AccScience Publishing / JSE / Article
Submit to JSE
Cite this article
8
Views
Journal Browser
Volume | Year
Issue
Search
Forthcoming Issue
Current Issue
View All
News and Announcements
View All
ARTICLE

Desert seismic data denoising and effective signal recovery by using improved shearlet transform based on the deep-learning coefficient selection

XINTONG DONG1 ,  YUE LI2* ,  BAOJUN YANG3
Show Less
1 Jilin University, College of Instrumentation and Electrical Engineering, Jilin, P.R. China.,
2 Jilin University, College of Communication Engineering, Jilin, P.R. China.,
3 Jilin University, College of Geo-exploration Science and Technology, Jilin, P.R. China.,
JSE 2021, 30(5), 455–479;
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

Dong, X., Li, Y. and Yang, B., 2021. Desert seismic data denoising and effective signal recovery by using improved shearlet transform based on the deep-learning coefficient selection. Journal of Seismic Exploration, 30: 455-479. Contamination of seismic data by background noise causes difficulties for imaging, reservoir fluid prediction, and stratigraphic interpretation. Desert seismic data poses a particular problem mainly due to two reasons: (1) low signal-to-noise ratio (SNR); (2) serious frequency spectrum overlapping between the effective signals and low-frequency noise (mainly including random noise and surface waves). Therefore, when apply sparse-transform-based methods to denoise desert seismic data, conventional threshold functions fail to distinguish the effective signal coefficients and low-frequency noise coefficients, which is likely to result in residual noise and signal leakage. To solve this problem, we utilize the convolutional neural network (CNN) to act as a threshold function, thereby establishing an optimal non-linear relationship between noisy coefficients and effective signal coefficients. In addition, in order to achieve multi-scale and multi-direction accurate noise suppression, we construct a corresponding training dataset for each sub-band, so as to obtain a CNN-based coefficient selection model suitable for this sub-band. In this paper, we take shearlet transform as an example to verify the effectiveness of the proposed CNN-based threshold function. Synthetic and real examples demonstrate that our method can effectively suppress the desert low-frequency noise and completely recover the effective signals reflected by layers.

Keywords
desert seismic data
shearlet transform
noise suppression
convolutional neural network
low signal-to-noise ratio
spectrum overlapping.
References
  1. Akram, J., 2018. An application of waveform denoising for microseismic data using
  2. polarization-linearity and time-frequency thresholding. Geophys. Prosp., 66:
  3. 872-893.
  4. Bekara, M. and van der Baan, M., 2007. Local singular value decomposition for signal
  5. enhancement of seismic data. Geophysics, 72(2): V59-V65.
  6. Bekara, M. and van der Baan M., 2009. Random and coherent noise attenuation by
  7. empirical mode decomposition. Geophysics, 74(5): V89-V98.
  8. Beckouche, S. and Ma, J.W., 2014. Simultaneous dictionary learning and denoising for
  9. seismic data. Geophysics, 79(3): A27-A31.
  10. Bonar, D. and Sacchi, M., 2012. Denoising seismic data using the nonlocal means
  11. algorithm. Geophysics, 77(1): A5-A8.
  12. Chen, Y.K., Zhang, M., Bai, M. and Chen, W., 2019. Improving the signal-to-noise ratio
  13. of seismological datasets by unsupervised machine learning. Seismol. Res. Lett.,
  14. 90: 1552-1564.
  15. Dong, X.T., Li, Y. and Yang, B.J., 2019a. Desert low-frequency noise suppression by
  16. using adaptive DnCNNs based on the determination of high-order statistic.
  17. Geophys. J. Internat., 219: 1281-1299.
  18. Dong, X.T., Jiang, H., Zheng, S., Li, Y. and Yang, B.J., 2019b. Signal-to-noise ratio
  19. enhancement for 3C downhole microseismic data based on the 3D shearlet transform
  20. and improved back-propagation neural networks, Geophysics 84(4),V245-V254.
  21. Dong X.T., Zhong T. and Li Y., 2020a. New suppression technology for low-frequency
  22. noise in desert region: the improved robust principle component analysis based on
  23. prediction of neural network. IEEE Transact. Geosci. Remote Sens., in Press.
  24. Dong, X.T., Zhong, T. and Li, Y., 2020b. A deep-learning-based denoising method for
  25. multiarea surface seismic data. IEEE Geosci. Remote Sens. Lett., in Press.
