Skip to Main Content
Skip Nav Destination
GEOREF RECORD

Deep learning denoising applied to regional distance seismic data in Utah

Rigobert Tibi, Patrick Hammond, Ronald Brogan, Christopher J. Young and Keith Koper
Deep learning denoising applied to regional distance seismic data in Utah
Bulletin of the Seismological Society of America (January 2021) 111 (2): 775-790

Abstract

Seismic waveform data are generally contaminated by noise from various sources. Suppressing this noise effectively so that the remaining signal of interest can be successfully exploited remains a fundamental problem for the seismological community. To date, the most common noise suppression methods have been based on frequency filtering. These methods, however, are less effective when the signal of interest and noise share similar frequency bands. Inspired by source separation studies in the field of music information retrieval (Jansson et al., 2017) and a recent study in seismology (Zhu et al., 2019), we implemented a seismic denoising method that uses a trained deep convolutional neural network (CNN) model to decompose an input waveform into a signal of interest and noise. In our approach, the CNN provides a signal mask and a noise mask for an input signal. The short-time Fourier transform (STFT) of the estimated signal is obtained by multiplying the signal mask with the STFT of the input signal. To build and test the denoiser, we used carefully compiled signal and noise datasets of seismograms recorded by the University of Utah Seismograph Stations network. Results of test runs involving more than 9000 constructed waveforms suggest that on average the denoiser improves the signal-to-noise ratios (SNRs) by approximately 5dB, and that most of the recovered signal waveforms have high similarity with respect to the target waveforms (average correlation coefficient of approximately 0.80) and suffer little distortion. Application to real data suggests that our denoiser achieves on average a factor of up to approximately 2-5 improvement in SNR over band-pass filtering and can suppress many types of noise that band-pass filtering cannot. For individual waveforms, the improvement can be as high as approximately 15dB.


ISSN: 0037-1106
EISSN: 1943-3573
Coden: BSSAAP
Serial Title: Bulletin of the Seismological Society of America
Serial Volume: 111
Serial Issue: 2
Title: Deep learning denoising applied to regional distance seismic data in Utah
Affiliation: Sandia National Laboratories, Albuquerque, NM, United States
Pages: 775-790
Published: 20210119
Text Language: English
Publisher: Seismological Society of America, Berkeley, CA, United States
References: 61
Accession Number: 2021-024405
Categories: Seismology
Document Type: Serial
Bibliographic Level: Analytic
Illustration Description: illus.
N37°00'00" - N42°00'00", W114°04'60" - W109°04'60"
Secondary Affiliation: University of Utah, USA, United States
Country of Publication: United States
Secondary Affiliation: GeoRef, Copyright 2022, American Geosciences Institute. Abstract, Copyright, Seismological Society of America. Reference includes data from GeoScienceWorld, Alexandria, VA, United States
Update Code: 202117
Close Modal

or Create an Account

Close Modal
Close Modal