DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Machine Learning in Seismology: Turning Data into Insights

Abstract

In this article, we provide an overview of current applications of machine learning (ML) in seismology. ML techniques are becoming increasingly widespread in seismology, with applications ranging from identifying unseen signals and patterns to extracting features that might improve our physical understanding. The survey of the applications in seismology presented here serves as a catalyst for further use of ML. Five research areas in seismology are surveyed in which ML classification, regression, clustering algorithms show promise: earthquake detection and phase picking, earthquake early warning (EEW), ground-motion prediction, seismic tomography, and earthquake geodesy. Lastly, we conclude by discussing the need for a hybrid approach combining data-driven ML with traditional physical modeling.

Authors:
 [1]; ORCiD logo [2];  [3];  [4];  [5];  [4]
  1. Univ. of California, Berkeley, CA (United States)
  2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
  3. California Inst. of Technology (CalTech), Pasadena, CA (United States)
  4. University of California San Diego, La Jolla, CA (United States)
  5. Harvard Univ., Cambridge, MA (United States)
Publication Date:
Research Org.:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE Laboratory Directed Research and Development (LDRD) Program
OSTI Identifier:
1492617
Report Number(s):
LA-UR-18-28089
Journal ID: ISSN 0895-0695
Grant/Contract Number:  
89233218CNA000001
Resource Type:
Accepted Manuscript
Journal Name:
Seismological Research Letters
Additional Journal Information:
Journal Volume: 90; Journal Issue: 1; Journal ID: ISSN 0895-0695
Publisher:
Seismological Society of America
Country of Publication:
United States
Language:
English
Subject:
58 GEOSCIENCES

Citation Formats

Kong, Qinkai, Trugman, Daniel Taylor, Ross, Zachary E., Bianco, Michael J., Meade, Brendan J., and Gerstoft, Peter. Machine Learning in Seismology: Turning Data into Insights. United States: N. p., 2018. Web. doi:10.1785/0220180259.
Kong, Qinkai, Trugman, Daniel Taylor, Ross, Zachary E., Bianco, Michael J., Meade, Brendan J., & Gerstoft, Peter. Machine Learning in Seismology: Turning Data into Insights. United States. https://doi.org/10.1785/0220180259
Kong, Qinkai, Trugman, Daniel Taylor, Ross, Zachary E., Bianco, Michael J., Meade, Brendan J., and Gerstoft, Peter. Wed . "Machine Learning in Seismology: Turning Data into Insights". United States. https://doi.org/10.1785/0220180259. https://www.osti.gov/servlets/purl/1492617.
@article{osti_1492617,
title = {Machine Learning in Seismology: Turning Data into Insights},
author = {Kong, Qinkai and Trugman, Daniel Taylor and Ross, Zachary E. and Bianco, Michael J. and Meade, Brendan J. and Gerstoft, Peter},
abstractNote = {In this article, we provide an overview of current applications of machine learning (ML) in seismology. ML techniques are becoming increasingly widespread in seismology, with applications ranging from identifying unseen signals and patterns to extracting features that might improve our physical understanding. The survey of the applications in seismology presented here serves as a catalyst for further use of ML. Five research areas in seismology are surveyed in which ML classification, regression, clustering algorithms show promise: earthquake detection and phase picking, earthquake early warning (EEW), ground-motion prediction, seismic tomography, and earthquake geodesy. Lastly, we conclude by discussing the need for a hybrid approach combining data-driven ML with traditional physical modeling.},
doi = {10.1785/0220180259},
journal = {Seismological Research Letters},
number = 1,
volume = 90,
place = {United States},
year = {2018},
month = {11}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 200 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

PageRank for Earthquakes
journal, March 2014

  • Aguiar, A. C.; Beroza, G. C.
  • Seismological Research Letters, Vol. 85, Issue 2
  • DOI: 10.1785/0220130162

Prediction of principal ground-motion parameters using a hybrid method coupling artificial neural networks and simulated annealing
journal, December 2011


The Status of Earthquake Early Warning around the World: An Introductory Overview
journal, September 2009

  • Allen, R. M.; Gasparini, P.; Kamigaichi, O.
  • Seismological Research Letters, Vol. 80, Issue 5
  • DOI: 10.1785/gssrl.80.5.682

Machine-Learning Methods for Earthquake Ground Motion Analysis and Simulation
journal, April 2015


Probabilistic Seismic Hazard Analysis without the Ergodic Assumption
journal, January 1999

