AccScience Publishing / JSE / Article
Submit to JSE
Cite this article
2
Views
Journal Browser
Volume | Year
Issue
Search
Forthcoming Issue
Current Issue
View All
News and Announcements
View All
ARTICLE

Sparse dictionary learning for noise attenuation in the exactly flattened dimension

HUI LV
Show Less
Department of Architecture Engineering and Administration, Jiangxi Institute of Economic Administrators, 269 Wolong Road, Hongjiaozhou District Nanchang, Jiangxi Province, 330088, P.R. China,
School of Civil Engineering and Architecture, Nanchang Hangkong University, 696 South Fenghe Avenue, Nanchang 330063, Jiangxi Province, P.R. China,
JSE 2019, 28(5), 449–474;
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

Lv, H., 2019. Sparse dictionary learning for noise attenuation in the exactly flattened dimension. Journal of Seismic Exploration, 28: 449-474. Seismic noise attenuation is a long-standing and crucial problem in reflection seismic data processing community. In recently years, the dictionary learning based approaches have attracted more and more attention. Dictionary learning provides an adaptive way to optimally represent a given dataset. In dictionary learning, the basis function is adapted according the given data instead of being fixed in many analytical sparse transforms. The application of the dictionary learning techniques in seismic data processing has been popular in the past decade. However, most dictionary learning algorithms are directly taken from the image processing community and thus are not suitable for seismic data. Considering that the seismic data is spatially coherent, the dictionary should better be learned according to the coherency information in the seismic data. We found the dictionary learning performs better when the spatial correlation is stronger and thus we propose to use a flattening operator to help learn the dictionary in the flattened dimension, where the strong spatial coherence helps construct a dictionary that follows better the structural pattern in the seismic data. The presented dictionary learning in the flattened dimension (DLF) thus has a stronger capability in separating signal and noise. We use both synthetic and field data examples to demonstrate the superb performance of the proposed method.

Keywords
noise suppression
dictionary learning
flattening
seismic data
signal-to-noise ratio
References
  1. Abma, R. and Claerbout, J., 1995. Lateral prediction for noise attenuation by t-x and f-x
  2. techniques. Geophysics, 60: 1887-1896.
  3. Bai, M. and Wu, J., 2017. Efficient deblending using median filtering without correct
  4. normal moveout - with comparison on migrated images. J. Seismic Explor., 26:
  5. 455-479.
  6. Bai, M., Wu, J., Xie, J. and Zhang, D., 2018a. Least-squares reverse time migration of
  7. blended data with low-rank constraint along structural direction. J. Seismic Explor.,
  8. 27: 29-48.
  9. Bai, M., Wu, J., Zu, S. and Chen, W., 2018b. A structural rank reduction operator for
  10. removing artifacts in least-squares reverse time migration. Comput. Geosci., 117:
  11. 9-20.
  12. Canales, L., 1984. Random noise reduction. Expanded Abstr., 54th Ann. Internat. SEG
  13. Mtg., Atlanta: 525-527.
  14. Chen, W., Chen, Y. and Cheng, Z., 2017a. Seismic time-frequency analysis using an
  15. improved empirical mode decomposition algorithm. J. Seismic Explor., 26: 367-380.
  16. Chen, W., Chen, Y. and Liu, W., 2016a. Ground roll attenuation using improved
  17. complete ensemble empirical mode decomposition. J. Seismic Explor., 25: 485-495.
  18. Chen, W., Xie, J., Zu, S., Gan, S. and Chen, Y., 2017b. Multiple reflections noise
  19. attenuation using adaptive randomized-order empirical mode decomposition. IEEE
  20. Geosci. Remote Sens. Lett., 14: 18-22.
  21. Chen, W., Yuan, J., Chen, Y. and Gan, S., 2017c. Preparing the initial model for iterative
  22. deblending by median filtering. J. Seismic Explor., 26: 25-47.
  23. Chen, W., Zhang, D. and Chen, Y., 2017d. Random noise reduction using a hybrid
  24. method based on ensemble empirical mode decomposition. J. Seismic Explor., 3:
  25. 227-249.
  26. Chen, Y., 2016. Dip-separated structural filtering using seislet thresholding and adaptive
  27. empirical mode decomposition based dip filter. Geophys. J. Internat., 206: 457-469.
  28. Chen, Y., 2017. Fast dictionary learning for noise attenuation of multidimensional
  29. seismic data. Geophys. J. Internat., 209: 21-31.
  30. Chen, Y., 2018a. Fast waveform detection for microseismic imaging using unsupervised
  31. machine learning. Geophys. J. Internat.,215: 1185-1199.
