Global Nuclear Explosion Discrimination Using a Convolutional Neural Network

Abstract Using P‐wave seismograms, we trained a seismic source classifier using a Convolutional Neural Network. We trained for three classes: earthquake P‐wave, underground nuclear explosion (UNE) P‐wave, and noise. With the current absence of nuclear testing by countries that have signed the Compre...

Full description

Saved in:
Bibliographic Details
Main Authors: Louisa Barama, Jesse Williams, Andrew V. Newman, Zhigang Peng
Format: Article
Language:English
Published: Wiley 2023-09-01
Series:Geophysical Research Letters
Subjects:
Online Access:https://doi.org/10.1029/2022GL101528
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849773019985084416
author Louisa Barama
Jesse Williams
Andrew V. Newman
Zhigang Peng
author_facet Louisa Barama
Jesse Williams
Andrew V. Newman
Zhigang Peng
author_sort Louisa Barama
collection DOAJ
description Abstract Using P‐wave seismograms, we trained a seismic source classifier using a Convolutional Neural Network. We trained for three classes: earthquake P‐wave, underground nuclear explosion (UNE) P‐wave, and noise. With the current absence of nuclear testing by countries that have signed the Comprehensive Test Ban Treaty, high quality seismic data from UNEs is limited. Even with limited training data, our model can accurately characterize most events recorded at regional and teleseismic distances, finding over 95% signals in the validation set. We applied the model on holdout datasets of the North Korean test explosions to evaluate the performance on unique region and station‐source pairs, with promising results. Additionally, we tested on the Source Physics Experiment events to investigate the potential for chemical explosions to act as a surrogate for nuclear explosions. We anticipate that machine‐learning models like our classifier system can have broad application for other seismic signals including volcanic and non‐volcanic tremor, anomalous earthquakes, ice‐quakes or landslide‐quakes.
format Article
id doaj-art-2d3fdb5699164d0e9cff2c42d180af96
institution DOAJ
issn 0094-8276
1944-8007
language English
publishDate 2023-09-01
publisher Wiley
record_format Article
series Geophysical Research Letters
spelling doaj-art-2d3fdb5699164d0e9cff2c42d180af962025-08-20T03:02:10ZengWileyGeophysical Research Letters0094-82761944-80072023-09-015017n/an/a10.1029/2022GL101528Global Nuclear Explosion Discrimination Using a Convolutional Neural NetworkLouisa Barama0Jesse Williams1Andrew V. Newman2Zhigang Peng3School of Earth and Atmospheric Sciences Georgia Institute of Technology GA Atlanta USAGlobal Technology Connection, Inc. GA Atlanta USASchool of Earth and Atmospheric Sciences Georgia Institute of Technology GA Atlanta USASchool of Earth and Atmospheric Sciences Georgia Institute of Technology GA Atlanta USAAbstract Using P‐wave seismograms, we trained a seismic source classifier using a Convolutional Neural Network. We trained for three classes: earthquake P‐wave, underground nuclear explosion (UNE) P‐wave, and noise. With the current absence of nuclear testing by countries that have signed the Comprehensive Test Ban Treaty, high quality seismic data from UNEs is limited. Even with limited training data, our model can accurately characterize most events recorded at regional and teleseismic distances, finding over 95% signals in the validation set. We applied the model on holdout datasets of the North Korean test explosions to evaluate the performance on unique region and station‐source pairs, with promising results. Additionally, we tested on the Source Physics Experiment events to investigate the potential for chemical explosions to act as a surrogate for nuclear explosions. We anticipate that machine‐learning models like our classifier system can have broad application for other seismic signals including volcanic and non‐volcanic tremor, anomalous earthquakes, ice‐quakes or landslide‐quakes.https://doi.org/10.1029/2022GL101528seismologymachine learningglobal discriminationnuclear blast
spellingShingle Louisa Barama
Jesse Williams
Andrew V. Newman
Zhigang Peng
Global Nuclear Explosion Discrimination Using a Convolutional Neural Network
Geophysical Research Letters
seismology
machine learning
global discrimination
nuclear blast
title Global Nuclear Explosion Discrimination Using a Convolutional Neural Network
title_full Global Nuclear Explosion Discrimination Using a Convolutional Neural Network
title_fullStr Global Nuclear Explosion Discrimination Using a Convolutional Neural Network
title_full_unstemmed Global Nuclear Explosion Discrimination Using a Convolutional Neural Network
title_short Global Nuclear Explosion Discrimination Using a Convolutional Neural Network
title_sort global nuclear explosion discrimination using a convolutional neural network
topic seismology
machine learning
global discrimination
nuclear blast
url https://doi.org/10.1029/2022GL101528
work_keys_str_mv AT louisabarama globalnuclearexplosiondiscriminationusingaconvolutionalneuralnetwork
AT jessewilliams globalnuclearexplosiondiscriminationusingaconvolutionalneuralnetwork
AT andrewvnewman globalnuclearexplosiondiscriminationusingaconvolutionalneuralnetwork
AT zhigangpeng globalnuclearexplosiondiscriminationusingaconvolutionalneuralnetwork