Seismic noise attenuation via convolution neural network with learningnoise prior

The presence of noise degrades the quality of seismic data and makes the subsequent processing tasks and interpretation more challenging. Therefore, seismic noise attenuation is a key step in the processing of seismic data. We propose a novel convolutional neural network (CNN) framework with learning noise prior. Unlike conventional CNN-based seismic denoising methods, this new network is composed of a noise extractor and a denoiser. The noise extractor extracts noise from the original data to provide a high-precision noise prior to the denoising process. The denoiser uses the noise prior for denoising of the seismic data. This method is superior to the presently used networks in terms of the denoising effect. Additionally, the proposed network can be applied for random noise suppression as well as coherent noise attenuation. Synthetic and field tests illustrated the superiority of the proposed approach over the traditional denoising methods in suppressing noise and improving the signal-to-noise ratio (SNR) of seismic data.

[1]  Weilin Huang,et al.  Simultaneous denoising and reconstruction of 5-D seismic data via damped rank-reduction method , 2016 .

[2]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[3]  Mauricio D. Sacchi,et al.  A fast reduced-rank interpolation method for prestack seismic volumes that depend on four spatial dimensions , 2013 .

[4]  Sergey Fomel,et al.  Seismic data analysis using local time‐frequency decomposition , 2013 .

[5]  J. Ma.  Deep Learning for Attenuating Random and Coherence Noise Simultaneously , 2018, 80th EAGE Conference and Exhibition 2018.

[6]  Mauricio D. Sacchi,et al.  Interpolation and denoising of high-dimensional seismic data by learning a tight frame , 2015 .

[7]  J. Welford,et al.  Ground-roll suppression from deep crustal seismic reflection data using a wavelet-based approach: A case study from western Canada , 2004 .

[8]  T. Ulrych,et al.  Physical Wavelet Frame Denoising , 2003 .

[9]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[10]  M. Sacchi,et al.  Simultaneous seismic data denoising and reconstruction via multichannel singular spectrum analysis , 2011 .

[11]  Felix J. Herrmann,et al.  Seismic denoising with nonuniformly sampled curvelets , 2006, Computing in Science & Engineering.

[12]  Robert B. Herrmann,et al.  Ground roll; rejection using adaptive phase-matched filters , 1990 .

[13]  R. Wiggins,et al.  CHARACTERISTICS OF OPTIMUM MULTICHANNEL STACKING FILTERS , 1968 .

[14]  Stefano Parolai,et al.  Denoising of Seismograms Using the S Transform , 2009 .

[15]  A. Bruckstein,et al.  K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation , 2005 .

[16]  Yue Li,et al.  Low-Frequency Noise Suppression Method Based on Improved DnCNN in Desert Seismic Data , 2019, IEEE Geoscience and Remote Sensing Letters.

[17]  Jianwei Ma,et al.  Seismic data denoising based on learning-type overcomplete dictionaries , 2012, Applied Geophysics.

[18]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[19]  Yang Liu,et al.  Seislet transform and seislet frame , 2010 .

[20]  Lynn Burroughs,et al.  Rank-Reduction-Based Trace Interpolation , 2010 .

[21]  Gilberto Corso,et al.  Seismic ground roll time–frequency filtering using the gaussian wavelet transform , 2003 .

[22]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[23]  Jingjing Zheng,et al.  The surface wave suppression using the second generation curvelet transform , 2010 .

[24]  Stewart Trickett,et al.  F-xy Cadzow Noise Suppression , 2008 .

[25]  Nadia Kreimer,et al.  A tensor higher-order singular value decomposition for prestack seismic data noise reduction and interpolation , 2012 .

[26]  Hamid Reza Siahkoohi,et al.  Ground roll attenuation using the S and x‐f‐k transforms , 2007 .

[27]  James H. McClellan,et al.  Seismic data denoising through multiscale and sparsity-promoting dictionary learning , 2015 .