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

Deep learning categorization of infrasound array data

Journal Article · · Journal of the Acoustical Society of America
DOI:https://doi.org/10.1121/10.0014903· OSTI ID:1922780
 [1];  [2];  [2];  [2];  [2]
  1. Univ. of Alaska, Fairbanks, AK (United States); Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
  2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
+ Show Author Affiliations
Here we develop a deep learning-based infrasonic detection and categorization methodology that uses convolutional neural networks with self-attention layers to identify stationary and non-stationary signals in infrasound array processing results. Using features extracted from the coherence and direction-of-arrival information from beamforming at different infrasound arrays, our model more reliably detects signals compared with raw waveform data. Using three infrasound stations maintained as part of the International Monitoring System, we construct an analyst-reviewed data set for model training and evaluation. We construct models using a 4-category framework, a generalized noise vs non-noise detection scheme, and a signal-of-interest (SOI) categorization framework that merges short duration stationary and non-stationary categories into a single SOI category. We evaluate these models using a combination of k-fold cross-validation, comparison with an existing “state-of-the-art” detector, and a transportability analysis. Although results are mixed in distinguishing stationary and non-stationary short duration signals, f-scores for the noise vs non-noise and SOI analyses are consistently above 0.96, implying that deep learning-based infrasonic categorization is a highly accurate means of identifying signals-of-interest in infrasonic data records.
Research Organization:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Organization:
USDOE
Grant/Contract Number:
89233218CNA000001
OSTI ID:
1922780
Alternate ID(s):
OSTI ID: 1895541
Report Number(s):
LA-UR-22-23301
Journal Information:
Journal of the Acoustical Society of America, Journal Name: Journal of the Acoustical Society of America Journal Issue: 4 Vol. 152; ISSN 0001-4966
Publisher:
Acoustical Society of AmericaCopyright Statement
Country of Publication:
United States
Language:
English

References (44)

Automatic infrasound detection and location of sources in the western United States journal July 2014
On the infrasound detected from the 2013 and 2016 DPRK's underground nuclear tests journal April 2016
The IMS Infrasound Network: Design and Establishment of Infrasound Stations book November 2009
Monitoring the Earth’s Atmosphere with the Global IMS Infrasound Network book November 2009
Volcano Infrasound and the International Monitoring System book October 2018
Infrasound signal classification based on spectral entropy and support vector machine journal December 2016
Analyzing continuous infrasound from Stromboli volcano, Italy using unsupervised machine learning journal July 2020
Using unsupervised machine learning to identify changes in eruptive behavior at Mount Etna, Italy journal November 2020
P Wave Arrival Picking and First-Motion Polarity Determination With Deep Learning journal June 2018
Deep Learning Models Augment Analyst Decisions for Event Discrimination journal April 2019
An End‐To‐End Earthquake Detection Method for Joint Phase Picking and Association Using Deep Learning journal March 2022
Detecting Large Explosions With Machine Learning Models Trained on Synthetic Infrasound Data journal June 2022
An automatic seismic event processing for detection and location: The P.M.C.C. Method journal May 1995
Deep learning journal May 2015
Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking journal August 2020
On Detecting a Signal in N Stationarily Correlated Noise Series journal August 1971
Evaluation of a pair-based, joint-likelihood association approach for regional infrasound event identification journal March 2020
Improved infrasound array processing with robust estimators journal March 2020
Development of a robust and automated infrasound event catalogue using the International Monitoring System journal January 2015
Improved Bayesian Infrasonic Source Localization for regional infrasound journal October 2015
Regional infrasound generated by the Humming Roadrunner ground truth experiment journal June 2018
PhaseNet: A Deep-Neural-Network-Based Seismic Arrival Time Picking Method journal October 2018
Infrasound signal duration: the effects of propagation distance and waveguide structure journal January 2019
Gradient-based learning applied to document recognition journal January 1998
Two decades of array signal processing research: the parametric approach journal July 1996
DeepFace: Closing the Gap to Human-Level Performance in Face Verification conference June 2014
Regional monitoring of infrasound events using multiple arrays: application to Utah and Washington State journal October 2008
The Buncefield explosion: a benchmark for infrasound analysis across Central Europe journal May 2009
Clustering and classification of infrasonic events at Mount Etna using pattern recognition techniques journal April 2011
A theoretical treatment of the long range propagation of impulsive signals under strongly ducted nocturnal conditions journal November 2008
Acoustic detection, tracking, and characterization of three tornadoes journal April 2014
Evaluating factors influencing infrasonic signal detection and automatic processing performance utilizing a regional network journal December 2020
Multi-year regional infrasound detection of Tungurahua, El Reventador, and Sangay volcanoes in Ecuador from 2006 to 2013
  • Ortiz, Hugo D.; Matoza, Robin S.; Garapaty, Charusheela
  • 179th Meeting of the Acoustical Society of America, Proceedings of Meetings on Acoustics https://doi.org/10.1121/2.0001362
conference January 2021
Convolutional neural network for earthquake detection and location journal February 2018
Machine learning for data-driven discovery in solid Earth geoscience journal March 2019
A New Classification Method of Infrasound Events Using Hilbert-Huang Transform and Support Vector Machine journal January 2014
Long Short-Term Memory journal November 1997
An Automatic Event Detector at the Tonto Forest Seismic Observatory journal October 1974
The F-Detector Revisited: An Improved Strategy for Signal Detection at Seismic and Infrasound Arrays journal February 2009
Generalized Seismic Phase Detection with Deep Learning journal August 2018
Machine Learning in Seismology: Turning Data into Insights journal November 2018
Benchmarking Current and Emerging Approaches to Infrasound Signal Classification journal January 2020
Waveform Features Strongly Control Subcrater Classification Performance for a Large, Labeled Volcano Infrasound Dataset journal July 2022
ObsPy: A Python Toolbox for Seismology journal May 2010

Figures / Tables (11)

FIG. 1(p. 11)figure FIG. 1
FIG. 2(p. 14)figure FIG. 2
TABLE I(p. 17)table TABLE I
FIG. 3(p. 20)figure FIG. 3
TABLE II(p. 22)table TABLE II
FIG. 4(p. 23)figure FIG. 4
TABLE III(p. 24)table TABLE III
TABLE IV(p. 27)table TABLE IV
TABLE V(p. 28)table TABLE V
FIG. 5(p. 30)figure FIG. 5
TABLE IV(p. 32)table TABLE IV

Similar Records

Evaluation of a generalized least squares algorithm for infrasound beamforming with coherent background noise
Journal Article · Mon Jun 02 20:00:00 EDT 2025 · Geophysical Journal International · OSTI ID:2570027

Related Subjects

47 OTHER INSTRUMENTATION
Gaussian processes
acoustic phenomena
acoustic sensors
acoustic signal processing
artificial intelligence
data streams
geophysics
infrasonic
machine learning
stochastic processes