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

Seismic random noise attenuation using multi-scale sparse dictionary learning

JINWEI FANG1 ,  LIANG ZHANG2* ,  HUI ZHOU3 ,  SHENGDONG LIU1 ,  BO WANG1 ,  WENJIE CHEN4
Show Less
1 State Key Laboratory of Deep Geomechanics & Underground Engineering, School of Resource and Earth Science, School of Mechanics and Civil Engineering, China University of Mining and Technology, Xuzhou, Jiangsu 221116, P.R. China,
2 Institute of Geosciences and Info-Physics, Central South University, Changsha, Hunan, 410083, P.R. China,
3 State Key Laboratory of Petroleum Resources and Prospecting, CNPC Key Lab of Geophysical Exploration, China University of Petroleum, Changping 102249, Beijing, P.R. China,
4 College of Information Technology, Guangxi Police College, Nanning, Guangxi 530028, P.R. China,
JSE 2022, 31(2), 177–202;
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

Fang, J.W., Zhang, L., Zhou, H., Liu, Z.D., Wang, B. and Chen, W.J., 2022. Seismic random noise attenuation using multi-scale sparse dictionary learning. Journal of Seismic Exploration, 31: 177-202. Seismic data contain random noise, which affects data processing and interpretation and possibly limits the use of seismic data in parameter building and attribute prediction. To effectively remove such noise, we develop a denoising workflow based on multi-scale sparse dictionary learning. The multi-scale sparse dictionary learning method decreases the complexity of data by two approaches. One is seismic data-sparse representation from the data domain to the wavelet domain by wavelet bases. The other is denoising by sparse dictionary learning in a certain frequency band without the noise effect from other frequency bands. Meanwhile, the wavelet transform can also reduce the dimension of the data, which ensures the computational efficiency of the proposed method. After analyzing the effects of sparse dictionary learning parameters on seismic data denoising, we test the proposed method on two synthetic and two field datasets. We learn from the examples that our approach can effectively recover signals from simulated and real noisy data, as well as time-variant noisy data. Compared with the sparse dictionary learning, K-singular value decomposition dictionary learning, and double-sparsity dictionary (DSD), our method can obtain the best-denoised result with less effective signals leaking in noise sections.

