Toward improved urban earthquake monitoring through deep-learning-based noise suppression
Abstract
Earthquake monitoring in urban settings is essential but challenging, due to the strong anthropogenic noise inherent to urban seismic recordings. Here, we develop a deep-learning-based denoising algorithm, UrbanDenoiser, to filter out urban seismological noise. UrbanDenoiser strongly suppresses noise relative to the signals, because it was trained using waveform datasets containing rich noise sources from the urban Long Beach dense array and high signal-to-noise ratio (SNR) earthquake signals from the rural San Jacinto dense array. Application to the dense array data and an earthquake sequence in an urban area shows that UrbanDenoiser can increase signal quality and recover signals at an SNR level down to ~0 dB. Earthquake location using our denoised Long Beach data does not support the presence of mantle seismicity beneath Los Angeles but suggests a fault model featuring shallow creep, intermediate locking, and localized stress concentration at the base of the seismogenic zone.
- Authors:
-
[1];
[2];
[4];
[3]
- Stanford Univ., CA (United States); Chinese Academy of Sciences (CAS), Beijing (China)
- Stanford Univ., CA (United States); JAMSTEC/YES, Yokohama (Japan)
- Stanford Univ., CA (United States)
- Chinese Academy of Sciences (CAS), Beijing (China)
- Publication Date:
- Research Org.:
- Stanford Univ., CA (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Basic Energy Sciences (BES); National Natural Science Foundation of China (NSFC)
- OSTI Identifier:
- 1972029
- Alternate Identifier(s):
- OSTI ID: 1904283; OSTI ID: 2267584
- Grant/Contract Number:
- SC0020445; 41888101; 41625016; 41904060
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Science Advances
- Additional Journal Information:
- Journal Volume: 8; Journal Issue: 15; Journal ID: ISSN 2375-2548
- Publisher:
- AAAS
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 58 GEOSCIENCES; Earthquakes; Denoising; Machine learning; Seismicity
Citation Formats
Yang, Lei, Liu, Xin, Zhu, Weiqiang, Zhao, Liang, and Beroza, Gregory C. Toward improved urban earthquake monitoring through deep-learning-based noise suppression. United States: N. p., 2022.
Web. doi:10.1126/sciadv.abl3564.
Yang, Lei, Liu, Xin, Zhu, Weiqiang, Zhao, Liang, & Beroza, Gregory C. Toward improved urban earthquake monitoring through deep-learning-based noise suppression. United States. https://doi.org/10.1126/sciadv.abl3564
Yang, Lei, Liu, Xin, Zhu, Weiqiang, Zhao, Liang, and Beroza, Gregory C. Wed .
"Toward improved urban earthquake monitoring through deep-learning-based noise suppression". United States. https://doi.org/10.1126/sciadv.abl3564. https://www.osti.gov/servlets/purl/1972029.
@article{osti_1972029,
title = {Toward improved urban earthquake monitoring through deep-learning-based noise suppression},
author = {Yang, Lei and Liu, Xin and Zhu, Weiqiang and Zhao, Liang and Beroza, Gregory C.},
abstractNote = {Earthquake monitoring in urban settings is essential but challenging, due to the strong anthropogenic noise inherent to urban seismic recordings. Here, we develop a deep-learning-based denoising algorithm, UrbanDenoiser, to filter out urban seismological noise. UrbanDenoiser strongly suppresses noise relative to the signals, because it was trained using waveform datasets containing rich noise sources from the urban Long Beach dense array and high signal-to-noise ratio (SNR) earthquake signals from the rural San Jacinto dense array. Application to the dense array data and an earthquake sequence in an urban area shows that UrbanDenoiser can increase signal quality and recover signals at an SNR level down to ~0 dB. Earthquake location using our denoised Long Beach data does not support the presence of mantle seismicity beneath Los Angeles but suggests a fault model featuring shallow creep, intermediate locking, and localized stress concentration at the base of the seismogenic zone.},
doi = {10.1126/sciadv.abl3564},
journal = {Science Advances},
number = 15,
volume = 8,
place = {United States},
year = {Wed Apr 13 00:00:00 EDT 2022},
month = {Wed Apr 13 00:00:00 EDT 2022}
}
Free Publicly Available Full Text
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Machine Learning in Seismology: Turning Data into Insights
journal, November 2018
- Kong, Qingkai; Trugman, Daniel T.; Ross, Zachary E.
- Seismological Research Letters, Vol. 90, Issue 1
Deep learning of aftershock patterns following large earthquakes
journal, August 2018
- DeVries, Phoebe M. R.; Viégas, Fernanda; Wattenberg, Martin
- Nature, Vol. 560, Issue 7720
Earthquake Monitoring in Southern California for Seventy-Seven Years (1932-2008)
journal, March 2010
- Hutton, K.; Woessner, J.; Hauksson, E.
- Bulletin of the Seismological Society of America, Vol. 100, Issue 2
Deep learning
journal, May 2015
- LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
- Nature, Vol. 521, Issue 7553
The Seismogenic Thickness of the Southern California Crust
journal, June 2004
- Nazareth, J. J.
