUCKSTEIN A. K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation[J]. IEEE Transactions on Signal Processing, 2006, 54(11):4311-4322.
[12]
LIU Z X, WAN W G. Image inpainting algorithm based on KSVD and improved CDD[C]. 2018 International Conference on Audio, Language and Image Processing (ICALIP), 2018:413-417.
[13]
SUN H M, JIA R S, ZHANG X L, et al. Reconstruction of missing seismic traces based on sparse dictionary learning and the optimization of measurement matrices[J]. Journal of Petroleum Science and Engi-neering, 2019, 175:719-727.
[14]
YU C X, ZHAO J T, WANG Y F. Seismic detection method for small-scale discontinuities based on dictionary learning and sparse representation[J]. Journal of Applied Geophysics, 2017, 137:55-62.
[15]
SMITH L N, ELAD M. Improving dictionary lear-ning:multiple dictionary updates and coefficient reuse[J]. IEEE Signal Processing Letters, 2013, 20(1):79-82.
[16]
NAZZAL M, YEGANLI F, OZKARAMANLI H. A strategy for residual component-based multiple structured dictionary learning[J]. IEEE Signal Processing Letters, 2015, 22(11):2059-2063.
[17]
CHEN B, POLATKAN G, SAPIRO G, et al. Deep learning with hierarchical convolutional factor analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8):1887-1901.
[18]
TARIYAL S, MAJUMDAR A, SINGH R, et al. Deep dictionary learning[J]. IEEE Access, 2016, 4:10096-10109.
[19]
FU J, YUAN H K, ZHAO R Q, et al. Adaptive multilayered dictionary learning for compressive-sensing-based image reconstruction[J]. IEEE Access, 2019, 7:105922-105936.
[20]
TROPP J A, GILBERT A C. Signal recovery from random measurements via orthogonal matching pursuit[J]. IEEE Transactions on Information Theory, 2007, 53(12):4655-4666.
[21]
TROPP J A. Greed is good:algorithmic results for sparse approximation[J]. IEEE Transactions on Information Theory, 2004, 50(10):2231-2242.
[22]
GAO Z, XUAN H Z, ZHANG H, et al. Adaptive fusion and category-level dictionary learning model for multiview human action recognition[J]. IEEE Internet of Things Journal, 2019, 6(6):9280-9293.
[23]
姚振岸, 孙成禹, 李红星, 等. 基于基追踪的时变子波提取与地震反射率反演[J]. 石油地球物理勘探, 2019, 54(1):137-144.YAO Zhen'an, SUN Chengyu, LI Hongxing, et al. Time-variant wavelet extraction and seismic reflectivity inversion based on basis pursuit[J]. Oil Geophysical Prospecting, 2019, 54(1):137-144.
[24]
CHEN S S, DONOHO D L, SAUNDERS M A. Atomic decomposition by basis pursuit[J]. SIAM Review, 2001, 43(1):129-159.
[25]
RAUHUT H. Stability results for random sampling of sparse trigonometric polynomials[J]. IEEE Transactions on Information Theory, 2008, 54(12):5661-5670.