Earthquake Event Classification Using Multitasking Deep Learning

Bonhwa Ku; Jeungki Min; Jae Kwang Ahn; Jimin Lee; Hanseok Ko

doi:10.1109/LGRS.2020.2996640

Earthquake Event Classification Using Multitasking Deep Learning

Bonhwa Ku, Jeungki Min, Jae Kwang Ahn, Jimin Lee, Hanseok Ko

School of Electrical Engineering

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

8 Citations (Scopus)

Abstract

This letter proposes an attention-based convolutional neural network architecture for multitasking learning to accurately classify not only the presence of an earthquake but also the event type of the earthquake. In particular, to improve the performance in earthquake-type classification, we develop an attention-based feature aggregation framework embedded in multitask learning architecture. Representative experimental results show that the proposed method provides an effective structure for an earthquake detection and event classification with an earthquake database of the Korean peninsula and the Circum-Pacific belt.

Original language	English
Article number	9107451
Pages (from-to)	1149-1153
Number of pages	5
Journal	IEEE Geoscience and Remote Sensing Letters
Volume	18
Issue number	7
DOIs	https://doi.org/10.1109/LGRS.2020.2996640
Publication status	Published - 2021 Jul

Bibliographical note

Publisher Copyright:
© 2004-2012 IEEE.

Keywords

Attention module
Convolutional neural network (CNN)
Earthquake event classification
Feature aggregation
Multitasking deep learning

ASJC Scopus subject areas

Geotechnical Engineering and Engineering Geology
Electrical and Electronic Engineering

Access to Document

10.1109/LGRS.2020.2996640

Cite this

@article{c0dcf90f88644d3ab40aa38fb1fa7c12,

title = "Earthquake Event Classification Using Multitasking Deep Learning",

abstract = "This letter proposes an attention-based convolutional neural network architecture for multitasking learning to accurately classify not only the presence of an earthquake but also the event type of the earthquake. In particular, to improve the performance in earthquake-type classification, we develop an attention-based feature aggregation framework embedded in multitask learning architecture. Representative experimental results show that the proposed method provides an effective structure for an earthquake detection and event classification with an earthquake database of the Korean peninsula and the Circum-Pacific belt.",

keywords = "Attention module, Convolutional neural network (CNN), Earthquake event classification, Feature aggregation, Multitasking deep learning",

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

note = "Publisher Copyright: {\textcopyright} 2004-2012 IEEE.",

year = "2021",

month = jul,

doi = "10.1109/LGRS.2020.2996640",

language = "English",

volume = "18",

pages = "1149--1153",

journal = "IEEE Geoscience and Remote Sensing Letters",

issn = "1545-598X",

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

number = "7",

}

TY - JOUR

T1 - Earthquake Event Classification Using Multitasking Deep Learning

AU - Ku, Bonhwa

AU - Min, Jeungki

AU - Ahn, Jae Kwang

AU - Lee, Jimin

AU - Ko, Hanseok

PY - 2021/7

Y1 - 2021/7

N2 - This letter proposes an attention-based convolutional neural network architecture for multitasking learning to accurately classify not only the presence of an earthquake but also the event type of the earthquake. In particular, to improve the performance in earthquake-type classification, we develop an attention-based feature aggregation framework embedded in multitask learning architecture. Representative experimental results show that the proposed method provides an effective structure for an earthquake detection and event classification with an earthquake database of the Korean peninsula and the Circum-Pacific belt.

AB - This letter proposes an attention-based convolutional neural network architecture for multitasking learning to accurately classify not only the presence of an earthquake but also the event type of the earthquake. In particular, to improve the performance in earthquake-type classification, we develop an attention-based feature aggregation framework embedded in multitask learning architecture. Representative experimental results show that the proposed method provides an effective structure for an earthquake detection and event classification with an earthquake database of the Korean peninsula and the Circum-Pacific belt.

KW - Attention module

KW - Convolutional neural network (CNN)

KW - Earthquake event classification

KW - Feature aggregation

KW - Multitasking deep learning

UR - http://www.scopus.com/inward/record.url?scp=85112460902&partnerID=8YFLogxK

U2 - 10.1109/LGRS.2020.2996640

DO - 10.1109/LGRS.2020.2996640

M3 - Article

AN - SCOPUS:85112460902

SN - 1545-598X

VL - 18

SP - 1149

EP - 1153

JO - IEEE Geoscience and Remote Sensing Letters

JF - IEEE Geoscience and Remote Sensing Letters

IS - 7

M1 - 9107451

ER -

Earthquake Event Classification Using Multitasking Deep Learning

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this