Attention-Based Convolutional Neural Network for Earthquake Event Classification

Bonhwa Ku; Gwantae Kim; Jae Kwang Ahn; Jimin Lee; Hanseok Ko

doi:10.1109/LGRS.2020.3014418

Attention-Based Convolutional Neural Network for Earthquake Event Classification

Bonhwa Ku, Gwantae Kim, Jae Kwang Ahn, Jimin Lee, Hanseok Ko

School of Electrical Engineering

Research output: Contribution to journal › Article › peer-review

28 Citations (Scopus)

Abstract

This letter presents a deep convolutional neural network (CNN) with attention module that improves the performance of the classification of various earthquake events. Addressing all possible earthquake events, including not only microearthquakes and artificial-earthquakes but also large-earthquakes, requires both suitable feature expression and a classifier that can effectively discriminate seismic waveforms under adverse conditions. To robustly classify earthquake events, a deep CNN with an attention module was proposed in raw seismic waveforms. Representative experimental results show that the proposed method provides an effective structure for earthquake events classification and, with the Korean peninsula earthquake database from 2016 to 2018, outperforms previous state-of-the-art methods.

Original language	English
Pages (from-to)	2057-2061
Number of pages	5
Journal	IEEE Geoscience and Remote Sensing Letters
Volume	18
Issue number	12
DOIs	https://doi.org/10.1109/LGRS.2020.3014418
Publication status	Published - 2021 Dec 1

Bibliographical note

Funding Information:
This work was supported by the Meteorological/Earthquake See-At Technology Development Research under Grant KMI2018-09610.

Publisher Copyright:
© 2004-2012 IEEE.

Keywords

Attention module
convolutional neural network (CNN)
deep learning
earthquake classification
raw seismic waveform

ASJC Scopus subject areas

Geotechnical Engineering and Engineering Geology
Electrical and Electronic Engineering

Access to Document

10.1109/LGRS.2020.3014418

Cite this

@article{9feea716d899456c83d199ef7ffda3a8,

title = "Attention-Based Convolutional Neural Network for Earthquake Event Classification",

abstract = "This letter presents a deep convolutional neural network (CNN) with attention module that improves the performance of the classification of various earthquake events. Addressing all possible earthquake events, including not only microearthquakes and artificial-earthquakes but also large-earthquakes, requires both suitable feature expression and a classifier that can effectively discriminate seismic waveforms under adverse conditions. To robustly classify earthquake events, a deep CNN with an attention module was proposed in raw seismic waveforms. Representative experimental results show that the proposed method provides an effective structure for earthquake events classification and, with the Korean peninsula earthquake database from 2016 to 2018, outperforms previous state-of-the-art methods.",

keywords = "Attention module, convolutional neural network (CNN), deep learning, earthquake classification, raw seismic waveform",

author = "Bonhwa Ku and Gwantae Kim and Ahn, {Jae Kwang} and Jimin Lee and Hanseok Ko",

note = "Funding Information: This work was supported by the Meteorological/Earthquake See-At Technology Development Research under Grant KMI2018-09610. Publisher Copyright: {\textcopyright} 2004-2012 IEEE.",

year = "2021",

month = dec,

day = "1",

doi = "10.1109/LGRS.2020.3014418",

language = "English",

volume = "18",

pages = "2057--2061",

journal = "IEEE Geoscience and Remote Sensing Letters",

issn = "1545-598X",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "12",

}

TY - JOUR

T1 - Attention-Based Convolutional Neural Network for Earthquake Event Classification

AU - Ku, Bonhwa

AU - Kim, Gwantae

AU - Ahn, Jae Kwang

AU - Lee, Jimin

AU - Ko, Hanseok

PY - 2021/12/1

Y1 - 2021/12/1

N2 - This letter presents a deep convolutional neural network (CNN) with attention module that improves the performance of the classification of various earthquake events. Addressing all possible earthquake events, including not only microearthquakes and artificial-earthquakes but also large-earthquakes, requires both suitable feature expression and a classifier that can effectively discriminate seismic waveforms under adverse conditions. To robustly classify earthquake events, a deep CNN with an attention module was proposed in raw seismic waveforms. Representative experimental results show that the proposed method provides an effective structure for earthquake events classification and, with the Korean peninsula earthquake database from 2016 to 2018, outperforms previous state-of-the-art methods.

AB - This letter presents a deep convolutional neural network (CNN) with attention module that improves the performance of the classification of various earthquake events. Addressing all possible earthquake events, including not only microearthquakes and artificial-earthquakes but also large-earthquakes, requires both suitable feature expression and a classifier that can effectively discriminate seismic waveforms under adverse conditions. To robustly classify earthquake events, a deep CNN with an attention module was proposed in raw seismic waveforms. Representative experimental results show that the proposed method provides an effective structure for earthquake events classification and, with the Korean peninsula earthquake database from 2016 to 2018, outperforms previous state-of-the-art methods.

KW - Attention module

KW - convolutional neural network (CNN)

KW - deep learning

KW - earthquake classification

KW - raw seismic waveform

UR - http://www.scopus.com/inward/record.url?scp=85120437930&partnerID=8YFLogxK

U2 - 10.1109/LGRS.2020.3014418

DO - 10.1109/LGRS.2020.3014418

M3 - Article

AN - SCOPUS:85120437930

SN - 1545-598X

VL - 18

SP - 2057

EP - 2061

JO - IEEE Geoscience and Remote Sensing Letters

JF - IEEE Geoscience and Remote Sensing Letters

IS - 12

ER -

Attention-Based Convolutional Neural Network for Earthquake Event Classification

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this