  32. Chen, Y., 2018b, Non-stationary least-squares complex decomposition for microseismic
  33. noise attenuation. Geophys. J. Internat., 213: 1572-1585.
  34. Chen, Y., Chen, H., Xiang, K. and Chen, X., 2017e. Preserving the discontinuities in
  35. least-squares reverse time migration of simultaneous-source data. Geophysics, 82(3):
  36. $185- $196.
  37. Chen, Y. and Fomel, S., 2015, Random noise attenuation using local signal-and-noise
  38. orthogonalization. Geophysics, 80: WD1-WD9.
  39. Chen, Y. and Fomel, S., 2018. EMD-seislet transform. Geophysics, 83(1): A27-A32.
  40. Chen, Y., Fomel, S. and Hu, J., 2014. Iterative deblending of simultaneous-source
  41. seismic data using seislet-domain shaping regularization: Geophysics, 79(5):
  42. V179-V189.
  43. Chen, Y., Huang, W., Zhou, Y., Liu, W. and Zhang, D., 2018. Plane-wave orthogonal
  44. polynomial transform for amplitude-preserving noise attenuation. Geophys. J.
  45. Internat., 214: 2207-2223.
  46. Chen, Y. and Ma, J., 2014. Random noise attenuation by f-x empirical mode
  47. decomposition predictive filtering: Geophysics, 79, V81-V91.
  48. Chen, Y., J. Ma, and S. Fomel, 2016b, Double-sparsity dictionary for seismic noise
  49. attenuation. Geophysics, 81(2): V17-V30.
  50. Chen, Y., Zhang, D., Huang, W. and Chen, W., 2016c. An open-source matlab code
  51. package for improved rank-reduction 3D seismic data denoising and reconstruction.
  52. Comput. Geosci., 95: 59-66.
  53. Chen, Y., Zhang, D., Jin, Z., Chen, X., Zu, S., Huang, W. and Gan, S., 2016d.
  54. Simultaneous denoising and reconstruction of 5D seismic data via damped
  55. rank-reduction method. Geophys. J. Internat., 206: 1695-1717.
  56. Chen, Y., Zhou, Y., Chen, W., Zu, S., Huang, W. and Zhang, D., 2017f,.Empirical low
  57. rank decomposition for seismic noise attenuation. IEEE Transact. Geosci. Remote
  58. Sens., 55: 4696-4711.
  59. Chen, Y., Zu, S., Wang, Y. and Chen, X., 2019. Deblending of simultaneous-source data
  60. using a structure-oriented space-varying median filter. Geophys. J. Internat., 216:
  61. 1214-1232.
  62. Cheng, J. and Sacchi, M., 2015. Separation and reconstruction of simultaneous source
  63. data via iterative rank reduction. Geophysics, 80(4): V57-V66.
  64. Dragomiretskiy, K. and Zosso, D., 2014. Variational mode decomposition. IEEE
  65. Transact. Signal Process., 62: 531-544.
  66. Fabien-Ouellet,G. Gloaguen, E. and Giroux, B., 2017. Time-domain seismic modeling
  67. in viscoelastic media for full waveform inversion on heterogeneous computing
  68. platforms with opencl (????). Comput. Geosci., 100: 142-155.
  69. Fomel, S., 2002. Application of plane-wave destruction filters. Geophysics, 67:
  70. 1946-1960.
  71. Fomel, S., 2013. Seismic data decomposition into spectral components using regularized
  72. non-stationary autoregression. Geophysics, 78: 069-076.
  73. Gan, S., Chen, Y., Zu, S., Qu, S. and Zhong, W., 2015a. Structure-oriented singular value
  74. decomposition for random noise attenuation of seismic data. J. Geophys. Engineer.,
  75. 12: 262-272.
  76. Gan, S., Wang, S., Chen, Y., Jin, Z. and Zhang, Y., 2015b. Dealiased seismic data
  77. interpolation using seislet transform with low-frequency constraint. IEEE Geosci.
  78. Remote Sens. Lett., 12: 2150-2154.
  79. Gan, S., Wang, S., Chen, Y., Chen, J., Zhong, W. and Zhang, C., 2016a. Improved
  80. random noise attenuation using f-x empirical mode decomposition and local similarity.
  81. Appl. Geophys., 13: 127-134.
  82. Gan, S., Wang, S., Chen, Y., Chen, X. and Xiang, K., 2016b. Separation of simultaneous
  83. sources using a structural-oriented median filter in the flattened dimension. Comput.
