Deep denoising autoencoder for seismic random noise attenuation

Attenuation of seismic random noise is considered an important processing step to enhance the signal-to-noise ratio of seismic data. A new approach is proposed to attenuate random noise based on a deep-denoising autoencoder (DDAE). In this approach, the time-series seismic data are used as an input for the DDAE. The DDAE encodes the input seismic data to multiple levels of abstraction, and then it decodes those levels to reconstruct the seismic signal without noise. The DDAE is pretrained in a supervised way using synthetic data; following this, the pretrained model is used to denoise the field data set in an unsupervised scheme using a new customized loss function. We have assessed the proposed algorithm based on four synthetic data sets and two field examples, and we compare the results with several benchmark algorithms, such as f- x deconvolution ( f- x deconv) and the f- x singular spectrum analysis ( f- x SSA). As a result, our algorithm succeeds in attenuating the random noise in an effective manner.

[1]  Min Bai,et al.  Obtaining free USArray data by multi-dimensional seismic reconstruction , 2019, Nature Communications.

[2]  Yang Liu,et al.  A 1D time-varying median filter for seismic random, spike-like noise elimination , 2009 .

[3]  Oz Yilmaz,et al.  Interpretive imaging of seismic data , 2001 .

[4]  Necati Gulunay,et al.  Noncausal spatial prediction filtering for random noise reduction on 3-D poststack data , 2000 .

[5]  Xiaohong Chen,et al.  Noncausal f–x–y regularized nonstationary prediction filtering for random noise attenuation on 3D seismic data , 2013 .

[6]  S. Mostafa Mousavi,et al.  Automatic microseismic denoising and onset detection using the synchrosqueezed continuous wavelet transform , 2016 .

[7]  Yangkang Chen,et al.  Damped multichannel singular spectrum analysis for 3D random noise attenuation , 2016 .

[8]  S LewMichael,et al.  Deep learning for visual understanding , 2016 .

[9]  Guang-Zhong Yang,et al.  Deep Learning for Health Informatics , 2017, IEEE Journal of Biomedical and Health Informatics.

[10]  Hui Zhou,et al.  Dictionary learning based on dip patch selection training for random noise attenuation , 2019, GEOPHYSICS.

[11]  Yurong Liu,et al.  A survey of deep neural network architectures and their applications , 2017, Neurocomputing.

[12]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[13]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[14]  Yangkang Chen,et al.  Random noise attenuation using local signal-and-noise orthogonalization , 2015 .

[15]  SchmidhuberJürgen.  Deep learning in neural networks , 2015 .

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

[17]  Yike Liu,et al.  Noise reduction by vector median filtering , 2013 .

[18]  Wei Chen,et al.  Random Noise Attenuation Based on Residual Convolutional Neural Network in Seismic Datasets , 2020, IEEE Access.

[19]  Jingwei Hu,et al.  Iterative deblending of simultaneous-source seismic data using seislet-domain shaping regularization , 2014 .

[20]  J. Claerbout,et al.  Lateral prediction for noise attenuation by t-x and f-x techniques , 1995 .

[21]  Guochang Liu,et al.  Random noise attenuation using f-x regularized nonstationary autoregression , 2012 .

[22]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  L. Canales.  Random Noise Reduction , 1984 .

[24]  Michael S. Lew,et al.  Deep learning for visual understanding: A review , 2016, Neurocomputing.

[25]  Hui Song,et al.  Automatic noise attenuation based on clustering and empirical wavelet transform , 2018, Journal of Applied Geophysics.

[26]  Yi Luo,et al.  Simultaneous sources separation via multidirectional vector-median filtering , 2012 .

[27]  Wei Chen,et al.  Recent Advancements in Empirical Wavelet Transform and Its Applications , 2019, IEEE Access.

[28]  Yangkang Chen,et al.  Separation of simultaneous sources using a structural-oriented median filter in the flattened dimension , 2016, Comput. Geosci..

[29]  Peng Jiang,et al.  Deep-Learning Inversion of Seismic Data , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[30]  Zachary E. Ross,et al.  P Wave Arrival Picking and First‐Motion Polarity Determination With Deep Learning , 2018, Journal of Geophysical Research: Solid Earth.

[31]  Yangkang Chen,et al.  Seismic Noise Attenuation Using Unsupervised Sparse Feature Learning , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[32]  Yangkang Chen,et al.  Simultaneous denoising and interpolation of 2D seismic data using data-driven non-negative dictionary learning , 2017, Signal Process..

[33]  S. Mostafa Mousavi,et al.  CRED: A Deep Residual Network of Convolutional and Recurrent Units for Earthquake Signal Detection , 2018, Scientific Reports.

[34]  Mauricio D. Sacchi,et al.  Multicomponent f-x seismic random noise attenuation via vector autoregressive operators , 2012 .

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

[36]  Sergey Fomel,et al.  Local seismic attributes , 2007 .

[37]  Yangkang Chen,et al.  Deep learning for seismic lithology prediction , 2018 .

[38]  S. Phinn,et al.  Australian vegetated coastal ecosystems as global hotspots for climate change mitigation , 2019, Nature Communications.