  • Anderson, J. G.; Brune, J. N.
  • Seismological Research Letters, Vol. 70, Issue 1
  • DOI: 10.1785/gssrl.70.1.19

Automated fault detection without seismic processing
journal, March 2017

  • Araya-Polo, Mauricio; Dahlke, Taylor; Frogner, Charlie
  • The Leading Edge, Vol. 36, Issue 3
  • DOI: 10.1190/tle36030208.1

Deep-learning tomography
journal, January 2018

  • Araya-Polo, Mauricio; Jennings, Joseph; Adler, Amir
  • The Leading Edge, Vol. 37, Issue 1
  • DOI: 10.1190/tle37010058.1

Understanding the Magnitude Dependence of PGA and PGV in NGA-West 2 Data
journal, October 2014

  • Baltay, A. S.; Hanks, T. C.
  • Bulletin of the Seismological Society of America, Vol. 104, Issue 6
  • DOI: 10.1785/0120130283

Fast Matched Filter (FMF): An Efficient Seismic Matched‐Filter Search for Both CPU and GPU Architectures
journal, December 2017

  • Beaucé, Eric; Frank, William B.; Romanenko, Alexey
  • Seismological Research Letters, Vol. 89, Issue 1
  • DOI: 10.1785/0220170181

Detecting earthquakes over a seismic network using single-station similarity measures
journal, March 2018

  • Bergen, Karianne J.; Beroza, Gregory C.
  • Geophysical Journal International, Vol. 213, Issue 3
  • DOI: 10.1093/gji/ggy100

Slow Earthquakes and Nonvolcanic Tremor
journal, May 2011


Constructing a Hidden Markov Model based earthquake detector: application to induced seismicity: Constructing a HMM based earthquake detector
journal, February 2012


Travel Time Tomography With Adaptive Dictionaries
journal, December 2018

  • Bianco, Michael J.; Gerstoft, Peter
  • IEEE Transactions on Computational Imaging, Vol. 4, Issue 4
  • DOI: 10.1109/TCI.2018.2862644

The Predictive Power of Ground‐Motion Prediction Equations
journal, January 2017

  • Bindi, D.
  • Bulletin of the Seismological Society of America, Vol. 107, Issue 2
  • DOI: 10.1785/0120160224

Real-time Finite Fault Rupture Detector (FinDer) for large earthquakes
journal, September 2012


PreSEIS: A Neural Network-Based Approach to Earthquake Early Warning for Finite Faults
journal, February 2008

  • Bose, M.; Wenzel, F.; Erdik, M.
  • Bulletin of the Seismological Society of America, Vol. 98, Issue 1
  • DOI: 10.1785/0120070002

NGA-West2 Research Project
journal, August 2014

  • Bozorgnia, Yousef; Abrahamson, Norman A.; Atik, Linda Al
  • Earthquake Spectra, Vol. 30, Issue 3
  • DOI: 10.1193/072113EQS209M

Random Forests
journal, January 2001


EQcorrscan: Repeating and Near‐Repeating Earthquake Detection and Analysis in Python
journal, December 2017

  • Chamberlain, Calum J.; Hopp, Chet J.; Boese, Carolin M.
  • Seismological Research Letters, Vol. 89, Issue 1
  • DOI: 10.1785/0220170151

Automatic microseismic event picking via unsupervised machine learning
journal, September 2017

  • Chen, Yangkang
  • Geophysical Journal International, Vol. 212, Issue 1
  • DOI: 10.1093/gji/ggx420

A Fast Earthquake Early Warning Algorithm Based on the First 3 s of the P‐Wave Coda
journal, July 2018

  • Cuéllar, Armando; Suárez, Gerardo; Espinosa‐Aranda, J. M.
  • Bulletin of the Seismological Society of America, Vol. 108, Issue 4
  • DOI: 10.1785/0120180079

Automatic picking of seismic arrivals in local earthquake data using an artificial neural network
journal, March 1995


Towards fully data driven ground-motion prediction models for Europe
journal, July 2013

  • Derras, Boumédiène; Bard, Pierre Yves; Cotton, Fabrice
  • Bulletin of Earthquake Engineering, Vol. 12, Issue 1
  • DOI: 10.1007/s10518-013-9481-0

Site-Condition Proxies, Ground Motion Variability, and Data-Driven GMPEs: Insights from the NGA-West2 and RESORCE Data Sets
journal, November 2016