  84. Geosci., 86: 46-54.
  85. Gan, S., Wang, S., Chen, Y., Qu, S. and Zu, S., 2016c. Velocity analysis of
  86. simultaneous-source data using high-resolution semblance-coping with the strong
  87. noise. Geophys. J. Internat., 204: 768-779.
  88. Gan, S., Wang, S., Chen, Y. and Chen, X., 2016d. Simultaneous-source separation using
  89. iterative seislet-frame thresholding, IEEE Geosci. Remote Sens. Lett., 13: 197-201.
  90. Gan, S., Chen, Y., Wang, S., Chen, X., Huang, W. and Chen, H., 2016e. Compressive
  91. sensing for seismic data reconstruction using a fast projection onto convex sets
  92. algorithm based on the seislet transform. J. Appl. Geophys., 130: 194-208.
  93. Gao, J., Sacchi, M.D. and Chen, X., 2013. A fast reduced-rank interpolation method for
  94. prestack seismic volumes that depend on four spatial dimensions. Geophysics, 78(1,):
  95. V21-V30.
  96. Garcia-Yeguas, A., Ledo, J., Pina-Varas, P., Prudencio, J., Queralt, P., Marcuello, A.,
  97. Ibanez, J.M., Benjumea, B., Sanchez-Alzola, A. and Perez, N., 2017. A 3D joint
  98. interpretation of magnetotelluric and seismic tomographic models: The case of the
  99. volcanic island of Tenerife. Comput. Geosci, 109: 95-105.
  100. Huang, N.E., Shen, Z., Long, S.R., Wu, M.C., Shih, H.H., Zheng, Q., Yen, N.-C., Tung,
  101. C.C. and Liu, H.H., 1998. The empirical mode decomposition and the Hilbert
  102. spectrum for nonlinear and non-stationary time series analysis. Proc. Roy. Soc.
  103. London Series A, 454: 903-995.
  104. Li, C., Liu, G. and Li, Y., 2017a,. A practical implementation of 3d TTI reverse time
  105. migration with multi-gpus. Comput. Geosci., 102: 68-78.
  106. Li, C. and Zhang, F., 2017. Matching pursuit parallel decomposition of seismic data.
  107. Comput. Geosci., 104: 54-61.
  108. Li, H., Tuo, X., Shen, T., Henderson, MJ., Courtois, J. and Yan, M., 2017b. An
  109. improved lossless group compression algorithm for seismic data in seg-y and
  110. miniseed file formats. Comput. Geosci., 100: 41-45.
  111. Li, H., Wang, R., Cao, S., Chen, Y. and Huang, W., 2016a. A method for low-frequency
  112. noise suppression based on mathematical morphology in microseismic monitoring.
  113. Geophysics, 81: V159-V167.
  114. Li, H., Wang, R., Cao, S., Chen, Y., Tian, N. and Chen, X., 2016b. Weak signal detection
  115. using multiscale morphology in microseismic monitoring. J. Appl. Geophys., 133:
  116. 39-49.
  117. Liu, S., Yang, D. and Ma, J., 2017a. A modified symplectic prk scheme for seismic wave
  118. modeling. Comput. Geosci., 99: 28-36.
  119. Liu, W., Cao, S. and Chen, Y., 2016a. Applications of variational mode decomposition in
  120. seismic time-frequency analysis. Geophysics, 81(5): V365-V378.
  121. Liu, W., Cao, S. and Chen, Y., 2016b. Seismic time-frequency analysis via empirical
  122. wavelet transform. IEEE Geosci. Remote Sens. Lett., 13: 28-32.
  123. Liu, W., Cao, S., Chen, Y. and Zu, S., 2016c. An effective approach to attenuate random
  124. noise based on compressive sensing and curvelet transform. J. Geophys. Engineer.,
  125. 13: 135-145.
  126. Liu, W., Cao, S., Jin, Z., Wang, Z. and Chen, Y., 2018. A novel hydrocarbon detection
  127. approach via high-resolution frequency-dependent AVO inversion based on
  128. variational mode decomposition. IEEE Transact. Geosci. Remote Sens., 56:
  129. 2007-2024.
  130. Liu, W., Cao, S. and Wang, Z., 2017b. Application of variational mode decomposition to
  131. seismic random noise reduction. J. Geophys. Engineer., 14: 888.
  132. Liu, W., Cao, S., Wang, Z., Kong, X. and Chen, Y., 2017c. Spectral decomposition for
  133. hydrocarbon detection based on VMD and Teager-Kaiser energy. IEEE Geosci.
  134. Remote Sens. Lett., 14: 539-543.
  135. Liu, Y., Fomel, S. and Liu, G., 2010. Nonlinear structure-enhancing filtering using
  136. plane-wave prediction. Geophys. Prosp., 58: 415-427.
