AccScience Publishing / JSE / Article
Submit to JSE
Cite this article
5
Views
Journal Browser
Volume | Year
Issue
Search
Forthcoming Issue
Current Issue
View All
News and Announcements
View All
ARTICLE

Sparse dictionary learning for seismic noise attenuation using a fast orthogonal matching pursuit algorithm

YATONG ZHOU1 ,  SHUHUA LI1 ,  JIANYONG XIE2 ,  DONG ZHANG2 ,  YANGKANG CHEN3
Show Less
1 School of Electronic and Information Engineering, Hebei University of Technology, Xiping Road 5340, Beichen District, Tianjin 300401, P.R. China. zyt_htu@126.com,
2 State Key Laboratory of Petroleum Resources and Prospecting University of Petroleum-Beijing, Fuxue Road 18, Beijing 102249, P.R. China. xjyshl@sina.com; zhangdongconan@163.com,
3 Bureau of Economic Geology, John A. and Katherine G. Jackson School of Geosciences, The University of Texas at Austin, University Station, Box X, Austin, TX 78713-8924, U.S.A. ykchen@utexas.edu,
JSE 2017, 26(5), 433–454;
Submitted: 9 June 2025 | Revised: 9 June 2025 | Accepted: 9 June 2025 | Published: 9 June 2025
© 2025 by the Authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC-by the license) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Download PDF
Cite
XML
Abstract

Zhou, Y., Li, S., Xie, J., Zhang, D. and Chen, Y., 2017. Sparse dictionary learning for seismic noise attenuation using a fast orthogonal matching pursuit algorithm. Journal of Seismic Exploration, 26: 433-454. Attenuation of random noise is a long-standing problem in seismic data processing. One of the most widely used approaches is based on sparse transforms. In the geophysics community, most of the currently used sparse transforms have fixed bases, which we call analytical transforms. In this paper, we seek a different type of sparse transform, with variant bases, to attenuate random noise. We call this type of transform dictionary learning-based (DLB) sparse transforms, because it can adaptively train a sparse dictionary from the observed data to adapt to different seismic data. To increase the efficiency of sparse dictionary learning, we propose to apply a fast orthogonal matching pursuit (OMP) algorithm for sparse coding. We use both synthetic and field data examples to show the superior performance of the dictionary learning-based transform over fixed-basis transforms, and much improved efficiency in sparse coding associated with the fast OMP algorithm, which is one of the two steps in the DLB transform.

Keywords
sparse dictionary learning
denoising
fast OMP algorithm
References
  1. Aharon, M., Elad, M. and Bruckstein, A.M., 2006. The K-SVD: An algorithm for designing of
  2. ever-complete dictionaries for sparse representation. IEEE Transact. Sign. Process., 54:
  3. 4311-4322.
  4. Bekara, M. and van der Baan, M., 2007. Local singular value decomposition for signal enhancement
  5. of seismic data. Geophysics, 72: V59-V65.
  6. Canales, L., 1984. Random noise reduction. Expanded Abstr., 54th Ann. Internat. SEG Mtg.,
  7. Atlanta: 525-527.
  8. Chen, Y., 2015a. Deblending using a space-varying median filter. Explor. Geophys., 46: 332-341.
  9. Chen, Y., 2015b. Iterative deblending with multiple constraints based on shaping regularization.
  10. IEEE Geosci. Remote Sens. Lett., 12: 2247-2251.
  11. Chen, Y., 2016. Dip-separated structural filtering using seislet thresholding and adaptive empirical
  12. mode decomposition based dip filter. Geophys. J. Internat., 206: 457-469.
  13. 452 ZHOU, LI, XIE, ZHANG & CHEN
  14. Chen, Y., 2017. Fast dictionary learning for noise attenuation of multidimensional seismic data.
  15. Geophys. J. Internat., 209: 21-31.
  16. Chen, Y. and Fomel, S., 2015a. EMD-seislet transform. Expanded Abstr., 85th Ann. Internat. SEG
  17. Mtg., New Orleans: 4775-4778.
  18. Chen, Y. and Fomel, S., 2015b. Random noise attenuation using local signal-and-noise
  19. orthogonalization. Geophysics, 80: WD1-WD9.
