skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Benchmarking Current and Emerging Approaches to Infrasound Signal Classification.

Abstract

Low frequency sound %3C zo Hz, known as infrasound, is generated by a variety of natural and anthropogenic sources. Following an event, infrasonic waves travel through a dynamic atmosphere that can change on the order of minutes. This makes infrasound event classification a difficult problem as waveforms from the same source type can look drastically different. Event classification usually requires ground truth information from seismic or other methods. This is time consuming, inefficient, and does not allow for a classification if the event locates somewhere other than a known source, the location accuracy is poor, or ground truth from seismic data is lacking. Here we compare the performance of the state of the art for infrasound event classification, support vector machine (SVM), to the performance of a convolutional neural network (CNN), a method that has been proven in tangential fields such as seismology. For a 1-class catalog consisting of only volcanic activity and earthquake events, the 4-fold average SVM classification accuracy is 75%, while it is 74% when using a CNN. Classification accuracies from the 4-class catalog consisting of the most common infrasound events detected at the global scale are 55% and 56% for the SVM and CNN architectures, respectively.more » These results demonstrate that using a CNN does not increase performance for infrasound event classification. This suggests that SVM should be the preferred classification method as it is a simpler and more trustworthy architecture and can be tied to the physical properties of the waveforms. The SVM and CNN algorithms described in this paper are not yet generalizable to other infrasound event catalogs. We anticipate this study to be a starting point for the development of large and comprehensive, systematically labeled, infrasound event catalogs as such catalogs will be necessary to provide an increase in the value of deep learning on event classification.« less

Authors:
;
Publication Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1564035
Report Number(s):
SAND2019-10901
679410
DOE Contract Number:  
AC04-94AL85000
Resource Type:
Technical Report
Country of Publication:
United States
Language:
English

Citation Formats

Albert, Sarah, and Linville, Lisa. Benchmarking Current and Emerging Approaches to Infrasound Signal Classification.. United States: N. p., 2019. Web. doi:10.2172/1564035.
Albert, Sarah, & Linville, Lisa. Benchmarking Current and Emerging Approaches to Infrasound Signal Classification.. United States. doi:10.2172/1564035.
Albert, Sarah, and Linville, Lisa. Sun . "Benchmarking Current and Emerging Approaches to Infrasound Signal Classification.". United States. doi:10.2172/1564035. https://www.osti.gov/servlets/purl/1564035.
@article{osti_1564035,
title = {Benchmarking Current and Emerging Approaches to Infrasound Signal Classification.},
author = {Albert, Sarah and Linville, Lisa},
abstractNote = {Low frequency sound %3C zo Hz, known as infrasound, is generated by a variety of natural and anthropogenic sources. Following an event, infrasonic waves travel through a dynamic atmosphere that can change on the order of minutes. This makes infrasound event classification a difficult problem as waveforms from the same source type can look drastically different. Event classification usually requires ground truth information from seismic or other methods. This is time consuming, inefficient, and does not allow for a classification if the event locates somewhere other than a known source, the location accuracy is poor, or ground truth from seismic data is lacking. Here we compare the performance of the state of the art for infrasound event classification, support vector machine (SVM), to the performance of a convolutional neural network (CNN), a method that has been proven in tangential fields such as seismology. For a 1-class catalog consisting of only volcanic activity and earthquake events, the 4-fold average SVM classification accuracy is 75%, while it is 74% when using a CNN. Classification accuracies from the 4-class catalog consisting of the most common infrasound events detected at the global scale are 55% and 56% for the SVM and CNN architectures, respectively. These results demonstrate that using a CNN does not increase performance for infrasound event classification. This suggests that SVM should be the preferred classification method as it is a simpler and more trustworthy architecture and can be tied to the physical properties of the waveforms. The SVM and CNN algorithms described in this paper are not yet generalizable to other infrasound event catalogs. We anticipate this study to be a starting point for the development of large and comprehensive, systematically labeled, infrasound event catalogs as such catalogs will be necessary to provide an increase in the value of deep learning on event classification.},
doi = {10.2172/1564035},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2019},
month = {9}
}