Deep convolutional autoencoders as generic feature extractors in seismological applications

Kong, Qingkai; Chiang, Andrea; Aguiar, Ana C.; Fernández-Godino, M. Giselle; Myers, Stephen C.; Lucas, Donald D.

doi:10.1016/j.aiig.2021.12.002

Deep convolutional autoencoders as generic feature extractors in seismological applications

Journal Article · Wed Dec 15 23:00:00 EST 2021 · Artificial intelligence in geosciences

DOI:https://doi.org/10.1016/j.aiig.2021.12.002· OSTI ID:1838599

^[1]; Chiang, Andrea ^[1]; ^[1]; ^[1]; Myers, Stephen C. ^[1]; ^[1]

Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

The idea of using a deep autoencoder to encode seismic waveform features and then use them in different seismological applications is appealing. In this paper, we designed tests to evaluate this idea of using autoencoders as feature extractors for different seismological applications, such as event discrimination (i.e., earthquake vs. noise waveforms, earthquake vs. explosion waveforms), and phase picking. These tests involve training an autoencoder, either undercomplete or overcomplete, on a large amount of earthquake waveforms, and then using the trained encoder as a feature extractor with subsequent application layers (either a fully connected layer, or a convolutional layer plus a fully connected layer) to make the decision. By comparing the performance of these newly designed models against the baseline models trained from scratch, we conclude that the autoencoder feature extractor approach may only outperform the baseline under certain conditions, such as when the target problems require features that are similar to the autoencoder encoded features, when a relatively small amount of training data is available, and when certain model structures and training strategies are utilized. The model structure that works best in all these tests is an overcomplete autoencoder with a convolutional layer and a fully connected layer to make the estimation.

View Accepted Manuscript (DOE)

Research Organization:: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA)

Grant/Contract Number:: AC52-07NA27344

OSTI ID:: 1838599

Report Number(s):: LLNL-JRNL--828227; 1043503

Journal Information:: Artificial intelligence in geosciences, Journal Name: Artificial intelligence in geosciences Vol. 2; ISSN 2666-5441

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (38)