  26. Duncan, G. and Beresford, G., 1995. Median filter behaviour with seismic data.
  27. Geophys. Prosp., 43: 329-345.
  28. Fomel, S. and Liu, Y., 2010. Seislet transform and seislet frame. Geophysics, 75(3):
  29. V25-V38.
  30. Gholami, A. and Zand, T., 2017. Fast L1-regularized radon transforms for seismic data
  31. processing. Digit. Sign. Process., 71: 83-94.
  32. Goudarzi, A. and Riahi, M.A., 2012. Seismic coherent and random noise attenuation
  33. using the undecimated discrete wavelet transform method with WDGA technique. J.
  34. Geophys. Engineer., 9: 619-631.
  35. Guo, K. and Labate, D., 2007. Optimally sparse multidimensional representation using
  36. shearlets. SIAM J. Mathemat. Anal., 39: 298-318.
  37. Giiltinay, N., 2017. Signal leakage in f -x deconvolution algorithms. Geophysics, 82(5):
  38. W31-W45.
  39. Han, J.J. and van der Baan, M., 2013. Empirical mode decomposition for seismic
  40. time-frequency analysis. Geophysics, 78(2). 09-019.
  41. Harris, P.E. and White, R.E., 1997. Improving the performance of f-x prediction filtering
  42. at low signal-to-noise ratios. Geophys. Prosp., 45: 269-302.
  43. Jin, K.H., McCann, M.T., Froustey, E. and Unser, M., 2017. Deep convolutional neural
  44. network for inverse problems in imaging. IEEE Transact. Image Process., 26:
  45. 4509-4522.
  46. Kulesh, M., Diallo, M., Holschneider, M., Kurennaya, K., Kruger, F., Ohrnberger, M.
  47. and Scherbaum, F., 2007. Polarization analysis in the wavelet domain based on
  48. adaptive covariance method. Geophys. J. Internat., 170: 667-678.
  49. Kutyniok, G. and Lim, W., 2011. Compactly supported shearlets are optimally sparse. J.
  50. Approxim. Theory, 163: 1564-1589.
  51. Li, F., Zhang, B., Verma, S. and Marfurt, K.J., 2017. Seismic signal denoising using
  52. thresholded variational mode decomposition. Explor. Geophys., 49: 450-461.
  53. Li, G.H., Li, Y. and Yang, B.J., 2017. Seismic exploration random noise on land:
  54. Modeling and application to noise suppression. IEEE Transact. Geosci. Remote
  55. Sens., 55: 4668-4681.
  56. Liang, X.Q., Li, Y. and Zhang, C., 2018. Noise suppression for microseismic data by
  57. non-subsampled shearlet transform based on singular value decomposition.
  58. Geophys. Prosp., 66: 894-903.
  59. Lim, W., 2010. The discrete shearlet transform: A new directional transform and
  60. compactly supported shearlet frames. IEEE Transact. Image Process., 19,
  61. 1166-1180.
  62. Loffe, S. and Szegedy, C., 2015. Batch normalization: Accelerating deep network
  63. training by reducing internal covariate shift. Proc., 32nd Internat. Conf. Mach.
  64. Learning, 448-456.
  65. Ma, H.T, Yao, H.Y., Li, Y. and Wang, H.Z., 2020a. Deep residual encoder-decoder
  66. networks for desert seismic noise suppression. IEEE Geosci. Remote Sens. Lett.,
  67. 17: 529-533.
  68. Ma, H.T, Yan, J. and Li, Y., 2020b. Low-frequency noise suppression of desert seismic
  69. data based on variational mode decomposition and low-rank component extraction.
  70. IEEE Geosci. Remote Sens. Lett., 17: 337-341.
  71. Mou, L.C., Ghamisi, P. and Zhu, X.X., 2018. Unsupervised spectral-spatial feature
  72. learning via deep residual conv-deconv network for hyperspectral image
  73. classification. IEEE Geosci. Remote Sens. Lett., 56: 391-406.
  74. Nazari Siahsar, M.A., Gholtashi, S., Abolghasemi, V. and Chen, Y., 2017. Simultaneous
  75. denoising and interpolation of 2D seismic data using data-driven non-negative
  76. dictionary learning. Sign. Process., 141: 309-321.
