Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Deep Learning Models Augment Analyst Decisions for Event Discrimination

Journal Article · · Geophysical Research Letters
DOI:https://doi.org/10.1029/2018GL081119· OSTI ID:1496986
 [1];  [1];  [2]
  1. University of Utah Seismograph Stations University of Utah, Salt Lake City, UT (United States)
  2. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

Long-term seismic monitoring networks are well positioned to leverage advances in machine learning because of the abundance of labeled training data that curated event catalogs provide. In this study, we explore the use of Convolutional and Recurrent Neural Networks to accomplish discrimination of explosive and tectonic sources for local distances. Using a 5-year event catalog generated by the University of Utah Seismograph Stations we train models to produce automated event labels using 90 s event spectrograms from 3-component and single-channel sensors. Both network architectures are able to replicate analyst labels above 98%. Most commonly, model error is the result of label error (70% of cases). Accounting for mislabeled events (~1% of the catalog) model accuracy for both models increases to above 99%. Finally, classification accuracy remains above 98% for shallow tectonic events, indicating that spectral characteristics controlled by event depth do not play a dominant role in event discrimination.

Research Organization:
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA)
Grant/Contract Number:
AC04-94AL85000; NA0003525
OSTI ID:
1496986
Alternate ID(s):
OSTI ID: 1504780
Report Number(s):
SAND--2019-1319J; 672351
Journal Information:
Geophysical Research Letters, Journal Name: Geophysical Research Letters Journal Issue: 7 Vol. 46; ISSN 0094-8276
Publisher:
American Geophysical UnionCopyright Statement
Country of Publication:
United States
Language:
English

References (16)

Magnitude-based discrimination of man-made seismic events from naturally occurring earthquakes in Utah, USA: DISCRIMINATION OF MAN-MADE SEISMICITY journal October 2016
Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition book January 2005
Characterization of mining explosions at regional distances: Implications with the International Monitoring System journal January 2002
Crustal structure along the Great Basin-Colorado Plateau Transition from seismic refraction studies journal March 1975
Backpropagation through time: what it does and how to do it journal January 1990
Gradient-based learning applied to document recognition journal January 1998
Learning long-term dependencies with gradient descent is difficult journal March 1994
Speech recognition with deep recurrent neural networks conference May 2013
Properties of cross-entropy minimization journal July 1981
Convolutional neural network for earthquake detection and location journal February 2018
Long Short-Term Memory journal November 1997
Discrimination of Earthquakes and Underwater Explosions Using Neural Networks journal February 2003
Depth Discrimination Using Rg‐to‐Sg Spectral Amplitude Ratios for Seismic Events in Utah Recorded at Local Distances journal March 2018
Generalized Seismic Phase Detection with Deep Learning journal August 2018
The Array Network Facility Seismic Bulletin: Products and an Unbiased View of United States Seismicity journal May 2014
Generalized Seismic Phase Detection with Deep Learning text January 2018

Cited By (1)

SediNet: a configurable deep learning model for mixed qualitative and quantitative optical granulometry journal March 2020

Similar Records

Classification of Local Seismic Events in the Utah Region: A Comparison of Amplitude Ratio Methods with a Spectrogram-Based Machine Learning Approach
Journal Article · Tue Oct 22 00:00:00 EDT 2019 · Bulletin of the Seismological Society of America · OSTI ID:1575270

Auto-Curation of Seismic Event Data for Signal Denoising
Technical Report · Wed Sep 15 00:00:00 EDT 2021 · OSTI ID:1820246

Depth Discrimination Using Rg-to-Sg Spectral Amplitude Ratios for Seismic Events in Utah Recorded at Local Distances
Journal Article · Tue Mar 20 00:00:00 EDT 2018 · Bulletin of the Seismological Society of America (Online) · OSTI ID:1429839