TY - JOUR
T1 - Generalization of Deep-Learning Models for Classification of Local Distance Earthquakes and Explosions across Various Geologic Settings
AU - Maguire, Ross
AU - Schmandt, Brandon
AU - Wang, Ruijia
AU - Kong, Qingkai
AU - Sanchez, Pedro
N1 - Publisher Copyright:
© Seismological Society of America.
PY - 2024/7
Y1 - 2024/7
N2 - Although accurately classifying signals from earthquakes and explosions at local distance (< 250 km) remains an important task for seismic network operations, the growing volume of available seismic data presents a challenge for analysts using traditional source discrimination techniques. In recent years, deep-learning models have proven effective at discriminating between low-magnitude earthquakes and explosions measured at local distances, but it is not clear how well these models are capable of generalizing across different geological settings. To address the issue of generalization between regions, we train deep-learning models (convolutional neural networks [CNNs]) on time–frequency representations (scalograms) of three-component earthquake and explosion signals from eight different regions in the continental United States. We explore scenarios where models are trained on data from all regions, individual regions, or all but one region. We find that although CNN models trained on individual regions do not necessarily generalize well across different settings, models trained on multiple regions that include diverse path coverage generalize to new regions, with station-level accuracy of up to 90% or more for data sets from unseen regions. In general, CNN-based discrimination models significantly outperform models based on uncorrected P/S ratio (measured in the 10–18 Hz frequency band), even when CNN models are tested on data from entirely unseen regions.
AB - Although accurately classifying signals from earthquakes and explosions at local distance (< 250 km) remains an important task for seismic network operations, the growing volume of available seismic data presents a challenge for analysts using traditional source discrimination techniques. In recent years, deep-learning models have proven effective at discriminating between low-magnitude earthquakes and explosions measured at local distances, but it is not clear how well these models are capable of generalizing across different geological settings. To address the issue of generalization between regions, we train deep-learning models (convolutional neural networks [CNNs]) on time–frequency representations (scalograms) of three-component earthquake and explosion signals from eight different regions in the continental United States. We explore scenarios where models are trained on data from all regions, individual regions, or all but one region. We find that although CNN models trained on individual regions do not necessarily generalize well across different settings, models trained on multiple regions that include diverse path coverage generalize to new regions, with station-level accuracy of up to 90% or more for data sets from unseen regions. In general, CNN-based discrimination models significantly outperform models based on uncorrected P/S ratio (measured in the 10–18 Hz frequency band), even when CNN models are tested on data from entirely unseen regions.
UR - http://www.scopus.com/inward/record.url?scp=85188528290&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85188528290&partnerID=8YFLogxK
U2 - 10.1785/0220230267
DO - 10.1785/0220230267
M3 - Article
AN - SCOPUS:85188528290
SN - 0895-0695
VL - 95
SP - 2229
EP - 2238
JO - Seismological Research Letters
JF - Seismological Research Letters
IS - 4
ER -