Classification of tectonic and non-tectonic seismicity based on convolutional neural network

SUMMARY In this paper, convolutional neural networks (CNNs) were used to distinguish between tectonic and non-tectonic seismicity. The proposed CNNs consisted of seven convolutional layers with small kernels and one fully connected layer, which only relied on the acoustic waveform without extracting...

Full description

Saved in:
Bibliographic Details
Published inGeophysical journal international Vol. 224; no. 1; pp. 191 - 198
Main Authors Liu, Xinliang, Ren, Tao, Chen, Hongfeng, Chen, Yufeng
Format Journal Article
LanguageEnglish
Published Oxford University Press 01.01.2021
Subjects
Acoustic properties
Asia
Neural networks
Seismicity and tectonics
Online AccessGet full text

Cover

More Information
Summary:SUMMARY In this paper, convolutional neural networks (CNNs) were used to distinguish between tectonic and non-tectonic seismicity. The proposed CNNs consisted of seven convolutional layers with small kernels and one fully connected layer, which only relied on the acoustic waveform without extracting features manually. For a single station, the accuracy of the model was 0.90, and the event accuracy could reach 0.93. The proposed model was tested using data from January 2019 to August 2019 in China. The event accuracy could reach 0.92, showing that the proposed model could distinguish between tectonic and non-tectonic seismicity.
ISSN:0956-540X
1365-246X
DOI:10.1093/gji/ggaa444