TY - GEN
T1 - Seismic Event Classification Using Spectrograms and Deep Neural Nets
AU - Salazar, Aaron
AU - Arroyo, Rodrigo
AU - Pérez, Noel
AU - Benítez, Diego S.
N1 - Publisher Copyright:
© 2021, Springer Nature Switzerland AG.
PY - 2021
Y1 - 2021
N2 - In this work, we proposed a new method to classify long-period and volcano-tectonic spectrogram images using eight different deep learning architectures. The developed method used three deep convolutional neural networks named DCNN1, DCNN2, and DCNN3, three deep convolutional neural networks combined with deep recurrent neural networks named DCNN-RNN1, DCNN-RNN2, and DCNN-RNN3, and two autoencoder neural networks named AE1 and AE2, to maximize the area under the curve of the receiver operating characteristic scores on a dataset of volcano seismic spectrogram images. The three deep recurrent neural network-based models reached the worst results due to the overfitting produced by the small number of samples in the training sets. The DCNN1 overcame the remaining models by obtaining an area under the curve of the receiver operating characteristic and accuracy scores of 0.98 and 95 %, respectively. Although these values were not the highest values per metric, they did not represent statistical differences against other results obtained by more algorithmically complex models. The proposed DCNN1 model showed similar or superior performance compared to the majority of the state of the art methods in terms of accuracy. Therefore it can be considered a successful scheme to classify LP and VT seismic events based on their spectrogram images.
AB - In this work, we proposed a new method to classify long-period and volcano-tectonic spectrogram images using eight different deep learning architectures. The developed method used three deep convolutional neural networks named DCNN1, DCNN2, and DCNN3, three deep convolutional neural networks combined with deep recurrent neural networks named DCNN-RNN1, DCNN-RNN2, and DCNN-RNN3, and two autoencoder neural networks named AE1 and AE2, to maximize the area under the curve of the receiver operating characteristic scores on a dataset of volcano seismic spectrogram images. The three deep recurrent neural network-based models reached the worst results due to the overfitting produced by the small number of samples in the training sets. The DCNN1 overcame the remaining models by obtaining an area under the curve of the receiver operating characteristic and accuracy scores of 0.98 and 95 %, respectively. Although these values were not the highest values per metric, they did not represent statistical differences against other results obtained by more algorithmically complex models. The proposed DCNN1 model showed similar or superior performance compared to the majority of the state of the art methods in terms of accuracy. Therefore it can be considered a successful scheme to classify LP and VT seismic events based on their spectrogram images.
KW - Artificial intelligence
KW - Deep-learning models
KW - Spectrogram images
KW - Volcanic seismic event classification
UR - http://www.scopus.com/inward/record.url?scp=85103298215&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-69774-7_2
DO - 10.1007/978-3-030-69774-7_2
M3 - Contribución a la conferencia
AN - SCOPUS:85103298215
SN - 9783030697730
T3 - Communications in Computer and Information Science
SP - 16
EP - 30
BT - Applications of Computational Intelligence - 3rd IEEE Colombian Conference, ColCACI 2020, Revised Selected Papers
A2 - Orjuela-Cañón, Alvaro David
A2 - Lopez, Jesus
A2 - Arias-Londoño, Julián David
A2 - Figueroa-García, Juan Carlos
PB - Springer Science and Business Media Deutschland GmbH
T2 - 3rd IEEE Colombian Conference on Applications of Computational Intelligence, IEEE ColCACI 2020
Y2 - 7 August 2020 through 8 August 2020
ER -