  137. Lv, H. and Bai, M., 2018. Learning dictionary in the approximately flattened structure
  138. domain. J. Appl. Geophys., 159: 522-531.
  139. Mayne, W.H., 1962. Common reflection point horizontal data stacking techniques.
  140. Geophysics, 27: 927-938.
  141. Rastogi, R., Londhe, A., Srivastava, A., Sirasala, K.M. and Khonde, K., 2017. 3D
  142. Kirchhoff depth migration algorithm: A new scalable approach for parallelization on
  143. multicore CPU based cluster. Comput. Geosci., 100: 67-75.
  144. Romano, Y. and Elad, M., 2013. Improving K-VSD denoising by post-processing its
  145. method-noise. Image Processing (ICIP), 20th IEEE Internat. Conf.: 435-439.
  146. Rubinstein, R., Zibulevsky, M. and Elad, M., 2008. Efficient implementation of the
  147. K-SVD algorithm using batch orthogonal matching pursuit. Tech. Report.
  148. Rubinstein, R., Zibulevsky, M. and Elad, M., 2010. Double sparsity: learning sparse
  149. dictionaries for sparse signal approximation. IEEE Transact. Signal Process., 58:
  150. 1553-1564.
  151. Siahsar, M.A.N., Abolghasemi, V. and Chen, Y., 2017a. Simultaneous denoising and
  152. interpolation of 2D seismic data using data-driven non-negative dictionary learning.
  153. Signal Process., 141: 309-321.
  154. Siahsar, M.A.N., Gholtashi, S., Kahoo, A.R., Chen, W. and Chen, Y., 2017b. Data-driven
  155. multi-task sparse dictionary learning for noise attenuation of 3D seismic data.
  156. Geophysics, 82(6): V385-V396.
  157. Siahsar, M.A.N., Gholtashi, S., Kahoo, A.R., Marvi, H. and Ahmadifard, A., 2016.
  158. Sparse time-frequency representation for seismic noise reduction using low-rank and
  159. sparse decomposition. Geophysics, 81: V117-V124.
  160. Siahsar, M.A.N., S. Gholtashi, E. Olyaei, W. Chen, and Y. Chen, 2017c, Simultaneous
  161. denoising and interpolation of 3D seismic data via damped data-driven optimal
  162. singular value shrinkage. IEEE Geosci. Remote Sens. Lett., 14: 1086-1090.
  163. Song, C., Liu, Z., Wang, Y., Li, X. and Hu, G., 2017. Multi-waveform classification for
  164. seismic facies analysis. Comput. Geosci., 101: 1-9.
  165. Vautard, R., Yiou, P. and Ghil, M., 1992. Singular-spectrum analysis: A toolkit for short,
  166. noisy chaotic signals. Physica D: Nonlinear Phenom., 58: 95-126.
  167. Wang, Y., Zhou, H., Zu, S., Mao, W. and Chen, Y., 2017a. Three-operator proximal
  168. splitting scheme for 3D seismic data reconstruction. IEEE Geosci. Remote Sens.
  169. Lett., 14: 1830-1834.
  170. Wang, Y., Zhou, H., Chen, H. and Chen, Y., 2017b. Adaptive stabilization for
  171. Q-compensated reverse time migration. Geophysics, 83: S$15-S32.
  172. Wang, Y., Zhou, H., Ma, X. and Chen, Y., 2018. L1-2 minimization for exact and stable
  173. seismic attenuation compensation, Geophys. J. Internat., 213: 1629-1646.
  174. Wu, G., Fomel, S. and Chen, Y., 2018. Data-driven time-frequency analysis of seismic
  175. data using non-stationary prony method. Geophys. Prosp., 66: 85-97.
  176. Wu, J. and Bai, M., 2018a. Incoherent dictionary learning for reducing crosstalk noise in |
  177. east-squares reverse time migration. Comput. Geosci., 114: 11-21.
  178. Wu, J. and Bai, M., 2018b. Stacking seismic data based on principal component analysis.
  179. J. Seismic Explor., 27: 331-348.
  180. Wu, Z. and Huang, N.E., 2009. Ensemble empirical mode decomposition: A
  181. noise-assisted data analysis method. Advances in Adaptive Data Analysis, 1: 1-41.
  182. Xie, J., Chen, W., Zhang, D., Zu, S. and Chen, Y., 2017. Application of principal
  183. component analysis in weighted stacking of seismic data. IEEE Geosci. Remote Sens.