  • Derras, Boumédiène; Bard, Pierre-Yves; Cotton, Fabrice
  • Earthquake Spectra, Vol. 32, Issue 4
  • DOI: 10.1193/060215EQS082M

Adapting the Neural Network Approach to PGA Prediction: An Example Based on the KiK-net Data
journal, August 2012

  • Derras, B.; Bard, P. -Y.; Cotton, F.
  • Bulletin of the Seismological Society of America, Vol. 102, Issue 4
  • DOI: 10.1785/0120110088

Enabling large-scale viscoelastic calculations via neural network acceleration: Accelerating VISCOELASTIC CALCULATIONS
journal, March 2017

  • DeVries, Phoebe M. R.; Thompson, T. Ben; Meade, Brendan J.
  • Geophysical Research Letters, Vol. 44, Issue 6
  • DOI: 10.1002/2017GL072716

Deep learning of aftershock patterns following large earthquakes
journal, August 2018


Recent and future developments in earthquake ground motion estimation
journal, September 2016


Explosion site recognition; neural net discriminator using single three-component stations
journal, June 1999

  • Fedorenko, Yu. V.; Husebye, Eystein S.; Ruud, Bent O.
  • Physics of the Earth and Planetary Interiors, Vol. 113, Issue 1-4
  • DOI: 10.1016/S0031-9201(99)00023-0

The detection of low magnitude seismic events using array-based waveform correlation
journal, April 2006


Guest Editorial Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique
journal, May 2016

  • Greenspan, Hayit; van Ginneken, Bram; Summers, Ronald M.
  • IEEE Transactions on Medical Imaging, Vol. 35, Issue 5
  • DOI: 10.1109/TMI.2016.2553401

Oklahoma's induced seismicity strongly linked to wastewater injection depth
journal, February 2018


Machine learning: Trends, perspectives, and prospects
journal, July 2015


Preface to the Focus Section on Geophone Array Seismology
journal, August 2018

  • Karplus, Marianne; Schmandt, Brandon
  • Seismological Research Letters, Vol. 89, Issue 5
  • DOI: 10.1785/0220180212

Propagation of Slow Slip Leading Up to the 2011 Mw 9.0 Tohoku-Oki Earthquake
journal, January 2012


Multisensor data fusion: A review of the state-of-the-art
journal, January 2013


Prioritizing Ground‐Motion Validation Metrics Using Semisupervised and Supervised Learning
journal, June 2018

  • Khoshnevis, Naeem; Taborda, Ricardo
  • Bulletin of the Seismological Society of America, Vol. 108, Issue 4
  • DOI: 10.1785/0120180056

MyShake: Initial observations from a global smartphone seismic network: OBSERVATIONS FROM MYSHAKE
journal, September 2016

  • Kong, Qingkai; Allen, Richard M.; Schreier, Louis
  • Geophysical Research Letters, Vol. 43, Issue 18
  • DOI: 10.1002/2016GL070955

MyShake: A smartphone seismic network for earthquake early warning and beyond
journal, February 2016

  • Kong, Qingkai; Allen, Richard M.; Schreier, Louis
  • Science Advances, Vol. 2, Issue 2
  • DOI: 10.1126/sciadv.1501055

Deep learning
journal, May 2015

  • LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
  • Nature, Vol. 521, Issue 7553
  • DOI: 10.1038/nature14539

Full waveform inversion with nonlocal similarity and model-derivative domain adaptive sparsity-promoting regularization
journal, September 2018

  • Li, Dongzhuo; Harris, Jerry M.
  • Geophysical Journal International, Vol. 215, Issue 3
  • DOI: 10.1093/gji/ggy380

Machine Learning Seismic Wave Discrimination: Application to Earthquake Early Warning
journal, May 2018

  • Li, Zefeng; Meier, Men-Andrin; Hauksson, Egill
  • Geophysical Research Letters, Vol. 45, Issue 10
  • DOI: 10.1029/2018GL077870

Tomographic inversion using ℓ 1 -norm regularization of wavelet coefficients
journal, July 2007


Sparse Modeling for Image and Vision Processing
journal, January 2014

  • Mairal, Julien
  • Foundations and Trends® in Computer Graphics and Vision, Vol. 8, Issue 2-3
  • DOI: 10.1561/0600000058

What Is Better Than Coulomb Failure Stress? A Ranking of Scalar Static Stress Triggering Mechanisms from 105Mainshock‐Aftershock Pairs
journal, November 2017

