Cover Image

Deep learning application in time-frequency analysis for noise attenuation

Time- frequency analysis of seismic data has been proven to be a reliable method for noise attenuation. Differentiation between the noise and signal energy is traditionally done by thresholding the coefficients, keeping the stronger values as they are assumed to be representing the signals, while ze...

Full description

Saved in:
Bibliographic Details
Main Author: Hamidi, R.
Format: Conference or Workshop Item
Published: European Association of Geoscientists and Engineers, EAGE 2019
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85093873287&doi=10.3997%2f2214-4609.201977037&partnerID=40&md5=920cbc4a9c5bda77f15b94729e261c68
http://eprints.utp.edu.my/30182/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utp.eprints.30182
record_format eprints
spelling my.utp.eprints.301822022-03-25T06:36:16Z Deep learning application in time-frequency analysis for noise attenuation Hamidi, R. Time- frequency analysis of seismic data has been proven to be a reliable method for noise attenuation. Differentiation between the noise and signal energy is traditionally done by thresholding the coefficients, keeping the stronger values as they are assumed to be representing the signals, while zeroing out the noise energy. Despite its effectiveness, this is a timely procedure and needs the user's interaction for each seismic survey. Considering the growing success of the deep learning in image and signal processing, it is used in this paper to estimate the signal coefficients of the trace in the time-frequency plane. As the continuous wavelet transform is a successful method for time-frequency analysis of the seismic data, it has been used in this study to calculate the two dimensional input for the deep learning. To enable the network to focus on attenuation of the random noise and not simply modeling the signals in a specific geological setting, traces from three different datasets have been used for training the network. Testing the final network with traces not used for training shows promising results as it can conveniently attenuate the noise energy compared to the traditional method. © EAGE 2019. European Association of Geoscientists and Engineers, EAGE 2019 Conference or Workshop Item NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85093873287&doi=10.3997%2f2214-4609.201977037&partnerID=40&md5=920cbc4a9c5bda77f15b94729e261c68 Hamidi, R. (2019) Deep learning application in time-frequency analysis for noise attenuation. In: UNSPECIFIED. http://eprints.utp.edu.my/30182/
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Institutional Repository
url_provider http://eprints.utp.edu.my/
description Time- frequency analysis of seismic data has been proven to be a reliable method for noise attenuation. Differentiation between the noise and signal energy is traditionally done by thresholding the coefficients, keeping the stronger values as they are assumed to be representing the signals, while zeroing out the noise energy. Despite its effectiveness, this is a timely procedure and needs the user's interaction for each seismic survey. Considering the growing success of the deep learning in image and signal processing, it is used in this paper to estimate the signal coefficients of the trace in the time-frequency plane. As the continuous wavelet transform is a successful method for time-frequency analysis of the seismic data, it has been used in this study to calculate the two dimensional input for the deep learning. To enable the network to focus on attenuation of the random noise and not simply modeling the signals in a specific geological setting, traces from three different datasets have been used for training the network. Testing the final network with traces not used for training shows promising results as it can conveniently attenuate the noise energy compared to the traditional method. © EAGE 2019.
format Conference or Workshop Item
author Hamidi, R.
spellingShingle Hamidi, R.
Deep learning application in time-frequency analysis for noise attenuation
author_facet Hamidi, R.
author_sort Hamidi, R.
title Deep learning application in time-frequency analysis for noise attenuation
title_short Deep learning application in time-frequency analysis for noise attenuation
title_full Deep learning application in time-frequency analysis for noise attenuation
title_fullStr Deep learning application in time-frequency analysis for noise attenuation
title_full_unstemmed Deep learning application in time-frequency analysis for noise attenuation
title_sort deep learning application in time-frequency analysis for noise attenuation
publisher European Association of Geoscientists and Engineers, EAGE
publishDate 2019
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85093873287&doi=10.3997%2f2214-4609.201977037&partnerID=40&md5=920cbc4a9c5bda77f15b94729e261c68
http://eprints.utp.edu.my/30182/
_version_ 1738657071609413632
score 13.211869

Similar Items