Keywords
sparse dictionary learning
wavelet transform
multi-scale denoising
References
  1. Aharon, M., Elad, M. and Bruckstein, A., 2006. K-SVD: An algorithm for designing
  2. over-complete dictionaries for sparse representation. IEEE Transact. Signal Process.,
  3. 54: 4311-4322.
  4. Bao, C., Ji, H. and Shen, Z., 2015. Convergence analysis for iterative data-driven tight
  5. frame construction scheme. Appl. Computat. Harmon. Analys., 38: 510-523.
  6. Beckouche, S. and Ma, J., 2014. Simultaneous dictionary learning and denoising for
  7. seismic data. Geophysics, 79(3): A27-A31.
  8. Bednar, J.B., 1983. Applications of median filtering to deconvolution, pulse estimation,
  9. and statistical editing of seismic data. Geophysics, 48: 1598-1610.
  10. Cai, J.F., Ji, H., Shen, Z. and Ye, G.B., 2014. Data-driven tight frame construction and
  11. image denoising. Appl. Computat. Harmon. Analys., 37: 89-105.
  12. Chen, S.S., Donoho, D.L. and Saunders, M.A., 2001. Atomic decomposition by basis
  13. pursuit. SIAM review, 43: 129-159.
  14. Chen, Y., 2017. Fast dictionary learning for noise attenuation of multidimensional
  15. seismic data. Geophys. J. Internat., 209: 21-31.
  16. Chen, Y., Ma, J. and Fomel, S., 2016. Double sparsity dictionary for seismic noise
  17. attenuation. Geophysics, 81(2): V103-V116.
  18. Daubechies, I., 1992. Ten lectures on wavelets. CBMS-NSF Regional Conference Series
  19. in Applied Mathematics, 61. SIAM Publications, Philadelphia.
  20. Daubechies, I, Han, B., Ron, A. and Shen, Z., 2003. Framelets: MRA-based
  21. constructions of wavelet frames. Appl. Computat. Harmon. Analys., 14: 1-46.
  22. Donoho D.L., 1995. Denoising by soft-thresholding. IEEE Transact. Informat. Theory,
  23. 41: 613-627.
  24. Fomel, S., Sava, P., Vlad, IL, Liu, Y. and Bashkardin, V., 2013. Madagascar:
  25. Open-source software project for multidimensional data analysis and reproducible
  26. computational experiments. J. Open Res. Softw., 1, e8.
  27. Feng, Z., 2021. Seismic random noise attenuation using effective and efficient dictionary
  28. learning. J. Appl. Geophys., 104258.
  29. Hennenfent, G. and Herrmann, F.J., 2006. Seismic denoising with nonuniformly sampled
  30. curvelets. Comput. Sci. Engineer., 8(3): 16-25.
  31. Ioup, J.W. and Ioup, G.E., 1998. Noise removal and compression using a wavelet
  32. transform. Expanded Abstr., 68th Ann. Internat. SEG Mtg. New Orleans:
  33. 1076-1079.
  34. Jawerth, B. and Sweldens, W., 1994. An overview of wavelet based multiresolution
  35. analyses. SIAM review, 36: 377-412.
  36. Liang, J., Ma, J. and Zhang, X., 2014. Seismic data restoration via data-driven tight
  37. frame. Geophysics, 79(3): V65-V74.
  38. Liu, C., Song, C. and Lu, Q., 2017. Random noise de-noising and direct wave
  39. eliminating based on SVD method for ground penetrating radar signals. J. Appl.
  40. Geophys., 144: 125-133.
  41. Lopes, M.E., 2016. Unknown sparsity in compressed sensing: Denoising and inference.
  42. IEEE Transact. Informat. Theory, 62: 5145-5166.
  43. Lv, H. and Bai, M., 2018. Learning dictionary in the approximately flattened structure
  44. domain. J. Appl. Geophys., 159: 522-531.
  45. Mallat, S., 1999. A Wavelet Tour of Signal Processing. Elsevier Science Publishers,
  46. Amsterdam.
  47. Margrave, G.F., 1998. Theory of nonstationary linear filtering in the Fourier domain with
  48. application to time-variant filtering. Geophysics, 63: 244-259.
  49. Miao, X. and Cheadle, S., 1998. Noise attenuation with wavelet transforms. Expanded
  50. Abstr., 68th Ann. Internat. SEG Mtg., New Orleans: 1072-1075.
  51. Naghizadeh, M. and Sacchi, M.D., 2010. Beyond alias hierarchical scale curvelet
  52. interpolation of regularly and irregularly sampled seismic data. Geophysics, 75(6):
  53. WB189-WB202.
  54. Neelamani, R., Baumstein, A. and Ross, W.S., 2010. Adaptive subtraction using
  55. complex-valued curvelet transforms. Geophysics, 75(4): V51-V60.
  56. Ophir, B., Lustig, M. and Elad, M., 2011. Multi-scale dictionary learning using wavelets.
  57. IEEE J. Select. Topics Sign. Process., 5: 1014-1024.
  58. Rubinstein, R., Zibulevsky, M. and Elad, M., 2009. Double sparsity: learning sparse
  59. dictionaries for sparse signal approximation. IEEE Transact. Signal Process., 58:
  60. 1553-1564.
  61. Schnemann, P.H., 1966. A generalized solution of the orthogonal procrustes problem.
  62. Psychometrika, 31: 1-10.
  63. Sezer, O.G., Guleryuz, O.G. and Altunbasak, Y., 2015. Approximation and compression
  64. with sparse orthonormal transforms. IEEE Transact. Image Process., 24: 2328-2343.
  65. Strang, G. and Nguyen, T., 1996. Wavelets and Filter Banks, Wellesley-Cambridge
  66. Press, New York.
  67. Tropp, J.-A. and Gilbert, A.C., 2007. Signal recovery from random measurements via
  68. orthogonal matching pursuit. IEEE Transact. Informat. Theory, 53: 4655-4666.
  69. Turquais, P., Asgedom, E.G. and Sdéllner, W., 2017. A method of combining
  70. coherence-constrained sparse coding and dictionary learning for denoising.
  71. Geophysics, 82(3): V137-V148.
  72. Wang, D., Saab, R., Yilmaz, O. and Herrmann, F.J., 2008. Bayesian wavefield separation
  73. by transform-domain sparsity promotion. Geophysics, 73(5): A33-A38.
  74. Yilmaz, O. and Donherty, S., 2001. Seismic Data Analysis. SEG, Tulsa, OK.
  75. Yu, S., Ma, J. and Osher, S., 2016. Monte Carlo data-driven tight frame for seismic data
  76. recovery. Geophysics, 81(4): V327-V340.
  77. Yu, S., Ma, J., Zhang, X. and Sacchi, M.D., 2015. Interpolation and denoising of
  78. high-dimensional seismic data by learning a tight frame. Geophysics, 80(5):
  79. V119-V132.
  80. Yuan, Y.O. and Simons, F.J., 2014. Multi-scale adjoint waveform-difference tomography
  81. using wavelets. Geophysics, 79(3): WA79-WA95.
  82. Zhan, R. and Dong, B., 2016. CT image reconstruction by spatial-Radon domain
  83. data-driven tight frame regularization. SIAM J. Imaging Sci., 9: 1063-1083.
  84. Zhang, R. and Ulrych, T.J., 2003. Physical wavelet frame denoising. Geophysics, 68:
  85. 225-231.
  86. Zhang, Q., Wang, H., Chen, W. and Huang, G., 2020. A robust method for random noise
  87. suppression based on the Radon transform. J. Appl. Geophys., 104183.
  88. Zhu, L., Liu, E. and Mcclellan, J.H., 2015. Seismic data denoising through multiscale
  89. and sparsity-promoting dictionary learning. Geophysics, 80(6): WD45-WD57.
  90. Zu, S., Zhou, H., Wu, R., Jiang, M. and Chen, Y., 2019. Dictionary learning based on dip
  91. patch selection training for random noise attenuation. Geophysics, 84(3):
  92. V169-V183.
  93. Zu, S., Zhou, H., Wu, R., Mao, W. and Chen, Y., 2018. Hybrid-sparsity constrained
  94. dictionary learning for iterative deblending of extremely noisy simultaneous-source
  95. data. IEEE Transact. Geosci. Remote Sens., 57: 2249-2262.
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