  • Meade, Brendan J.; DeVries, Phoebe M. R.; Faller, Jeremy
  • Geophysical Research Letters, Vol. 44, Issue 22
  • DOI: 10.1002/2017GL075875

The Gutenberg Algorithm: Evolutionary Bayesian Magnitude Estimates for Earthquake Early Warning with a Filter Bank
journal, September 2015

  • Meier, M. ‐A.; Heaton, T.; Clinton, J.
  • Bulletin of the Seismological Society of America, Vol. 105, Issue 5
  • DOI: 10.1785/0120150098

Inversion of a velocity model using artificial neural networks
journal, December 2010


Fast magnitude determination using a single seismological station record implementing machine learning techniques
journal, January 2018


Migration of early aftershocks following the 2004 Parkfield earthquake
journal, November 2009

  • Peng, Zhigang; Zhao, Peng
  • Nature Geoscience, Vol. 2, Issue 12
  • DOI: 10.1038/ngeo697

Convolutional neural network for earthquake detection and location
journal, February 2018

  • Perol, Thibaut; Gharbi, Michaël; Denolle, Marine
  • Science Advances, Vol. 4, Issue 2
  • DOI: 10.1126/sciadv.1700578

Hidden physics models: Machine learning of nonlinear partial differential equations
journal, March 2018


MR Image Reconstruction From Highly Undersampled k-Space Data by Dictionary Learning
journal, May 2011

  • Ravishankar, Saiprasad; Bresler, Yoram
  • IEEE Transactions on Medical Imaging, Vol. 30, Issue 5
  • DOI: 10.1109/TMI.2010.2090538

Seismic tomography: A window into deep Earth
journal, February 2010

  • Rawlinson, N.; Pozgay, S.; Fishwick, S.
  • Physics of the Earth and Planetary Interiors, Vol. 178, Issue 3-4
  • DOI: 10.1016/j.pepi.2009.10.002

Using graph clustering to locate sources within a dense sensor array
journal, March 2017


Generalized Seismic Phase Detection with Deep Learning
journal, August 2018

  • Ross, Zachary E.; Meier, Men‐Andrin; Hauksson, Egill
  • Bulletin of the Seismological Society of America, Vol. 108, Issue 5A
  • DOI: 10.1785/0120180080

Aftershocks driven by afterslip and fluid pressure sweeping through a fault-fracture mesh: Aftershocks From Afterslip and Fluids
journal, August 2017

  • Ross, Zachary E.; Rollins, Christopher; Cochran, Elizabeth S.
  • Geophysical Research Letters, Vol. 44, Issue 16
  • DOI: 10.1002/2017GL074634

Neural networks and inversion of seismic data
journal, January 1994

  • Röth, Gunter; Tarantola, Albert
  • Journal of Geophysical Research, Vol. 99, Issue B4
  • DOI: 10.1029/93JB01563

Machine Learning Predicts Laboratory Earthquakes: MACHINE LEARNING PREDICTS LAB QUAKES
journal, September 2017

  • Rouet-Leduc, Bertrand; Hulbert, Claudia; Lubbers, Nicholas
  • Geophysical Research Letters, Vol. 44, Issue 18
  • DOI: 10.1002/2017GL074677

Data-driven discovery of partial differential equations
journal, April 2017

  • Rudy, Samuel H.; Brunton, Steven L.; Proctor, Joshua L.
  • Science Advances, Vol. 3, Issue 4
  • DOI: 10.1126/sciadv.1602614

Non-volcanic tremor and low-frequency earthquake swarms
journal, March 2007

  • Shelly, David R.; Beroza, Gregory C.; Ide, Satoshi
  • Nature, Vol. 446, Issue 7133
  • DOI: 10.1038/nature05666

Visibility Graph Analysis of Seismicity around Enguri High Arch Dam, Caucasus
journal, August 2018

  • Telesca, Luciano; Chelidze, Tamaz
  • Bulletin of the Seismological Society of America, Vol. 108, Issue 5B
  • DOI: 10.1785/0120170370

Prediction of ground motion parameters using randomized ANFIS (RANFIS)
journal, March 2016


Strong Correlation between Stress Drop and Peak Ground Acceleration for Recent M 1–4 Earthquakes in the San Francisco Bay Area
journal, March 2018

  • Trugman, Daniel T.; Shearer, Peter M.
  • Bulletin of the Seismological Society of America, Vol. 108, Issue 2
  • DOI: 10.1785/0120170245

