Multi-station automatic classification of seismic signatures from the Lascar volcano database
<p>This study was aimed to build a multi-station automatic classification system for volcanic seismic signatures such as hybrid, long period, tremor, tectonic, and volcano–tectonic events. This system was based on a probabilistic model made using transfer learning, which has, as the main tool,...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2023-03-01
|
Series: | Natural Hazards and Earth System Sciences |
Online Access: | https://nhess.copernicus.org/articles/23/991/2023/nhess-23-991-2023.pdf |
_version_ | 1811160369361584128 |
---|---|
author | P. Salazar P. Salazar P. Salazar F. Yupanqui F. Yupanqui C. Meneses S. Layana G. Yáñez |
author_facet | P. Salazar P. Salazar P. Salazar F. Yupanqui F. Yupanqui C. Meneses S. Layana G. Yáñez |
author_sort | P. Salazar |
collection | DOAJ |
description | <p>This study was aimed to build a multi-station automatic classification system for volcanic seismic signatures such as hybrid, long period, tremor, tectonic, and volcano–tectonic events. This system was based on a probabilistic model made using transfer learning, which has, as the main tool, a pre-trained convolutional network named AlexNet. We designed five experiments using different datasets with data that were real, synthetic, two different combinations of these (combined 1 and combined 2), and a balanced subset without synthetic data. The experiment presented the highest scores when a process of data augmentation was introduced into processing sequence. Thus, the lack of real data in some classes (imbalance) dramatically affected the quality of the results, because the learning step (training) was overfitted to the more numerous classes. To test the model stability with variable inputs, we implemented a <span class="inline-formula"><i>k</i></span>-fold cross-validation procedure. Under this approach, the results reached high predictive performance, considering that only the percentage of recognition of the tectonic events (TC) class was partially affected. The results obtained showed the performance of the probabilistic model, reaching high scores over different test datasets. The most valuable benefit of using this technique was that the use of volcano seismic signals from multiple stations provided a more generalizable model which, in the near future, can be extended to multi-volcano database systems. The impact of this work is significant in the evaluation of hazard and risk by monitoring the dynamic evolution of volcanic centers, which is crucial for understanding the stages in a volcano’s eruptive cycle.</p> |
first_indexed | 2024-04-10T05:56:12Z |
format | Article |
id | doaj.art-728397738c674dbb99a6051fe559e6eb |
institution | Directory Open Access Journal |
issn | 1561-8633 1684-9981 |
language | English |
last_indexed | 2024-04-10T05:56:12Z |
publishDate | 2023-03-01 |
publisher | Copernicus Publications |
record_format | Article |
series | Natural Hazards and Earth System Sciences |
spelling | doaj.art-728397738c674dbb99a6051fe559e6eb2023-03-03T14:33:08ZengCopernicus PublicationsNatural Hazards and Earth System Sciences1561-86331684-99812023-03-0123991100610.5194/nhess-23-991-2023Multi-station automatic classification of seismic signatures from the Lascar volcano databaseP. Salazar0P. Salazar1P. Salazar2F. Yupanqui3F. Yupanqui4C. Meneses5S. Layana6G. Yáñez7Millennium Institute on Volcanic Risk Research – Ckelar Volcanoes, Avenida Angamos 0610, 1270709 Antofagasta, ChileDepartamento de Ciencias Geológicas, Universidad Católica del Norte, Avenida Angamos 0610, 1270709 Antofagasta, ChileCentro de Investigación para la Gestión Integrada del Riesgo de Desastres (CIGIDEN), Avenida Vicuña Mackenna 4860, 7820436 Santiago, ChileMillennium Institute on Volcanic Risk Research – Ckelar Volcanoes, Avenida Angamos 0610, 1270709 Antofagasta, ChilePrograma de Doctorado en Ingeniería Sustentable, Universidad Católica del Norte, Avenida Angamos 0610, 1270709 Antofagasta, ChileDepartamento de Ingeniería de Sistemas y Computación, Universidad Católica del Norte, Avenida Angamos 0610, 1270709 Antofagasta, ChileMillennium Institute on Volcanic Risk Research – Ckelar Volcanoes, Avenida Angamos 0610, 1270709 Antofagasta, ChileDepartamento de Ingeniería Estructural y Geotécnica, Pontificia Universidad Católica de Chile, Avenida Vicuña Mackenna 4860, 7820436 Santiago, Chile<p>This study was aimed to build a multi-station automatic classification system for volcanic seismic signatures such as hybrid, long period, tremor, tectonic, and volcano–tectonic events. This system was based on a probabilistic model made using transfer learning, which has, as the main tool, a pre-trained convolutional network named AlexNet. We designed five experiments using different datasets with data that were real, synthetic, two different combinations of these (combined 1 and combined 2), and a balanced subset without synthetic data. The experiment presented the highest scores when a process of data augmentation was introduced into processing sequence. Thus, the lack of real data in some classes (imbalance) dramatically affected the quality of the results, because the learning step (training) was overfitted to the more numerous classes. To test the model stability with variable inputs, we implemented a <span class="inline-formula"><i>k</i></span>-fold cross-validation procedure. Under this approach, the results reached high predictive performance, considering that only the percentage of recognition of the tectonic events (TC) class was partially affected. The results obtained showed the performance of the probabilistic model, reaching high scores over different test datasets. The most valuable benefit of using this technique was that the use of volcano seismic signals from multiple stations provided a more generalizable model which, in the near future, can be extended to multi-volcano database systems. The impact of this work is significant in the evaluation of hazard and risk by monitoring the dynamic evolution of volcanic centers, which is crucial for understanding the stages in a volcano’s eruptive cycle.</p>https://nhess.copernicus.org/articles/23/991/2023/nhess-23-991-2023.pdf |
spellingShingle | P. Salazar P. Salazar P. Salazar F. Yupanqui F. Yupanqui C. Meneses S. Layana G. Yáñez Multi-station automatic classification of seismic signatures from the Lascar volcano database Natural Hazards and Earth System Sciences |
title | Multi-station automatic classification of seismic signatures from the Lascar volcano database |
title_full | Multi-station automatic classification of seismic signatures from the Lascar volcano database |
title_fullStr | Multi-station automatic classification of seismic signatures from the Lascar volcano database |
title_full_unstemmed | Multi-station automatic classification of seismic signatures from the Lascar volcano database |
title_short | Multi-station automatic classification of seismic signatures from the Lascar volcano database |
title_sort | multi station automatic classification of seismic signatures from the lascar volcano database |
url | https://nhess.copernicus.org/articles/23/991/2023/nhess-23-991-2023.pdf |
work_keys_str_mv | AT psalazar multistationautomaticclassificationofseismicsignaturesfromthelascarvolcanodatabase AT psalazar multistationautomaticclassificationofseismicsignaturesfromthelascarvolcanodatabase AT psalazar multistationautomaticclassificationofseismicsignaturesfromthelascarvolcanodatabase AT fyupanqui multistationautomaticclassificationofseismicsignaturesfromthelascarvolcanodatabase AT fyupanqui multistationautomaticclassificationofseismicsignaturesfromthelascarvolcanodatabase AT cmeneses multistationautomaticclassificationofseismicsignaturesfromthelascarvolcanodatabase AT slayana multistationautomaticclassificationofseismicsignaturesfromthelascarvolcanodatabase AT gyanez multistationautomaticclassificationofseismicsignaturesfromthelascarvolcanodatabase |