  20. Chen, Y., Fomel, S. and Hu, J., 2014a. Iterative deblending of simultaneous-source seismic data
  21. using seislet-domain shaping regularization. Geophysics, 79: V179-V189.
  22. Chen, Y. and Jin, Z., 2015. Simultaneously removing noise and increasing resolution of seismic data
  23. using waveform shaping. IEEE Geosci. Remote Sens. Lett., 13: 102-104.
  24. Chen, Y., Jin, Z., Gan, S., Yang, W., Xiang, K., Bai, M. and Huang, W., 2015. Iterative
  25. deblending using shaping regularization with a combined PNMO-MF-FK coherency filter.
  26. J. Appl. Geophys., 122: 18-27.
  27. Chen, Y. and Ma, J., 2014. Random noise attenuation by f-x empirical mode decomposition
  28. predictive filtering. Geophysics, 79: V81-V91.
  29. Chen, Y., Ma, J. and Fomel, S., 2016a. Double-sparsity dictionary for seismic noise attenuation.
  30. Geophysics, 81: V17-V30.
  31. Chen, Y., Zhang, D., Huang, W. and Chen, W., 2016b. An open-source matlab code package for
  32. improved rank-reduction 3D seismic data denoising and reconstruction. Comput. Geosci.,
  33. 95: 59-66.
  34. Chen, Y., Zhang, D., Jin, Z., Chen, X., Zu, S., Huang, W. and Gan, S., 2016c. Simultaneous
  35. denoising and reconstruction of 5D seismic data via damped rank-reduction method.
  36. Geophys. J. Internat., 206: 1695-1717.
  37. Chen, Y., Zhou, C., Yuan, J. and Jin, Z., 2014. Application of empirical mode decomposition to
  38. random noise attenuation of seismic data. J. Seismic Explor., 23: 481-495.
  39. Duijndam, A.J., Schonewille, M.A. and Hindriks, C.O.H., 1999. Reconstruction of band-limited
  40. signals, irregularly sampled along one spatial direction. Geophysics, 64: 524-538.
  41. Fomel, S. and Liu, Y., 2010. Seislet transform and seislet frame. Geophysics, 75: V25-V38.
  42. Gan, S., Chen, Y., Zu, S., Qu, S. and Zhong, W., 2015a. Structure-oriented singular value
  43. decomposition for random noise attenuation of seismic data: J. Geophys. Engineer., 12: 262-
  45. Gan, S., Wang, S., Chen, Y., Zhang, Y. and Jin, Z., 2015b. Dealiased seismic data interpolation
  46. using seislet transform with low-frequency constraint. IEEE Geosci. Remote Sens. Lett., 12:
  47. 2150-2154.
  48. Gan, S., Chen, Y., Wang, S., Chen, X., Huang, W. and Chen, H., 2016a. Compressive sensing
  49. for seismic data reconstruction using a fast projection onto convex sets algorithm based on
  50. the seislet transform. J. Appl. Geophys., 130: 194-208.
  51. Gan, S., Wang, S., Chen, Y., Chen, J., Zhong, W. and Zhang, C., 2016b. Improved random noise
  52. attenuation using f-x empirical mode decomposition and local similarity. Appl. Geophys. ,
  53. 13: 127-134.
  54. Gan, S., Wang, S., Chen, Y. and Chen, X., 2016c. Simultaneous-source separation using iterative
  55. seislet-frame thresholding. IEEE Geosci. Remote Sens. Lett., 13: 197-201.
  56. Gan, S., Wang, S., Chen, Y., Chen, X. and Xiang, K., 2016d. Separation of simultaneous sources
  57. using a structural-oriented median filter in the flattened dimension. Comput. Geosci., 86:
  58. 46-54.
  59. Gan, S., Wang, S., Chen, Y., Qu, S. and Zu, S., 2016e., Velocity analysis of simultaneous-source
  60. data using high-resolution semblance-coping with the strong noise. Geophys. J. Internat.,
  61. 204: 768-779.
  62. Hennenfent, G. and Herrmann, F., 2006. Seismic denoising with nonunformly sampled curvelets.
  63. Comput. Sci. Engineer., 8: 16-25.
  64. Huang, N.E., Shen, Z., Long, S.R., Wu, M.C., Shih, H.H., Zheng, Q., Yen, N.-C., Tung, C.C.
  65. and Liu, H.H., 1998. The empirical mode decomposition and the Hilbert spectrum for
  66. nonlinear and non-stationary time series analysis. Proc. Roy. Soc. London, Series A, 454:
  67. 903-995.
