Efficient seismic sparse decomposition based on multiple kernel-based models
Fu Lihua1, Li Hongwei1, Liu Zhihui1, Zhao Haolan2,3
1. School of Mathematics and Physics, China University of Geosciences (Wuhan), Wuhan, Hubei 430074, China;
2. College of Physical Science and Technology, Central China Normal University, Wuhan, Hubei 430079, China;
3. R&D Department/Network Business Unit, Fiberhome Telecommunication Technologies Ltd., Wuhan, Hubei 430073, China
Abstract:To enhance the efficiency and sparsity of seismic signal decomposition, multiple kernels are used for the adaptive sparse decomposition of seismic signals. At first, the global k-means clustering algorithm is utilized to generate the preselected behavioral parameters in the dictionary. Then the signal is reconstructed with orthogonal least squares method. The experiments both on synthetic and real data were conducted to evaluate the performance. The results show that multiple kernel-based models greatly improve the sparsity with the similar accuracy.
Van Groenestijn G J A,Verschuur D J.Estimation of primaries by sparse inversion from passive seismic data.Geophysics,2010,75(4):61-69.
[2]
Ma J,Plonka G,Chauris H.A new sparse representa-tion of seismic data using adaptive easy-path wavelet transform. IEEE Geoscience and Remote Letters,2010,7(3):540-544.
[3]
Vapnik V.The Nature of Statistical Learning Theo-ry.New York: Springer-Verlag,1995.
[4]
Donoho D.Compressed sensing.IEEE Trans Inform Theory,2006,52(4):1289-1306.
[5]
Yu S,Khwaja S,Ma J.Compressed sensing of com-plex-valued data.Signal Processing,2012, 92(2):357-362.
[6]
刘婧玉.基于稀疏变换的地震数据压缩编码[硕士学位论文].四川成都:西南交通大学, 2010.
Liu Jingyu.Seismic Data Compression Based on Sparse Decomposition[M].Sichuan:Southwest Jiaotong University,2010.
Chen Wenchao,Wang Wei,Gao Jinghuai et al.Sparsity optimized separation of Ground-roll noise based on morphological diversity of seismic waveform components.Chinese Jounal of Geophsics,2013,56(8):2771-2782.
[8]
Rodriguez I V,Sacchi M and Gu Y J.A compressive sensing framework for seismic source parameter estimation.Geophysical Journal International,2012,191(3):1226-1236.
[9]
Mallat S,Zhang Z.Matching pursuits with time-fre-quency dictionaries.IEEE Transactions on Signal Processing,1993,41(12): 3397-3415.
[10]
Liu J L,Marfurt J K.Matching pursuit decomposition using Morlet wavelet.SEG Technical Program Expanded Abstracts,2005,24:786-789.
[11]
Wang Y H.Seismic time frequency spectral decomposition by matching pursuit.Geophysics, 2007,72(1):13-20.
Zhang Fanchang,Li Chuanhui.Orthogonal time-frequency atom based fast matching pursuit for seismic signal.Chinese Journal of Geophysics, 2012, 55(1):277-283.
[16]
Shan H,Ma J,Yang H.Comparison of wavelets, contourlets and curvelets in seismic denosing. Journal of Applied Geophysics,2009,69(2):103-115.
[17]
Fu L,Li H,Zhang M.Sparse RBF networks with multi-kernels. Neural Processing Letters,2010,32(3):235-247.
[18]
Bardainne T,Gaillot P,Dubos-Sallee N.Characterization of seismic waveforms and classification seismic event using chirplet atomic decomposition-Example for the Lacq gas field (Western Pyrenees, France).Geophysical Journal International,2006,166(2):699-718.
[19]
Lozano J A,Pena J M,Larranaga P.An empirical comparison of four initialization methods for the k-means algorithm.Pattern Recognition Letters,1999,20:1027-1040.