  184. Lett., 14: 1213-1217.
  185. Xie, J., Di, B., Schmitt, D., Wei, J. and Chen, Y., 2018. Estimation of 6 and C,, of
  186. organic-rich shale from laser ultrasonic technique (LUT) measurement. Geophysis,
  187. 83(4): C137-C152.
  188. Xue, Y., Chang, F., Zhang, D. and Chen, Y., 2016. Simultaneous sources separation via
  189. an iterative rank-increasing method. IEEE Geosci. Remote Sens. Lett., 13:
  190. 1915-1919.
  191. Xue, Y., Man, M., Zu, S., Chang, F. and Chen, Y., 2017. Amplitude-preserving iterative
  192. deblending of simultaneous source seismic data using high-order radon transform. J.
  193. Appl. Geophys., 139: 79-90.
  194. Yang, W., Wang, R., Wu, J., Chen, Y., Gan, S. and Zhong, W., 2015. An efficient and
  195. effective common reflection surface stacking approach using local similarity and
  196. plane-wave flattening. J. Appl. Geophys., 117: 67-72.
  197. Yang, X. and Zhu, P., 2017. Stochastic seismic inversion based on an improved local
  198. gradual deformation method. Comput. Geosci., 109: 75-86.
  199. Zhang, D., Chen, Y., Huang, W. and Gan, S., 2016. Multi-step damped multichannel
  200. singular spectrum analysis for simultaneous reconstruction and denoising of 3D
  201. seismic data. J. Geophys. Engineer., 13: 704-720.
  202. Zhang, D., Zhou, Y., Chen, H., Chen, W., Zu, S. and Chen, Y., 2017. Hybrid
  203. rank-sparsity constraint model for simultaneous reconstruction and denoising of 3D
  204. seismic data. Geophysics, 82(5): V351-V367.
  205. Zhou, Y., Gao, J., Chen, W. and Frossard, P., 2016. Seismic simultaneous source
  206. separation via patchwise sparse representation. IEEE Transact. Geosci. Remote Sens.,
  207. 54: 5271-5284.
  208. Zhou, Y. and Han, W., 2018. Multiples attenuation in the presence of blending noise. J.
  209. Seismic Explor., 27: 69-88.
  210. Zhou, Y., Li, S., Xie, J., Zhang, D. and Chen, Y., 2017a. Sparse dictionary learning for
  211. seismic noise attenuation using a fast orthogonal matching pursuit algorithm. J.
  212. Seismic Explor., 26: 433-454.
  213. Zhou, Y., Li, S., Zhang, D. and Chen, Y., 2018. Seismic noise attenuation using an online
  214. subspace tracking algorithm. Geophys. J. Internat., 212: 1072-1097.
  215. Zhou, Y., Shi, C., Chen, H., Xie, J., Wu, G. and Chen, Y., 2017b. Spike-like blending
  216. noise attenuation using structural low-rank decomposition. IEEE Geosci. Remote
  217. Sens. Lett., 14: 1633-1637.
  218. Zhou, Y. and S. Zhang, S., 2017. Robust noise attenuation based on nuclear norm
  219. minimization and a trace prediction strategy. J. Appl. Geophys., 147: 52-67.
  220. Zhu, L., Liu, E. and Mcclellan, J-H., 2014. Seismic data denoising through multiscale and
  221. sparsity-promoting dictionary learning. Geophysics, 80: WD45-WD57.
  222. Zu, S., Zhou, H., Chen, Y., Qu, S., Zou, X., Chen, H. and Liu, R., 2016. A periodically
  223. varying code for improving deblending of simultaneous sources in marine
  224. acquisition. Geophysics, 81:V213-V225.
  225. Zu, S., Zhou, H., Chen, Y., Pan, X., Gan, S. and Zhang, D., 2016. Interpolating big gaps
  226. using inversion with slope constraint. IEEE Geosci. Remote Sens. Lett., 13:
  227. 1369-1373.
  228. Zu, S., Zhou, H., Mao, W., Zhang, D., Li, C., Pan, X. and Chen, Y., 2017. Iterative
  229. deblending of simultaneous-source data using a coherency-pass shaping operator.
  230. Geophys. J. Internat., 211: 541-557.
  231. Zu, S., Zhou, H., Chen, H., Gong, F., Li, C., Zheng, H. and Chen, Y., 2017. Two field
  232. trials for deblending of simultaneous source: why we failed and why we succeeded?
  233. J. Appl. Geophys., 143: 182-194.
  234. Zu, S., Zhou, H., Chen, H., Li, Q., Zhang, Q. and Chen, Y., 2017. Shot-domain
  235. deblending using least-squares inversion. Geophysics, 82: V241-V256.
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