Convolutional Sparse Coding for Noise Attenuation of Seismic Data

Zhaolun Liu; Kai Lu; Xiaodan Ge

doi:10.1190/aiml2018-02.1

Convolutional Sparse Coding for Noise Attenuation of Seismic Data

Zhaolun Liu, Kai Lu, Xiaodan Ge

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Convolutional sparse coding (CSC) is proposed to attenuate noise for 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 phase and the denoising phase. The 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 and field data indicate that the proposed method achieves good performance for denoising random and coherent noise and separating the ground roll.

Original language	English (US)
Title of host publication	SEG 2018 Workshop: SEG Maximizing Asset Value Through Artificial Intelligence and Machine Learning, Beijing, China, 17-19 September 2018
Publisher	Society of Exploration Geophysicists and the Chinese Geophysical Society
DOIs	https://doi.org/10.1190/aiml2018-02.1
State	Published - Dec 14 2018

Access to Document

10.1190/aiml2018-02.1

Cite this

@inproceedings{a6f6869d53f34df7b924a629efcd37a1,

title = "Convolutional Sparse Coding for Noise Attenuation of Seismic Data",

abstract = "Convolutional sparse coding (CSC) is proposed to attenuate noise for 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 phase and the denoising phase. The 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 and field data indicate that the proposed method achieves good performance for denoising random and coherent noise and separating the ground roll.",

author = "Zhaolun Liu and Kai Lu and Xiaodan Ge",

note = "KAUST Repository Item: Exported on 2021-03-09 Acknowledgements: The research reported in this publication was supported by the King Abdullah University of Science and Technology (KAUST) in Thuwal, Saudi Arabia. We are grateful to the sponsors of the Center for Subsurface Imaging and Modeling Consortium for their ﬁnancial support. For computer time, this research used the resources of the Supercomputing Laboratory at KAUST and the IT Research Computing Group. We thank them forproviding the computational resources required for carryingout this work.",

year = "2018",

month = dec,

day = "14",

doi = "10.1190/aiml2018-02.1",

language = "English (US)",

booktitle = "SEG 2018 Workshop: SEG Maximizing Asset Value Through Artificial Intelligence and Machine Learning, Beijing, China, 17-19 September 2018",

publisher = "Society of Exploration Geophysicists and the Chinese Geophysical Society",

}

Convolutional Sparse Coding for Noise Attenuation of Seismic Data. / Liu, Zhaolun; Lu, Kai; Ge, Xiaodan.
SEG 2018 Workshop: SEG Maximizing Asset Value Through Artificial Intelligence and Machine Learning, Beijing, China, 17-19 September 2018. Society of Exploration Geophysicists and the Chinese Geophysical Society, 2018.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Convolutional Sparse Coding for Noise Attenuation of Seismic Data

AU - Liu, Zhaolun

AU - Lu, Kai

AU - Ge, Xiaodan

N1 - KAUST Repository Item: Exported on 2021-03-09 Acknowledgements: The research reported in this publication was supported by the King Abdullah University of Science and Technology (KAUST) in Thuwal, Saudi Arabia. We are grateful to the sponsors of the Center for Subsurface Imaging and Modeling Consortium for their ﬁnancial support. For computer time, this research used the resources of the Supercomputing Laboratory at KAUST and the IT Research Computing Group. We thank them forproviding the computational resources required for carryingout this work.

PY - 2018/12/14

Y1 - 2018/12/14

N2 - Convolutional sparse coding (CSC) is proposed to attenuate noise for 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 phase and the denoising phase. The 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 and field data indicate that the proposed method achieves good performance for denoising random and coherent noise and separating the ground roll.

AB - Convolutional sparse coding (CSC) is proposed to attenuate noise for 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 phase and the denoising phase. The 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 and field data indicate that the proposed method achieves good performance for denoising random and coherent noise and separating the ground roll.

UR - http://hdl.handle.net/10754/667944

UR - https://library.seg.org/doi/10.1190/AIML2018-02.1

U2 - 10.1190/aiml2018-02.1

DO - 10.1190/aiml2018-02.1

M3 - Conference contribution

BT - SEG 2018 Workshop: SEG Maximizing Asset Value Through Artificial Intelligence and Machine Learning, Beijing, China, 17-19 September 2018

PB - Society of Exploration Geophysicists and the Chinese Geophysical Society

ER -

Convolutional Sparse Coding for Noise Attenuation of Seismic Data

Abstract

Access to Document

Other files and links

Fingerprint

Cite this