ABSTRACT
We have developed convolutional sparse coding (CSC) to attenuate noise in seismic data. CSC gives a data-driven set of basis functions whose coefficients form a sparse distribution. The noise attenuation method by CSC can be divided into the training and denoising phases. Seismic data with a relatively high signal-to-noise ratio are chosen for training to get the learned basis functions. Then, we use all (or a subset) of the basis functions to attenuate the random or coherent noise in the seismic data. Numerical experiments on synthetic data show that CSC can learn a set of shifted invariant filters, which can reduce the redundancy of learned filters in the traditional sparse-coding denoising method. CSC achieves good denoising performance when training with the noisy data and better performance when training on a similar but noiseless data set. The numerical results from the field data test indicate that CSC can effectively suppress seismic noise in complex field data. By excluding filters with coherent noise features, our method can further attenuate coherent noise and separate ground roll.
REFERENCES
- , 2019, Fast and accurate dictionary learning for seismic data denoising using convolutional sparse coding:
89th Annual International Meeting, SEG , Expanded Abstracts,4645–4649 , doi:10.1190/segam2019-3215814.1 . - , 2014, Simultaneous dictionary learning and denoising for seismic data: Geophysics, 79, no. 3,
A27–A31 , doi:10.1190/geo2013-0382.1 .GPYSA7 0016-8033 - , 2009, Random and coherent noise attenuation by empirical mode decomposition: Geophysics, 74, no. 5,
V89–V98 , doi:10.1190/1.3157244 .GPYSA7 0016-8033 - , 2012, Denoising seismic data using the nonlocal means algorithm: Geophysics, 77, no. 1,
A5–A8 , doi:10.1190/geo2011-0235.1 .GPYSA7 0016-8033 - , 2011, Distributed optimization and statistical learning via the alternating direction method of multipliers: Foundations and Trends® in Machine learning, 3,
1–122 , doi:10.1561/2200000016 . - , 2013, Fast convolutional sparse coding:
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , IEEE,391–398 . - , 2002, An approach to seismic correction which includes wavelet de-noising:
Proceedings of the Sixth Conference on Computational Structures Technology , Civil-Comp Press,107–108 . - , 2016, Dip-separated structural filtering using seislet transform and adaptive empirical mode decomposition based dip filter: Geophysical Journal International, 206,
457–469 , doi:10.1093/gji/ggw165 .GJINEA 0956-540X - , 2016, Double-sparsity dictionary for seismic noise attenuation: Geophysics, 81, no. 2,
V103–V116 , doi:10.1190/geo2014-0525.1 .GPYSA7 0016-8033 - , 2017, Consensus convolutional sparse coding:
Proceedings of the IEEE International Conference on Computer Vision ,4280–4288 . - , 2006, Image denoising via sparse and redundant representations over learned dictionaries: IEEE Transactions on Image Processing, 15,
3736–3745 , doi:10.1109/TIP.2006.881969 .IIPRE4 1057-7149 - , 2015, Convolutional sparse coding for image super-resolution:
Proceedings of the IEEE International Conference on Computer Vision ,1823–1831 . - , 2002, Coherent noise attenuation using inverse problems and prediction-error filters: First Break, 20,
161–167 , doi:10.1046/j.1365-2397.2002.00246.x . - , 2015, Fast and flexible convolutional sparse coding:
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition ,5135–5143 . - , 2006, Seismic denoising with nonuniformly sampled curvelets: Computing in Science Engineering, 8,
16–25 , doi:10.1109/MCSE.2006.49 . - , 2014, Eliminating blending noise using fast apex shifted hyperbolic radon transform:
76th Conference and Exhibition , EAGE, Extended Abstracts, doi:10.3997/2214-4609.20141455 . - , 2017, Learning the morphology of brain signals using alpha-stable convolutional sparse coding:
Advances in Neural Information Processing Systems ,1099–1108 . - , 2009, Sparse coding for data-driven coherent and incoherent noise attenuation:
79th Annual International Meeting, SEG , Expanded Abstracts,3327–3331 , doi:10.1190/1.3255551 . - , 2018, An unsupervised learning method for residual seismic signal recovery:
88th Annual International Meeting, SEG , Expanded Abstracts,1996–2000 , doi:10.1190/segam2018-2996280.1 . - , 2019, Wave equation dispersion inversion of love waves: Geophysics, 84, no. 5,
R693–R705 , doi:10.1190/geo2018-0039.1 .GPYSA7 0016-8033 - , 2020, Seismic data denoising based on sparse and low-rank regularization: Energies, 13,
372 , doi:10.3390/en13020372 .NRGSDB 0165-2117 - , 2011, Seismic noise attenuation using nonstationary polynomial fitting: Applied Geophysics, 8,
18–26 , doi:10.1007/s11770-010-0244-2 . - , 2020, Deep convolutional neural network and sparse least squares migration: Geophysics, 85, no. 4,
WA241–WA253 , doi:10.1190/geo2019-0412.1 .GPYSA7 0016-8033 - , 2019, 3D wave-equation dispersion inversion of Rayleigh waves: Geophysics, 84, no. 5,
R673–R691 , doi:10.1190/geo2018-0543.1 .GPYSA7 0016-8033 - , 2019, Multilayer sparse LSM = deep neural network:
89th Annual International Meeting, SEG , Expanded Abstracts,2323–2327 , doi:10.1190/segam2019-3215033.1 . - , 2017a, Convolutional neural networks analyzed via convolutional sparse coding: Journal of Machine Learning Research, 18,
2887–2938 . - , 2017b, Convolutional dictionary learning via local processing:
Proceedings of the IEEE International Conference on Computer Vision ,5296–5304 . - , 2014, Proximal algorithms: Foundations and Trends in Optimization, 1, no. 3,
127–239 . - , 2017, Sparse convolutional coding for neuronal assembly detection:
Advances in Neural Information Processing Systems ,3675–3685 . - , 2016, Convolutional sparse coding for high dynamic range imaging:
Computer Graphics Forum , Wiley,153–163 . - , 2016, Boundary handling for convolutional sparse representations:
IEEE International Conference on Image Processing (ICIP) , IEEE,1833–1837 . - , 2019, Stochastic convolutional sparse coding: arXiv preprint arXiv:1909.00145.
- , 2001, Seismic data analysis: Processing, inversion, and interpretation of seismic data: SEG.
- , 2019, Deep learning for denoising: Geophysics, 84, no. 6,
V333–V350 , doi:10.1190/geo2018-0668.1 .GPYSA7 0016-8033 - , 2015, Seismic data denoising through multiscale and sparsity-promoting dictionary learning: Geophysics, 80, no. 6,
WD45–WD57 , doi:10.1190/geo2015-0047.1 .GPYSA7 0016-8033 - , 2019, A local block coordinate descent algorithm for the CSC model:
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition ,8208–8217 .
