ESeismic-GAN: A Generative Model for Seismic Events From Cotopaxi Volcano

With the growing ability to collect large volumes of volcano seismic data, the detection and labeling process of these records is increasingly challenging. Clearly, analyzing all available data through manual inspection is no longer a viable option. Supervised machine learning models might be consid...

Full description

Saved in:
Bibliographic Details
Main Authors: Felipe Grijalva, Washington Ramos, Noel Perez, Diego Benitez, Roman Lara, Mario Ruiz
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9477001/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846127423810174976
author Felipe Grijalva
Washington Ramos
Noel Perez
Diego Benitez
Roman Lara
Mario Ruiz
author_facet Felipe Grijalva
Washington Ramos
Noel Perez
Diego Benitez
Roman Lara
Mario Ruiz
author_sort Felipe Grijalva
collection DOAJ
description With the growing ability to collect large volumes of volcano seismic data, the detection and labeling process of these records is increasingly challenging. Clearly, analyzing all available data through manual inspection is no longer a viable option. Supervised machine learning models might be considered to automatize the analysis of data acquired by <italic>in situ</italic> monitoring stations. However, the direct application of such algorithms is defiant, given the high complexity of waveforms and the scarce and often imbalanced amount of labeled data. In light of this and motivated by the wide success that generative adversarial networks (GANs) have seen at generating images, we present ESeismic-GAN, a GAN model to generate the magnitude frequency response of volcanic events. Our experiments demonstrate that ESeismic-GAN learns to generate the frequency components that characterize long-period and volcano-tectonic events from Cotopaxi volcano. We evaluate the performance of ESeismic-GAN during the training stage using Fr&#x00E9;chet distance, and, later on, we reconstruct the signals into time-domain to be finally evaluated with Frechet inception distance.
format Article
id doaj-art-00cd7fb105a04eacac5402eb73f81607
institution Kabale University
issn 1939-1404
2151-1535
language English
publishDate 2021-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-00cd7fb105a04eacac5402eb73f816072024-12-12T00:00:08ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352021-01-01147111712010.1109/JSTARS.2021.30952709477001ESeismic-GAN: A Generative Model for Seismic Events From Cotopaxi VolcanoFelipe Grijalva0https://orcid.org/0000-0001-6162-3429Washington Ramos1https://orcid.org/0000-0002-3311-7446Noel Perez2https://orcid.org/0000-0003-3166-745XDiego Benitez3https://orcid.org/0000-0001-6219-067XRoman Lara4https://orcid.org/0000-0001-8848-9928Mario Ruiz5https://orcid.org/0000-0002-0872-6573Faculty of Engineering and Applied Sciences (FICA), Telecommunications Engineering, Universidad de Las Am&#x00E9;ricas (UDLA), Quito, EcuadorDepartamento de Electrónica, Telecomunicaciones y Redes de Información (DETRI), Escuela Polit&#x00E9;cnica Nacional, Quito, EcuadorColegio de Ciencias e Ingenierías “El Politécnico,”, Universidad San Francisco de Quito (USFQ), Quito, EcuadorColegio de Ciencias e Ingenierías “El Politécnico,”, Universidad San Francisco de Quito (USFQ), Quito, EcuadorGrupo de Investigaci&#x00F3;n en Sistemas Inteligentes (WiCOM-Energy), Sangolqu&#x00ED;, EcuadorInstituto Geofísico, Escuela Polit&#x00E9;cnica Nacional, Quito, EcuadorWith the growing ability to collect large volumes of volcano seismic data, the detection and labeling process of these records is increasingly challenging. Clearly, analyzing all available data through manual inspection is no longer a viable option. Supervised machine learning models might be considered to automatize the analysis of data acquired by <italic>in situ</italic> monitoring stations. However, the direct application of such algorithms is defiant, given the high complexity of waveforms and the scarce and often imbalanced amount of labeled data. In light of this and motivated by the wide success that generative adversarial networks (GANs) have seen at generating images, we present ESeismic-GAN, a GAN model to generate the magnitude frequency response of volcanic events. Our experiments demonstrate that ESeismic-GAN learns to generate the frequency components that characterize long-period and volcano-tectonic events from Cotopaxi volcano. We evaluate the performance of ESeismic-GAN during the training stage using Fr&#x00E9;chet distance, and, later on, we reconstruct the signals into time-domain to be finally evaluated with Frechet inception distance.https://ieeexplore.ieee.org/document/9477001/Adversarial learningCotopaxigenerative adversarial networks (GANs)generative modelseismicvolcano
spellingShingle Felipe Grijalva
Washington Ramos
Noel Perez
Diego Benitez
Roman Lara
Mario Ruiz
ESeismic-GAN: A Generative Model for Seismic Events From Cotopaxi Volcano
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Adversarial learning
Cotopaxi
generative adversarial networks (GANs)
generative model
seismic
volcano
title ESeismic-GAN: A Generative Model for Seismic Events From Cotopaxi Volcano
title_full ESeismic-GAN: A Generative Model for Seismic Events From Cotopaxi Volcano
title_fullStr ESeismic-GAN: A Generative Model for Seismic Events From Cotopaxi Volcano
title_full_unstemmed ESeismic-GAN: A Generative Model for Seismic Events From Cotopaxi Volcano
title_short ESeismic-GAN: A Generative Model for Seismic Events From Cotopaxi Volcano
title_sort eseismic gan a generative model for seismic events from cotopaxi volcano
topic Adversarial learning
Cotopaxi
generative adversarial networks (GANs)
generative model
seismic
volcano
url https://ieeexplore.ieee.org/document/9477001/
work_keys_str_mv AT felipegrijalva eseismicganagenerativemodelforseismiceventsfromcotopaxivolcano
AT washingtonramos eseismicganagenerativemodelforseismiceventsfromcotopaxivolcano
AT noelperez eseismicganagenerativemodelforseismiceventsfromcotopaxivolcano
AT diegobenitez eseismicganagenerativemodelforseismiceventsfromcotopaxivolcano
AT romanlara eseismicganagenerativemodelforseismiceventsfromcotopaxivolcano
AT marioruiz eseismicganagenerativemodelforseismiceventsfromcotopaxivolcano