An overview of full-waveform inversion in exploration geophysics
journal, November 2009


Application of real time recurrent neural network for detection of small natural earthquakes in Poland
journal, October 2013

  • Wiszniowski, Jan; Plesiewicz, Beata M.; Trojanowski, Jacek
  • Acta Geophysica, Vol. 62, Issue 3
  • DOI: 10.2478/s11600-013-0140-2

Suppression of Azimuth Ambiguities in Spaceborne SAR Images Using Spectral Selection and Extrapolation
journal, January 2018


Regionally Adjustable Generic Ground‐Motion Prediction Equation Based on Equivalent Point‐Source Simulations: Application to Central and Eastern North America
journal, July 2015

  • Yenier, Emrah; Atkinson, Gail M.
  • Bulletin of the Seismological Society of America, Vol. 105, Issue 4
  • DOI: 10.1785/0120140332

Rapid Earthquake Discrimination for Earthquake Early Warning: A Bayesian Probabilistic Approach Using Three‐Component Single‐Station Waveforms and Seismicity Forecast
journal, June 2018

  • Yin, Lucy; Andrews, Jennifer; Heaton, Thomas
  • Bulletin of the Seismological Society of America, Vol. 108, Issue 4
  • DOI: 10.1785/0120170138

Earthquake detection through computationally efficient similarity search
journal, December 2015

  • Yoon, Clara E.; O’Reilly, Ossian; Bergen, Karianne J.
  • Science Advances, Vol. 1, Issue 11
  • DOI: 10.1126/sciadv.1501057

Real-time earthquake monitoring using a search engine method
journal, December 2014

  • Zhang, Jie; Zhang, Haijiang; Chen, Enhong
  • Nature Communications, Vol. 5, Issue 1
  • DOI: 10.1038/ncomms6664

An artificial neural network approach for broadband seismic phase picking
journal, June 1999

  • Zhao, Yue; Takano, Kiyoshi
  • Bulletin of the Seismological Society of America, Vol. 89, Issue 3
  • DOI: 10.1785/BSSA0890030670

Sparse-promoting full-waveform inversion based on online orthonormal dictionary learning
journal, March 2017


PhaseNet: A Deep-Neural-Network-Based Seismic Arrival Time Picking Method
journal, October 2018

  • Zhu, Weiqiang; Beroza, Gregory C.
  • Geophysical Journal International
  • DOI: 10.1093/gji/ggy423

Works referencing / citing this record:

The promise of implementing machine learning in earthquake engineering: A state-of-the-art review
journal, June 2020


High-resolution seismic tomography of Long Beach, CA using machine learning
journal, October 2019


Pervasive Foreshock Activity Across Southern California
journal, August 2019

  • Trugman, Daniel T.; Ross, Zachary E.
  • Geophysical Research Letters, Vol. 46, Issue 15
  • DOI: 10.1029/2019gl083725

A Deeper Look into ‘Deep Learning of Aftershock Patterns Following Large Earthquakes’: Illustrating First Principles in Neural Network Physical Interpretability
book, May 2019

  • Mignan, Arnaud; Broccardo, Marco; Rojas, Ignacio
  • Advances in Computational Intelligence: 15th International Work-Conference on Artificial Neural Networks, IWANN 2019, Gran Canaria, Spain, June 12-14, 2019, Proceedings, Part I, p. 3-14
  • DOI: 10.1007/978-3-030-20521-8_1

One neuron versus deep learning in aftershock prediction
journal, October 2019


Spatial Prediction of Aftershocks Triggered by a Major Earthquake: A Binary Machine Learning Perspective
journal, October 2019

  • Karimzadeh, Sadra; Matsuoka, Masashi; Kuang, Jianming
  • ISPRS International Journal of Geo-Information, Vol. 8, Issue 10
  • DOI: 10.3390/ijgi8100462

Machine Learning Reveals the State of Intermittent Frictional Dynamics in a Sheared Granular Fault
journal, July 2019

  • Ren, C. X.; Dorostkar, O.; Rouet‐Leduc, B.
  • Geophysical Research Letters, Vol. 46, Issue 13
  • DOI: 10.1029/2019gl082706

A Neural Network for Automated Quality Screening of Ground Motion Records from Small Magnitude Earthquakes
journal, November 2019

  • Bellagamba, Xavier; Lee, Robin; Bradley, Brendon A.
  • Earthquake Spectra, Vol. 35, Issue 4
  • DOI: 10.1193/122118eqs292m