- Bulletin of the Seismological Society of America, Vol. 94, Issue 3
Characteristics of Ground Motion Generated by Wind Interaction With Trees, Structures, and Other Surface Obstacles
journal, August 2019
- Johnson, Christopher W.; Meng, Haoran; Vernon, Frank
- Journal of Geophysical Research: Solid Earth
Reliable Real‐Time Seismic Signal/Noise Discrimination With Machine Learning
journal, January 2019
- Meier, Men‐Andrin; Ross, Zachary E.; Ramachandran, Anshul
- Journal of Geophysical Research: Solid Earth, Vol. 124, Issue 1
Localized seismic deformation in the upper mantle revealed by dense seismic arrays
journal, October 2016
- Inbal, A.; Ampuero, J. P.; Clayton, R. W.
- Science, Vol. 354, Issue 6308
High-resolution seismic event detection using local similarity for Large-N arrays
journal, January 2018
- Li, Zefeng; Peng, Zhigang; Hollis, Dan
- Scientific Reports, Vol. 8, Issue 1
Deep fault plane geometry inferred from multiplet relative relocation beneath the south flank of Kilauea
journal, January 1994
- Got, J. -L.; Fréchet, J.; Klein, Fred W.
- Journal of Geophysical Research, Vol. 99, Issue B8
Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking
journal, August 2020
- Mousavi, S. Mostafa; Ellsworth, William L.; Zhu, Weiqiang
- Nature Communications, Vol. 11, Issue 1
A comparison of earthquake backprojection imaging methods for dense local arrays
journal, December 2017
- Beskardes, G. D.; Hole, J. A.; Wang, K.
- Geophysical Journal International, Vol. 212, Issue 3
The Use of Wavelet-Based Denoising Techniques to Enhance the First-Arrival Picking on Seismic Traces
journal, August 2014
- Gaci, Said
- IEEE Transactions on Geoscience and Remote Sensing, Vol. 52, Issue 8
Basic data features and results from a spatially dense seismic array on the San Jacinto fault zone
journal, May 2015
- Ben-Zion, Yehuda; Vernon, Frank L.; Ozakin, Yaman
- Geophysical Journal International, Vol. 202, Issue 1
A Double-Difference Earthquake Location Algorithm: Method and Application to the Northern Hayward Fault, California
journal, December 2000
- Waldhauser, F.
- Bulletin of the Seismological Society of America, Vol. 90, Issue 6
PhaseLink: A Deep Learning Approach to Seismic Phase Association
journal, January 2019
- Ross, Zachary E.; Yue, Yisong; Meier, Men‐Andrin
- Journal of Geophysical Research: Solid Earth, Vol. 124, Issue 1
Automatic microseismic denoising and onset detection using the synchrosqueezed continuous wavelet transform
journal, July 2016
- Mousavi, S. Mostafa; Langston, Charles A.; Horton, Stephen P.
- GEOPHYSICS, Vol. 81, Issue 4
Detection of random noise and anatomy of continuous seismic waveforms in dense array data near Anza California
journal, July 2019
- Meng, Haoran; Ben-Zion, Yehuda; Johnson, Christopher W.
- Geophysical Journal International, Vol. 219, Issue 3
Denoising seismic data using the nonlocal means algorithm
journal, January 2012
- Bonar, David; Sacchi, Mauricio
- GEOPHYSICS, Vol. 77, Issue 1
Convolutional neural network for earthquake detection and location
journal, February 2018
- Perol, Thibaut; Gharbi, Michaël; Denolle, Marine
- Science Advances, Vol. 4, Issue 2
Seismic Signal Denoising and Decomposition Using Deep Neural Networks
journal, November 2019
- Zhu, Weiqiang; Mousavi, S. Mostafa; Beroza, Gregory C.
- IEEE Transactions on Geoscience and Remote Sensing, Vol. 57, Issue 11
Revisiting evidence for widespread seismicity in the upper mantle under Los Angeles
journal, January 2021
- Yang, Lei; Liu, Xin; Beroza, Gregory C.
- Science Advances, Vol. 7, Issue 4
Unified Structural Representation of the southern California crust and upper mantle
journal, April 2015
- Shaw, John H.; Plesch, Andreas; Tape, Carl
- Earth and Planetary Science Letters, Vol. 415
Deep Clustering to Identify Sources of Urban Seismic Noise in Long Beach, California
journal, December 2020
- Snover, Dylan; Johnson, Christopher W.; Bianco, Michael J.
- Seismological Research Letters, Vol. 92, Issue 2A
Deep Learning Denoising Applied to Regional Distance Seismic Data in Utah
journal, January 2021
- Tibi, Rigobert; Hammond, Patrick; Brogan, Ronald
- Bulletin of the Seismological Society of America, Vol. 111, Issue 2
Searching for hidden earthquakes in Southern California
journal, April 2019
- Ross, Zachary E.; Trugman, Daniel T.; Hauksson, Egill
- Science, Vol. 364, Issue 6442
Imaging widespread seismicity at midlower crustal depths beneath Long Beach, CA, with a dense seismic array: Evidence for a depth-dependent earthquake size distribution: LB ARRAY SEISMIC MONITORING
journal, August 2015
- Inbal, Asaf; Clayton, Robert W.; Ampuero, Jean-Paul
- Geophysical Research Letters, Vol. 42, Issue 15