Chemical Explosion Experiments to Improve Nuclear Test Monitoring Snelson, Catherine M.; Abbott, Robert E.; Broome, Scott T. Eos, Transactions American Geophysical Union, Vol. 94, Issue 27 https://doi.org/10.1002/2013EO270002	journal	July 2013
Structure of the Bighorn Mountain region, Wyoming, from teleseismic receiver function analysis: Implications for the kinematics of Laramide shortening: STRUCTURE OF THE BIGHORN MOUNTAIN REGION Yeck, William L.; Sheehan, Anne F.; Anderson, Megan L. Journal of Geophysical Research: Solid Earth, Vol. 119, Issue 9 https://doi.org/10.1002/2013JB010769	journal	September 2014
Automated detection and location of microseismicity at Mount St. Helens with a large‐N geophone array Hansen, Steven M.; Schmandt, Brandon Geophysical Research Letters, Vol. 42, Issue 18 https://doi.org/10.1002/2015GL064848	journal	September 2015
Crustal structure of the Bighorn Mountains region: Precambrian influence on Laramide shortening and uplift in north‐central Wyoming Worthington, Lindsay L.; Miller, Kate C.; Erslev, Eric A. Tectonics, Vol. 35, Issue 1 https://doi.org/10.1002/2015TC003840	journal	January 2016
Machine Learning Predicts Laboratory Earthquakes: MACHINE LEARNING PREDICTS LAB QUAKES Rouet-Leduc, Bertrand; Hulbert, Claudia; Lubbers, Nicholas Geophysical Research Letters, Vol. 44, Issue 18 https://doi.org/10.1002/2017GL074677	journal	September 2017
Discriminative Autoencoder for Feature Extraction: Application to Character Recognition Gogna, Anupriya; Majumdar, Angshul Neural Processing Letters, Vol. 49, Issue 3 https://doi.org/10.1007/s11063-018-9894-5	journal	July 2018
Local earthquakes detection: A benchmark dataset of 3-component seismograms built on a global scale Magrini, Fabrizio; Jozinović, Dario; Cammarano, Fabio Artificial Intelligence in Geosciences, Vol. 1 https://doi.org/10.1016/j.aiig.2020.04.001	journal	December 2020
Machine learning in geosciences and remote sensing Lary, David J.; Alavi, Amir H.; Gandomi, Amir H. Geoscience Frontiers, Vol. 7, Issue 1 https://doi.org/10.1016/j.gsf.2015.07.003	journal	January 2016
A survey of deep neural network architectures and their applications Liu, Weibo; Wang, Zidong; Liu, Xiaohui Neurocomputing, Vol. 234 https://doi.org/10.1016/j.neucom.2016.12.038	journal	April 2017
Machine Learning Seismic Wave Discrimination: Application to Earthquake Early Warning Li, Zefeng; Meier, Men-Andrin; Hauksson, Egill Geophysical Research Letters, Vol. 45, Issue 10 https://doi.org/10.1029/2018GL077870	journal	May 2018
Deep Learning Models Augment Analyst Decisions for Event Discrimination Linville, Lisa; Pankow, Kristine; Draelos, Timothy Geophysical Research Letters, Vol. 46, Issue 7 https://doi.org/10.1029/2018GL081119	journal	April 2019
Reliable Real‐Time Seismic Signal/Noise Discrimination With Machine Learning Meier, Men‐Andrin; Ross, Zachary E.; Ramachandran, Anshul Journal of Geophysical Research: Solid Earth, Vol. 124, Issue 1 https://doi.org/10.1029/2018JB016661	journal	January 2019
Machine‐Learning‐Based Analysis of the Guy‐Greenbrier, Arkansas Earthquakes: A Tale of Two Sequences Park, Yongsoo; Mousavi, S. Mostafa; Zhu, Weiqiang Geophysical Research Letters, Vol. 47, Issue 6 https://doi.org/10.1029/2020GL087032	journal	March 2020
Injection‐Induced Earthquakes on Complex Fault Zones of the Raton Basin Illuminated by Machine‐Learning Phase Picker and Dense Nodal Array Wang, Ruijia; Schmandt, Brandon; Zhang, Miao Geophysical Research Letters, Vol. 47, Issue 14 https://doi.org/10.1029/2020GL088168	journal	July 2020
Using a Deep Neural Network and Transfer Learning to Bridge Scales for Seismic Phase Picking Chai, Chengping; Maceira, Monica; Santos‐Villalobos, Hector J. Geophysical Research Letters, Vol. 47, Issue 16 https://doi.org/10.1029/2020GL088651	journal	August 2020
Deep learning LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey Nature, Vol. 521, Issue 7553 https://doi.org/10.1038/nature14539	journal	May 2015
Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking Mousavi, S. Mostafa; Ellsworth, William L.; Zhu, Weiqiang Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-17591-w	journal	August 2020
ObsPy: a bridge for seismology into the scientific Python ecosystem Krischer, Lion; Megies, Tobias; Barsch, Robert Computational Science & Discovery, Vol. 8, Issue 1 https://doi.org/10.1088/1749-4699/8/1/014003	journal	January 2015
Spatio-temporal analysis of seismic anisotropy associated with the Cook Strait and Kaikōura earthquake sequences in New Zealand Graham, Kenny M.; Savage, Martha K.; Arnold, Richard Geophysical Journal International, Vol. 223, Issue 3 https://doi.org/10.1093/gji/ggaa433	journal	September 2020
Universal Joint Feature Extraction for P300 EEG Classification Using Multi-Task Autoencoder Ditthapron, Apiwat; Banluesombatkul, Nannapas; Ketrat, Sombat IEEE Access, Vol. 7 https://doi.org/10.1109/ACCESS.2019.2919143	journal	January 2019
