Coal Geology & Exploration


Seismic data processing is a critical step in seismic exploration. Due to the complexity of underground structure and surface conditions, seismic data processing needs to go through a series of complex processes, thus forming various types of seismic data. Different types of seismic data have different data characteristics. Exploring and making full use of the data characteristics can not only give full play to the technical potential of processing methods, eliminate the influence of various non-geological factors on the quality of seismic data processing, but also enhance the reliability of seismic data processing. Improving the signal-to-noise ratio and resolution of seismic data plays a significant role in the exploration and development of complex reservoirs. The useful signal in pre-stack seismic imaging gathers(common-reflection-point gathers) is approximately horizontal, and the useful signal in post-stack seismic imaging data is regular and straightforward compared with random noise and arc-like imaging noise because of the regularity of stratum deposition. Therefore, the corresponding FK domain is focused on low-frequency energy due to the specific characteristics of multiscale self-similarity. According to the characteristics of the above seismic data, this paper proposes an unsupervised noise suppression method for deep network seismic data based on prior information constraints. Inspired by the deep image prior (DIP), the structure of the neural network can be regarded as a kind of particular implicit prior information. The reasonable design of network structure can improve the ability of multiscale self-similarity feature extraction. Because of the multiscale self-similarity of the useful signals of pre-stack seismic imaging gather data and post-stack seismic imaging data but noise without this characteristic, the network with specific structure can extract the useful signals from the original data, so as to achieve the goal of noise suppression. The application results of pre-stack imaging gathers and post-stack imaging data show that the proposed method has good fidelity and robustness. In addition, due to its strong feature extraction ability, the proposed method also has a good effect on arc-like imaging noise not easy to suppress by conventional methods.


unsupervised learning, neural network, arc-like imaging noise, imaging gathers, multiscale similarity




[1] TRICKETT S. F-xy Cadzow noise suppression[C]//SEG Technical Program Expanded Abstracts 2008. Society of Exploration Geophysicists,2008:2586-2590.

[2] SOUBARAS R. Signal-preserving random noise attenuation by the f-x projection[C]//SEG Technical Program Expanded Abstracts,Jan. 1994:1576-1579.

[3] TRICKETT S R. F-xy eigenimage noise suppression[J]. Geophysics,2003,68(2):751-759.

[4] BEKARA M,BAAN VAN DER M. Local singular value decomposition for signal enhancement of seismic data[J]. Geophysics,2007,72(2):59-65.

[5] OROPEZA V,SACCHI M. Simultaneous seismic data denoising and reconstruction via multichannel singular spectrum analysis[J]. Geophysics,2011,76(3):25-32.

[6] KREIMER N,SACCHI M D. A tensor higher-order singular value decomposition for pre-stack seismic data noise reduction and interpolation[J]. Geophysics,2012,77(3):113-122.

[7] YU Z,ABMA R,ETGEN J,et al. Attenuation of noise and simultaneous source interference using wavelet denoising[J]. Geophysics,2017,82(3):179-190.

[8] WANG Xiaojing,MA Jianwei. Adaptive dictionary learning for blind seismic data denoising[J]. IEEE Geoscience and Remote Sensing Letters,2019:1-5.

[9] WANG Shen,LI Jianchao,CHIU S K,et al. Seismic data compression and regularization via wave packets[C]//SEG Technical Program Expanded Abstracts 2010.2010:3650-3655.

[10] ZHANG Yinxue,TIAN Xuemin,DENG Xiaogang,et al. Seismic denoising based on modified BP neural network[C]//2010 Sixth International Conference on Natural Computation. 2010:1825-1829.

[11] WANG Enning,NEALON J. Applying machine learning to 3D seismic image denoising and enhancement[J]. Interpretation,2019,7(3):131-139.

[12] LIU Dawei,WANG Wei,WANG Xiaokai,et al. Poststack seismic data denoising based on 3-D convolutional neural network[J]. IEEE Trans. Geosci. Remote Sens.,2020,58(3):1598-1629.

[13] CHEN Yangkang,ZHANG Mi,BAI Min,et al. Improving the signal-to-noise ratio of seismological datasets by unsupervised machine learning[J]. Seismol. Res. Lett.,2019,90(4):1552-1564.

[14] ULYANOV D,VEDALDI A,LEMPITSKY V. Deep image prior[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018:9446-9454[2020-03-19].

[15] HERRMANN F J,WANG DeLi,HENNENFENT G,et al. Curvelet-based seismic data processing:A multiscale and nonlinear approach[J]. Geophysics,2008,73(1):1-5.

[16] BUNKS C,SALECKF M,ZALESKI S,et al. Multiscale seismic waveform inversion[J]. Geophysics,1995,60(5):1457-1473.

[17] XU Z-Q J. Frequency principle:Fourier analysis sheds light on deep neural networks[J]. Commun. Comput. Phys.,2020,28(5):1746-1767.

[18] LIANG Jianwei,MA Jianwei,ZHANG Xiaoqun. Seismic data restoration via data-driven tight frame[J]. Geophysics,2014,79(3):65-74.



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.