Coherent Noise Suppression Via a Self-Supervised Deep Learning Scheme

dc.conference.dateJune 6-9, 2021
dc.conference.locationMadrid / Online
dc.conference.name83rd EAGE Annual Conference & Exhibition
dc.contributor.authorLiu, S.
dc.contributor.authorBirnie, Claire Emma
dc.contributor.authorAlkhalifah, Tariq Ali
dc.contributor.departmentAli I. Al-Naimi Petroleum Engineering Research Center (ANPERC)
dc.contributor.departmentEarth Science and Engineering Program
dc.contributor.departmentPhysical Science and Engineering (PSE) Division
dc.contributor.departmentSeismic Wave Analysis Group
dc.date.accessioned2022-05-30T08:56:49Z
dc.date.available2022-05-30T08:56:49Z
dc.date.issued2022
dc.description.abstractCoherent noise attenuation is an essential step in seismic data processing to improve data quality and signal-to-noise ratio. The use of deep learning based approaches for noise suppression has grown throughout the last five years due to neural networks strength in pattern recognition tasks and their low computation cost, i.e. fast application during the inference stage. A limitation of the majority of such procedures is their requirement for noisy-clean pairs of data for training. Here, we propose the use of self-supervised procedure, namely, Structured Noise2Void, which has no such requirements. Through the inclusion of a noise mask, the coherency of noise is suppressed by randomising the noise, allowing the network to learn how to predict only the signal component of a sample’s value. Numerical experiments on synthetic and field seismic data demonstrate that our method can effectively attenuate trace-wise coherent noise. In the synthetic example, noise was injected into ten random traces, which showed no notable indication of their previously noisy state after denoising. In the field data, some locations already exhibited trace-wise coherent noise. After application of the trained network, the noise on these traces was drastically reduced resulting in a notable continuation in the seismic wave’s first arrival.
dc.eprint.versionPre-print
dc.identifier.arxivid2206.00301
dc.identifier.citationLiu, S., Birnie, C., & Alkhalifah, T. (2022). Coherent Noise Suppression Via a Self-Supervised Deep Learning Scheme. 83rd EAGE Annual Conference & Exhibition. https://doi.org/10.3997/2214-4609.202210382
dc.identifier.doi10.3997/2214-4609.202210382
dc.identifier.urihttp://hdl.handle.net/10754/678319
dc.publisherEuropean Association of Geoscientists & Engineers
dc.relation.urlhttps://www.earthdoc.org/content/papers/10.3997/2214-4609.202210382
dc.rightsArchived with thanks to European Association of Geoscientists & Engineers
dc.titleCoherent Noise Suppression Via a Self-Supervised Deep Learning Scheme
dc.typeConference Paper
display.details.left<span><h5>Type</h5>Conference Paper<br><br><h5>Authors</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.author=Liu, S.,equals">Liu, S.</a><br><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.author=Birnie, Claire Emma,equals">Birnie, Claire Emma</a><br><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0002-9363-9799&spc.sf=dc.date.issued&spc.sd=DESC">Alkhalifah, Tariq Ali</a> <a href="https://orcid.org/0000-0002-9363-9799" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br><br><h5>KAUST Department</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.department=Ali I. Al-Naimi Petroleum Engineering Research Center (ANPERC),equals">Ali I. Al-Naimi Petroleum Engineering Research Center (ANPERC)</a><br><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.department=Earth Science and Engineering Program,equals">Earth Science and Engineering Program</a><br><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.department=Physical Science and Engineering (PSE) Division,equals">Physical Science and Engineering (PSE) Division</a><br><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.department=Seismic Wave Analysis Group,equals">Seismic Wave Analysis Group</a><br><br><h5>Date</h5>2022</span>
display.details.right<span><h5>Abstract</h5>Coherent noise attenuation is an essential step in seismic data processing to improve data quality and signal-to-noise ratio. The use of deep learning based approaches for noise suppression has grown throughout the last five years due to neural networks strength in pattern recognition tasks and their low computation cost, i.e. fast application during the inference stage. A limitation of the majority of such procedures is their requirement for noisy-clean pairs of data for training. Here, we propose the use of self-supervised procedure, namely, Structured Noise2Void, which has no such requirements. Through the inclusion of a noise mask, the coherency of noise is suppressed by randomising the noise, allowing the network to learn how to predict only the signal component of a sample’s value. Numerical experiments on synthetic and field seismic data demonstrate that our method can effectively attenuate trace-wise coherent noise. In the synthetic example, noise was injected into ten random traces, which showed no notable indication of their previously noisy state after denoising. In the field data, some locations already exhibited trace-wise coherent noise. After application of the trained network, the noise on these traces was drastically reduced resulting in a notable continuation in the seismic wave’s first arrival.<br><br><h5>Citation</h5>Liu, S., Birnie, C., & Alkhalifah, T. (2022). Coherent Noise Suppression Via a Self-Supervised Deep Learning Scheme. 83rd EAGE Annual Conference & Exhibition. https://doi.org/10.3997/2214-4609.202210382<br><br><h5>Publisher</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.publisher=European Association of Geoscientists & Engineers,equals">European Association of Geoscientists & Engineers</a><br><br><h5>Conference/Event Name</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.conference=83rd EAGE Annual Conference & Exhibition,equals">83rd EAGE Annual Conference & Exhibition</a><br><br><h5>DOI</h5><a href="https://doi.org/10.3997/2214-4609.202210382">10.3997/2214-4609.202210382</a><br><br><h5>arXiv</h5><a href="https://arxiv.org/abs/2206.00301">2206.00301</a><br><br><h5>Additional Links</h5>https://www.earthdoc.org/content/papers/10.3997/2214-4609.202210382</span>
kaust.personLiu, S.
kaust.personBirnie, Claire Emma
kaust.personAlkhalifah, Tariq Ali
orcid.authorLiu, S.
orcid.authorBirnie, Claire Emma
orcid.authorAlkhalifah, Tariq Ali::0000-0002-9363-9799
orcid.id0000-0002-9363-9799
Files