STanford EArthquake Dataset (STEAD): A Global Data Set of Seismic Signals for AI Mousavi, S. Mostafa; Sheng, Yixiao; Zhu, Weiqiang IEEE Access, Vol. 7 https://doi.org/10.1109/ACCESS.2019.2947848	journal	January 2019
Unsupervised Clustering of Seismic Signals Using Deep Convolutional Autoencoders Mousavi, S. Mostafa; Zhu, Weiqiang; Ellsworth, William IEEE Geoscience and Remote Sensing Letters, Vol. 16, Issue 11 https://doi.org/10.1109/LGRS.2019.2909218	journal	November 2019
Seismic Signal Denoising and Decomposition Using Deep Neural Networks Zhu, Weiqiang; Mousavi, S. Mostafa; Beroza, Gregory C. IEEE Transactions on Geoscience and Remote Sensing, Vol. 57, Issue 11 https://doi.org/10.1109/TGRS.2019.2926772	journal	November 2019
Machine Learning for the Geosciences: Challenges and Opportunities Karpatne, Anuj; Ebert-Uphoff, Imme; Ravela, Sai IEEE Transactions on Knowledge and Data Engineering, Vol. 31, Issue 8 https://doi.org/10.1109/TKDE.2018.2861006	journal	August 2019
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning Shin, Hoo-Chang; Roth, Holger R.; Gao, Mingchen IEEE Transactions on Medical Imaging, Vol. 35, Issue 5 https://doi.org/10.1109/TMI.2016.2528162	journal	May 2016
MyShake: A smartphone seismic network for earthquake early warning and beyond Kong, Qingkai; Allen, Richard M.; Schreier, Louis Science Advances, Vol. 2, Issue 2 https://doi.org/10.1126/sciadv.1501055	journal	February 2016
Convolutional neural network for earthquake detection and location Perol, Thibaut; Gharbi, Michaël; Denolle, Marine Science Advances, Vol. 4, Issue 2 https://doi.org/10.1126/sciadv.1700578	journal	February 2018
Machine learning for data-driven discovery in solid Earth geoscience Bergen, Karianne J.; Johnson, Paul A.; de Hoop, Maarten V. Science, Vol. 363, Issue 6433 https://doi.org/10.1126/science.aau0323	journal	March 2019
Deep denoising autoencoder for seismic random noise attenuation Saad, Omar M.; Chen, Yangkang GEOPHYSICS, Vol. 85, Issue 4 https://doi.org/10.1190/geo2019-0468.1	journal	June 2020
Generalized Seismic Phase Detection with Deep Learning Ross, Zachary E.; Meier, Men‐Andrin; Hauksson, Egill Bulletin of the Seismological Society of America, Vol. 108, Issue 5A https://doi.org/10.1785/0120180080	journal	August 2018
Investigating the Effectiveness of P/S Amplitude Ratios for Local Distance Event Discrimination Pyle, Moira L.; Walter, William R. Bulletin of the Seismological Society of America, Vol. 109, Issue 3 https://doi.org/10.1785/0120180256	journal	March 2019
Discrimination of Small Earthquakes and Buried Single-Fired Chemical Explosions at Local Distances (<150 km) in the Western United States from Comparison of Local Magnitude (ML) and Coda Duration Magnitude (MC) Koper, Keith D.; Holt, Monique M.; Voyles, Jonathan R. Bulletin of the Seismological Society of America, Vol. 111, Issue 1 https://doi.org/10.1785/0120200188	journal	October 2020
Deep Learning Denoising Applied to Regional Distance Seismic Data in Utah Tibi, Rigobert; Hammond, Patrick; Brogan, Ronald Bulletin of the Seismological Society of America, Vol. 111, Issue 2 https://doi.org/10.1785/0120200292	journal	January 2021
Machine Learning in Seismology: Turning Data into Insights Kong, Qingkai; Trugman, Daniel T.; Ross, Zachary E. Seismological Research Letters, Vol. 90, Issue 1 https://doi.org/10.1785/0220180259	journal	November 2018
Hybrid Event Detection and Phase‐Picking Algorithm Using Convolutional and Recurrent Neural Networks Zhou, Yijian; Yue, Han; Kong, Qingkai Seismological Research Letters, Vol. 90, Issue 3 https://doi.org/10.1785/0220180319	journal	April 2019
Deep Clustering to Identify Sources of Urban Seismic Noise in Long Beach, California Snover, Dylan; Johnson, Christopher W.; Bianco, Michael J. Seismological Research Letters, Vol. 92, Issue 2A https://doi.org/10.1785/0220200164	journal	December 2020
ObsPy: A Python Toolbox for Seismology Beyreuther, M.; Barsch, R.; Krischer, L. Seismological Research Letters, Vol. 81, Issue 3 https://doi.org/10.1785/gssrl.81.3.530	journal	May 2010
Accelerating Bayesian microseismic event location with deep learning Spurio Mancini, Alessio; Piras, Davide; Ferreira, Ana Margarida Godinho Solid Earth, Vol. 12, Issue 7 https://doi.org/10.5194/se-12-1683-2021	journal	January 2021

Similar Records

Predicting wind-driven spatial deposition through simulated color images using deep autoencoders

Journal Article · Tue Jan 24 23:00:00 EST 2023 · Scientific Reports · OSTI ID:1922125

Related Subjects

58 GEOSCIENCES
Autoencoder
Machine learning

Deep convolutional autoencoders as generic feature extractors in seismological applications

Citation Formats

References (38)

Similar Records

Related Subjects