Convolutional sparse coding for noise attenuation in seismic data
dc.contributor.author | Liu, Zhaolun | |
dc.contributor.author | Lu, Kai | |
dc.date.accessioned | 2021-02-07T08:57:44Z | |
dc.date.available | 2021-02-07T08:57:44Z | |
dc.date.issued | 2021-01-04 | |
dc.date.submitted | 2019-11-17 | |
dc.identifier.citation | Liu, Z., & Lu, K. (2021). Convolutional sparse coding for noise attenuation in seismic data. GEOPHYSICS, 86(1), V23–V30. doi:10.1190/geo2019-0746.1 | |
dc.identifier.issn | 0016-8033 | |
dc.identifier.issn | 1942-2156 | |
dc.identifier.doi | 10.1190/geo2019-0746.1 | |
dc.identifier.uri | http://hdl.handle.net/10754/667240 | |
dc.description.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. | |
dc.description.sponsorship | 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 for providing the computational resources required for carrying out this work. | |
dc.publisher | Society of Exploration Geophysicists | |
dc.relation.url | http://mr.crossref.org/iPage?doi=10.1190%2Fgeo2019-0746.1 | |
dc.rights | Archived with thanks to GEOPHYSICS | |
dc.title | Convolutional sparse coding for noise attenuation in seismic data | |
dc.type | Article | |
dc.contributor.department | Earth Science and Engineering Program | |
dc.contributor.department | Physical Science and Engineering (PSE) Division | |
dc.identifier.journal | GEOPHYSICS | |
dc.eprint.version | Post-print | |
dc.identifier.volume | 86 | |
dc.identifier.issue | 1 | |
dc.identifier.pages | V23-V30 | |
kaust.person | Liu, Zhaolun | |
kaust.person | Lu, Kai | |
dc.date.accepted | 2020-08-16 | |
refterms.dateFOA | 2021-02-08T05:44:48Z | |
kaust.acknowledged.supportUnit | Center for Subsurface Imaging and Modeling Consortium | |
kaust.acknowledged.supportUnit | IT Research Computing Group | |
kaust.acknowledged.supportUnit | Supercomputing Laboratory at KAUST |
Files in this item
This item appears in the following Collection(s)
-
Articles
-
Physical Science and Engineering (PSE) Division
For more information visit: http://pse.kaust.edu.sa/ -
Earth Science and Engineering Program
For more information visit: https://pse.kaust.edu.sa/study/academic-programs/earth-science-and-engineering/Pages/home.aspx