  68. SPARSE DICTIONARY LEARNING 453
  69. Huang, W., Wang, R., Chen, Y., Li, H. and Gan, S., 2016a. Damped multichannel singular
  70. spectrum analysis for 3D random noise attenuation. Geophysics, 81: V261-V270.
  71. Huang, W., Wang, R., Chen, Y., Yuan, Y. and Zhou, Y., 2016b. Randomized-order multi-channel
  72. singular spectrum analysis for simultaneously attenuating random and coherent noise.
  73. Expanded Abstr., 86th Ann. Internat. SEG Mtg., Dallas: 4777-4781.
  74. Huang, W., Wang, R., Yuan, Y., Gan, S. and Chen, Y., 2017. Signal extraction using
  75. randomized-order multichannel singular spectrum analysis. Geophysics, 82(2): V59-V74.
  76. Huang, W., Wang, R., Zhang, M., Chen, Y. and Yu, J., 2015. Random noise attenuation for 3D
  77. seismic data by modified multichannel singular spectrum analysis. Extended Abstr., 77th
  78. EAGE Conf., Madrid. DOI.10.3997/2214- 4609.201412830.
  79. Huang, W., Wang, R., Zhou, Y., Chen, Y. and Yang, R., 2016c. Improved principal component
  80. analysis for 3D seismic data simultaneous reconstruction and denoising. Expanded Abstr. ,
  81. 86th Ann. Internat. SEG Mtg., Dallas.
  82. Kaplan, S.T., Sacchi, M.D. and Ulrych, T.J., 2009. Sparse coding for data-driven coherent and
  83. incoherent noise attenuation. Expanded Abstr., 79th Ann. Internat. SEG Mtg., Houston:
  84. 3327-3331.
  85. Kong, D. and Peng, Z., 2015. Seismic random noise attenuation using shearlet and total generalized
  86. variation. J. Geophys. Engineer., 12: 1024-1035.
  87. Kong, D., Peng, Z., He, Y. and Fan, H., 2016. Seismic random noise attenuation using directional
  88. total variation in the shearlet domain. J. Seismic Explor., 25: 321-338.
  89. Li, H., Wang, R., Cao, S., Chen, Y. and Huang, W., 2016. A method for low-frequency noise
  90. suppression based on mathematical morphology in microseismic monitoring. Geophysics,
  91. 81(3): V159-V 167.
  92. Liu, G., Fomel, S., Jin, L. and Chen, X., 2009a. Stacking seismic data using local correlation.
  93. Geophysics, 74: V43-V48.
  94. Liu, Y., Liu, C. and Wang, D., 2009b. A 1D time-varying median filter for seismic random,
  95. spike-like noise elimination. Geophysics, 74: V17-V24.
  96. Liu, C., Wang, D., Hu, B. and Wang, T., 2016a. Seismic deconvolution with shearlet sparsity
  97. constrained inversion. J. Seismic Explor., 25: 433-445.
  98. Liu, W., Cao, S. and Chen, Y., 2016b. Applications of variational mode decomposition in seismic
  99. time-frequency analysis. Geophysics, 81: V365-V378.
  100. Liu, W., Cao, S. and Chen, Y., 2016c. Seismic time-frequency analysis via empirical wavelet
  101. transform. IEEE Geosci. Remote Sens. Lett., 13: 28-32.
  102. Liu, W., Cao, S., Chen, Y. and Zu, S., 2016d. An effective approach to attenuate random noise
  103. based on compressive sensing and curvelet transform. J. Geophys. Engineer., 13: 135-145.
  104. Liu, W., Cao, S., Liu, Y. and Chen, Y., 2016e. Synchrosqueezing transform and its applications
  105. in seismic data analysis. J. Seismic Explor., 25: 27-44.
  106. Naghizadeh, M., 2012. Seismic data interpolation and denoising in the frequency-wavenumber
  107. domain. Geophysics, 77: V71-V80.
  108. Neelamani, R., Baumstein, A., Gillard, D., Hadidi, M. and Soroka, W., 2008. Coherent and
  109. random noise attenuation using the curvelet transform. The Leading Edge, 27: 240-248.