  77. Neelamani, R., Baumstein, A.I., Gillard, D.G., Hadidi, M.T. and Soroka, W.L., 2008.
  78. Coherent and random noise attenuation using the curvelet transform. The Leading
  79. Edge, 27: 240-248.
  80. Remez, T., Litany, O., Giryes, R. and Bronstein, A.M., 2018. Class-aware fully
  81. convolutional Gaussian and Poisson denoising. IEEE Transact. Geosci. Remote
  82. Sens., 27: 5707-5722.
  83. Stein, R.A. and Bartley, N.R., 1983. Continuously time-variable recursive digital
  84. band-pass filters for seismic signal processing. Geophysics 48: 702-712.
  85. Tang, N., Zhao, X., Li, Y. and Zhu, D., 2018. Adaptive threshold shearlet transform for
  86. surface microseismic data denoising. J. Appl. Geophys., 153: 64-74.
  87. Tian, Y.N., Li, Y. and Yang, B.J., 2014. Variable-eccentricity hyperbolic-trace TFPF for
  88. seismic random noise attenuation. IEEE Transact. Geosci. Remote Sens., 52:
  89. 6449-6458.
  90. Tirer, T. and Giryes, R., 2019. Super-resolution via image-adapted denoising CNNs:
  91. Incorporating external and internal learning. IEEE Signal Processing Letters 26(7),
  92. 1080-1084.
  93. Wang, F. and Chen, S., 2019. Residual learning of deep convolutional neural network for
  94. seismic random noise attenuation. IEEE Geosci. Remote Sens. Lett., 16: 1314-1318.
  95. Wang, Y., 1999. Random noise attenuation using forward-backward linear prediction. J.
  96. Seismic Explor., 8: 133-142.
  97. Wang, Y., Liu X., Gao F. and Rao Y., 2020. Robust vector median filtering with a
  98. structure-adaptive implementation. Geophysics, 85(5): V407-V414.
  99. Wang, Y., Lu, W., Wang, B. and Liu, L., 2016. A robust polynomial principal
  100. component analysis for seismic noise attenuation. J. Geophys. Engineer., 13:
  101. 1002-1009.
  102. Wu, S., Li, G.Q., Deng, L., Liu, L., Wu, D., Xie, Y. and Shi, L.P., 2019. L1-norm batch
  103. normalization for efficient training of deep neural networks. IEEE Transact. Neural
  104. Netw. Learning Syst., 30: 2043-2051.
  105. Wu, Y. and McMechan, G.A., 2019. Parametric convolutional neural network-domain
  106. full-waveform inversion. Geophysics, 84(6): R881-R896.
  107. Xiong, M.J., Li, Y. and Wu, N., 2014. Random-noise attenuation for seismic data by
  108. local parallel radial-trace TFPF. IEEE Transact Geosci. Remote Sens., 52:
  109. 4025-4031.
  110. Yang, W., Feng, J., Yang, J., Zhao, F., Liu, J., Guo, Z. and Yan, S., 2017. Deep edge
  111. guided recurrent residual learning for image super-resolution. IEEE Transact. Image
  112. Process., 26: 5895-5907.
  113. Yang Y., Liu C. and Langston C.A., 2020. Processing seismic ambient noise data with
  114. the continuous wavelet transform to obtain reliable empirical Green's functions.
  115. Geophys. J. Internat., 222: 1224-1235.
  116. Yuan, S.Y., Liu, J.W., Wang, S.X., Wang, T.Y. and Shi, P.D., 2018. Seismic waveform
  117. classification and first-break picking using convolution neural networks. IEEE
  118. Geosci. Remote Sens. Lett., 15: 272-276.
  119. Zhang, K., Zuo, W.M., Chen, Y.J., Meng, D.Y. and Zhang, L., 2017. Beyond a Gaussian
  120. denoiser: Residual learning of deep CNN for image denoising. IEEE Transact.
  121. Image Process., 26: 3142-3155.
  122. Zhong, T., Li, Y., Wu, N., Nie, P.F. and Yang, B.J., 2015a. Statistical analysis of
  123. background noise in seismic prospecting. Geophys. Prosp., 63: 1161-1174.
  124. Zhong, T., Li, Y., Wu, N., Nie, P.F. and Yang, B.J., 2015b. A study on the stationarity
  125. and Gaussianity of the background noise in land-seismic prospecting. Geophysics,
  126. 80(4): V67-V82.
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