Discriminating seismic events of the Llaima volcano (Chile) based on spectrogram cross-correlations
| Primer Autor |
Araujo Rios, Ricardo
|
| Co-autores |
Curilem, Millaray#de Mello, Rodrigo Fernandes#Huenupan, Fernando#San Martin, Cesar#Franco, Luis#Hernandez, Erasmo
|
| Título |
Discriminating seismic events of the Llaima volcano (Chile) based on spectrogram cross-correlations
|
| Editorial |
ELSEVIER SCIENCE BV
|
| Revista |
JOURNAL OF VOLCANOLOGY AND GEOTHERMAL RESEARCH
|
| Lenguaje |
en
|
| Resumen |
The surveillance of active volcanoes around the world has become a critical security issue for many countries, requiring a continuous monitoring of seismic signals. By analyzing such signals, we intend to understand volcanic activities (e.g. explosions, eruptions and depressurization) and take decisions to reduce the effects and damages to the economy and society of nearby regions. Active volcanoes constantly produce signals, which may then be characterized as data streams, making impractical the presence of specialists to monitor and label every activity. To overcome this drawback, we present a new and straightforward approach to discriminate volcano seismic signals using spectrogram cross-correlations (SPCC) in conjunction with the K-Nearest Neighbors algorithm, a supervised machine learning strategy. Experiments were performed on signals collected from the Llaima volcano (Chile), and results confirmed the ability of our approach to discriminate events with a sensitivity over 95% for three out of the five classes considered. (C) 2018 Elsevier B.V. All rights reserved.
|
| Tipo de Recurso |
Artículo original
|
| Description |
The authors would like to thank the FONDEF IDeA 1T15I10027 project for financing part of the study, the PNPD/CAPES for supporting the postdoctoral position in the dept of Computer Science at Federal University of Bahia and the OVDAS for providing the datasets.
Los autores agradecen al proyecto FONDEF IDeA 1T15I10027 por financiar parte del estudio, al PNPD/CAPES por el apoyo al puesto postdoctoral en el Departamento de Computación de la Universidad Federal de Bahía y al OVDAS por proporcionar los conjuntos de datos.
|
| doi |
10.1016/j.jvolgeores.2018.10.023
|
| Formato Recurso |
pdf
|
| Palabras Claves |
Volcano monitoring# Pattern recognition# Seismic spectrograms# Volcano-seismic events processing
|
| Ubicación del archivo |
http://dx.doi.org/10.1016/j.jvolgeores.2018.10.023
|
| Categoría OCDE |
Geosciences, Multidisciplinary
|
| Materias |
Monitoreo de volcanes# Reconocimiento de patrones# Espectrogramas sísmicos# Procesamiento de eventos volcánico-sísmicos.
|
| Disciplinas de la OCDE |
Vulcanología
Ciencias de la Computación
Geociencias
|
| Id de Web of Science |
WOS:000451493100006
|
| Título de la cita (Recomendado-único) |
Discriminating seismic events of the Llaima volcano (Chile) based on spectrogram cross-correlations
|
| Identificador del recurso (Mandatado-único) |
Artículo original
|
| Versión del recurso (Recomendado-único) |
version publicada
|
| Editorial |
ELSEVIER SCIENCE BV
|
| Revista/Libro |
JOURNAL OF VOLCANOLOGY AND GEOTHERMAL RESEARCH
|
| Categoría WOS |
Geociencias, Multidisciplinar
|
| ISSN |
0377-0273
|
| Idioma |
en
|
| Referencia del Financiador (Mandatado si es aplicable-repetible) |
ANID FONDEF IDeA IT15I10028#Universidad de Bahía
ANID FONDEF IDeA 1T15I10027
PNPD/CAPES
|
| Descripción |
The authors would like to thank the FONDEF IDeA 1T15I10027 project for financing part of the study, the PNPD/CAPES for supporting the postdoctoral position in the dept of Computer Science at Federal University of Bahia and the OVDAS for providing the datasets.
|
| Formato |
pdf
|
| Tipo de ruta |
hibrida#verde
|
| Access Rights |
metadata
|
| Derechos de acceso |
metadata
|
| Página de inicio (Recomendado-único) |
186
|
| Página final (Recomendado-único) |
195
|
- Colecciones
- Colección Publicaciones Científicas
cienciaabierta.ufro.cl
ciencia.abierta@ufrontera.cl