  110. Rubinstein, R., Zibulevsky, M. and Elad, M., 2008. Efficient implementation of the k-svd algorithm
  111. using batch orthogonal matching pursuit. Tech. Rep. Comput. Sci. Dept., Technion Israel
  112. Inst. of Technol.
  113. Shahidi, R., Tang, R., Ma, J. and Herrmann, F.J., 2013. Application of randomized sampling
  114. schemes to curvelet-based sparsity-promoting seismic data recovery. Geophys. Prosp., 61:
  115. 973-997.
  116. Wang, D., Liu, C., Liu, Y. and Liu, G., 2008. Application of wavelet transform based on lifting
  117. scheme and percentiles soft-threshold to elimination of seismic random noise. Progr.
  118. Geophys. (in Chinese), 23: 1124-1130.
  119. Wang, J., Ng, M. and Perz, M., 2010. Seismic data interpolation by greedy local Radon transform.
  120. Geophysics, 75: WB225-WB234.
  121. Wu, J., Wang, R., Chen, Y., Zhang, Y., Gan, S. and Zhou, C., 2016. Multiples attenuation using
  122. shaping regularization with seislet domain sparsity constraint. J. Seismic Explor., 25: 1-9.
  123. 454 ZHOU, LI, XIE, ZHANG & CHEN
  124. Xue, Y., Chang, F., Zhang, D. and Chen, Y., 2016a. Simultaneous sources separation via an
  125. iterative rank-increasing method. IEEE Geosci. Remote Sens. Lett., 13: 1915-1919.
  126. Xue, Y., Yang, J., Ma, J. and Chen, Y., 2016b. Amplitude-preserving nonlinear adaptive multiple
  127. attenuation using the high-order sparse Radon transform. J. Geophys. Engineer., 13: 207-
  129. Xue, Y., Man, M., Zu, S., Chang, F. and Chen, Y., 2017. Amplitude-preserving iterative
  130. deblending of simultaneous source seismic data using high-order Radon transform. J. Appl.
  131. Geophys., 139: 79-90.
  132. Yang, W., Wang, R., Chen, Y. and Wu, J., 2014. Random noise attenuation using a new spectral
  133. decomposition method. Expanded Abstr., 84th Ann. Internat. SEG Mtg., Denver: 4366-
  135. Yang, W., Wang, R., Chen, Y., Wu, J. Qu, S., Yuan, J. and Gan, S., 2015. Application of
  136. spectral decomposition using regularized non-stationary autoregression to random noise
  137. attenuation. J. Geophys. Engineer., 12: 175-187.
  138. Yu, Z., Ferguson, J., McMechan, G. and Anno, P., 2007. Wavelet-Radon domain dealiasing and
  139. interpolation of seismic data. Geophysics, 72: V41-V49.
  140. Zhang, D., Chen, Y., Huang, W. and Gan, S., 2016a. Multi-step damped multichannel singular
  141. spectrum analysis for simultaneous reconstruction and denoising of 3D seismic data. J.
  142. Geophys. Engineer., 13: 704-720.
  143. Zhang, D., Chen, Y., Huang, W. and Gan, S., 2016b. Multi-step reconstruction of 3D seismic data
  144. via an improved mass algorithm. Expanded Abstr., CPS/SEG Internat. Geophys. Conf. ,
  145. Beijing: 745-749.
  146. Zhong, W., Chen, Y., Gan, S. and Yuan, J., 2016. L,,. norm regularization for 3D seismic data
  147. interpolation. J. Seismic Explor., 25: 257-268.
  148. Zu, S., Zhou, H., Chen, Y., Qu, S., Zou, X., Chen, H. and Liu, R., 2016a. A periodically varying
  149. code for improving deblending of simultaneous sources in marine acquisition. Geophysics,
  150. 81: V213-V225.
  151. Zu, S., Zhou, H., Chen, Y., Chen, H., Cao, M. and Xie, C., 2016b. A marine field trial for
  152. iterative deblending of simultaneous sources. Expanded Abstr., 86th Ann. Internat. SEG
  153. Mtg., Dallas: 113-118.
Share
Back to top
Journal of Seismic Exploration, Electronic ISSN: 0963-0651 Print ISSN: 0963-0651, Published by AccScience Publishing
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here
Accept