Seismic Signal Synthesis by Generative Adversarial Network with Gated Convolutional Neural Network Structure

Yuanming Li; Bonhwa Ku; Gwantae Kim; Jae Kwang Ahn; Hanseok Ko

doi:10.1109/IGARSS39084.2020.9323670

Seismic Signal Synthesis by Generative Adversarial Network with Gated Convolutional Neural Network Structure

Yuanming Li, Bonhwa Ku, Gwantae Kim, Jae Kwang Ahn, Hanseok Ko

School of Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

Abstract

Detecting earthquake events from seismic time series signal is a challenging task. Recently, detection methods based on machine learning have been developed to improve the accuracy and efficiency. However, accuracy of those methods rely on sufficient amount of high-quality training data. In many situations, the high-quality data is difficulty to obtain. We address and resolve this issue by using a Generative Adversarial Network (GAN) model for seismic signal synthesis. GAN already shows its powerful capability in generating high quality synthetic samples in multiple domains. In this paper, we propose a GAN model with gated CNN which can excellently capture sequential structure of seismic time series. We demonstrate its effectiveness via earthquake classification performance. The results show the synthetic data generated by our model indeed can improve the classification performance over the one trained with only real samples.

Original language	English
Title of host publication	2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3857-3860
Number of pages	4
ISBN (Electronic)	9781728163741
DOIs	https://doi.org/10.1109/IGARSS39084.2020.9323670
Publication status	Published - 2020 Sept 26
Event	2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Virtual, Waikoloa, United States Duration: 2020 Sept 26 → 2020 Oct 2

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)

Conference

Conference	2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020
Country/Territory	United States
City	Virtual, Waikoloa
Period	20/9/26 → 20/10/2

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Keywords

data augmentation
deep learning
earthquake detection
generative adversarial network

ASJC Scopus subject areas

Computer Science Applications
General Earth and Planetary Sciences

Access to Document

10.1109/IGARSS39084.2020.9323670

Cite this

Li, Y., Ku, B., Kim, G., Ahn, J. K., & Ko, H. (2020). Seismic Signal Synthesis by Generative Adversarial Network with Gated Convolutional Neural Network Structure. In 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings (pp. 3857-3860). Article 9323670 (International Geoscience and Remote Sensing Symposium (IGARSS)). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS39084.2020.9323670

Seismic Signal Synthesis by Generative Adversarial Network with Gated Convolutional Neural Network Structure. / Li, Yuanming; Ku, Bonhwa; Kim, Gwantae et al.
2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. p. 3857-3860 9323670 (International Geoscience and Remote Sensing Symposium (IGARSS)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Li, Y, Ku, B, Kim, G, Ahn, JK & Ko, H 2020, Seismic Signal Synthesis by Generative Adversarial Network with Gated Convolutional Neural Network Structure. in 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings., 9323670, International Geoscience and Remote Sensing Symposium (IGARSS), Institute of Electrical and Electronics Engineers Inc., pp. 3857-3860, 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020, Virtual, Waikoloa, United States, 20/9/26. https://doi.org/10.1109/IGARSS39084.2020.9323670

Li Y, Ku B, Kim G, Ahn JK, Ko H. Seismic Signal Synthesis by Generative Adversarial Network with Gated Convolutional Neural Network Structure. In 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. p. 3857-3860. 9323670. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS39084.2020.9323670

Li, Yuanming ; Ku, Bonhwa ; Kim, Gwantae et al. / Seismic Signal Synthesis by Generative Adversarial Network with Gated Convolutional Neural Network Structure. 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 3857-3860 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{8a7292b75dd648d98d33a14331523b6e,

title = "Seismic Signal Synthesis by Generative Adversarial Network with Gated Convolutional Neural Network Structure",

abstract = "Detecting earthquake events from seismic time series signal is a challenging task. Recently, detection methods based on machine learning have been developed to improve the accuracy and efficiency. However, accuracy of those methods rely on sufficient amount of high-quality training data. In many situations, the high-quality data is difficulty to obtain. We address and resolve this issue by using a Generative Adversarial Network (GAN) model for seismic signal synthesis. GAN already shows its powerful capability in generating high quality synthetic samples in multiple domains. In this paper, we propose a GAN model with gated CNN which can excellently capture sequential structure of seismic time series. We demonstrate its effectiveness via earthquake classification performance. The results show the synthetic data generated by our model indeed can improve the classification performance over the one trained with only real samples.",

keywords = "data augmentation, deep learning, earthquake detection, generative adversarial network",

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

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 ; Conference date: 26-09-2020 Through 02-10-2020",

year = "2020",

month = sep,

day = "26",

doi = "10.1109/IGARSS39084.2020.9323670",

language = "English",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

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

pages = "3857--3860",

booktitle = "2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings",

}

TY - GEN

T1 - Seismic Signal Synthesis by Generative Adversarial Network with Gated Convolutional Neural Network Structure

AU - Li, Yuanming

AU - Ku, Bonhwa

AU - Kim, Gwantae

AU - Ahn, Jae Kwang

AU - Ko, Hanseok

PY - 2020/9/26

Y1 - 2020/9/26

N2 - Detecting earthquake events from seismic time series signal is a challenging task. Recently, detection methods based on machine learning have been developed to improve the accuracy and efficiency. However, accuracy of those methods rely on sufficient amount of high-quality training data. In many situations, the high-quality data is difficulty to obtain. We address and resolve this issue by using a Generative Adversarial Network (GAN) model for seismic signal synthesis. GAN already shows its powerful capability in generating high quality synthetic samples in multiple domains. In this paper, we propose a GAN model with gated CNN which can excellently capture sequential structure of seismic time series. We demonstrate its effectiveness via earthquake classification performance. The results show the synthetic data generated by our model indeed can improve the classification performance over the one trained with only real samples.

AB - Detecting earthquake events from seismic time series signal is a challenging task. Recently, detection methods based on machine learning have been developed to improve the accuracy and efficiency. However, accuracy of those methods rely on sufficient amount of high-quality training data. In many situations, the high-quality data is difficulty to obtain. We address and resolve this issue by using a Generative Adversarial Network (GAN) model for seismic signal synthesis. GAN already shows its powerful capability in generating high quality synthetic samples in multiple domains. In this paper, we propose a GAN model with gated CNN which can excellently capture sequential structure of seismic time series. We demonstrate its effectiveness via earthquake classification performance. The results show the synthetic data generated by our model indeed can improve the classification performance over the one trained with only real samples.

KW - data augmentation

KW - deep learning

KW - earthquake detection

KW - generative adversarial network

UR - http://www.scopus.com/inward/record.url?scp=85102017542&partnerID=8YFLogxK

U2 - 10.1109/IGARSS39084.2020.9323670

DO - 10.1109/IGARSS39084.2020.9323670

M3 - Conference contribution

AN - SCOPUS:85102017542

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 3857

EP - 3860

BT - 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020

Y2 - 26 September 2020 through 2 October 2020

ER -

Seismic Signal Synthesis by Generative Adversarial Network with Gated Convolutional Neural Network Structure

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this