Publicado

2017-01-01

Hacia un sistema de detección automática de señales del volcán Cotopaxi

Towards an automatic detection system of signals at cotopaxi volcano

Palabras clave:

Descomposición multinivel wavelet, árbol de decisión, extracción de características, detección de eventos sísmicos (es)
Multilevel decomposition wavelet, decision tree, feature extraction, seismic event detection (en)

Descargas

Autores/as

  • Roman Lara-Cueva Universidad de las Fuerzas Armadas-ESPE https://orcid.org/0000-0001-8848-9928
  • Valeria Paillacho-Salazar Universidad de las Fuerzas Armadas-ESPE
  • Michelle Villalva-Chaluisa Universidad de las Fuerzas Armadas-ESPE
Actualmente el Volcán Cotopaxi ha experimentado un incremento progresivo en su actividad sísmica, por lo que los especialistas requieren herramientas de alta eficiencia y confiabilidad para la monitorización volcánica. Este artículo presenta una detección basada en clasificación supervisada de los eventos sismo-volcánicos y no volcánicos registrados durante el año 2010. Nuestro algoritmo emplea cuatro características adquiridas por medio de la energía de los coeficientes de aproximación y detalle de la descomposición wavelet analizados con las familias Daubechies y Symlet. La clasificación de eventos fue realizada con el algoritmo de árboles de decisión empleando técnicas embebidas: validación cruzada y podamiento para una reducción del número de características. Los mejores resultados son obtenidos con la aplicación de la wavelet madre Symlet con una exactitud del 99% y una precisión de 98%.
Currently, Cotopaxi volcano has increased its seismic activity. Efficient and reliable tools are required for volcano monitoring, and early and effective emergency alerts are necessary. This article presents a supervised classification-based detection of seismic-volcanic and non-volcanic events recorded during 2010. Our algorithm use four features acquired using energy of approximation and detail coefficients of the wavelet decomposition analyzed with Daubechies and Symlet families. The classification of events was performed by the algorithm of decision trees with embedded techniques: cross-validation and pruning for reduction in the number features. The best results are obtained by application of the mother wavelet Symlet with accuracy of 99% and precision of 98%.

Descargas

Los datos de descargas todavía no están disponibles.

Citas

González, M., Jurado, E., González, S., Aguirre, O., Jiménez, J. and Návar-Cháidez, J.D.J., Cambio climático mundial: Origen y consecuencias. Ciencia UANL, 6(3), pp. 377-385, 2003.

Tilling, R. y Beate, B., Los peligros volcánicos. Apuntes breves sobre un curso breve. Organización Mundial de Observatorios Vulcanológicos, 1993. pp. 2-3.

Nugroho, A., and Winarko, E., Geographical information system and Web Service implementation for volcanic eruptions geologic disasters surveillance, monitoring, and mitigation system. International Conference on Electrical Engineering and Informatics (ICEEI), 2011. pp. 17-19. DOI: 10.1109/ICEEI.2011.6021766

Wener-Allen, G., Johnson J., Ruiz, M. and Lees, J., Monitoring volcanic eruptions with a wireless sensor network, Wireless Sensor Networks, 2005. Workshop on Proceeedings of the Second European, 2005. pp. 108-120. DOI: 10.1109/EWSN.2005.1462003

Wassermann, J., Volcano seismology. Fürstenfeldbruck, Geophysikalisches Observatorium der Ludwig-Maximilians Universität München, 2011. pp. 1-67.

Arciniega-Ceballos, A., Chouet, B. and Dawson, P., Long-period events and tremor at Popocatepetl volcano (1994-2000) and their broadband characteristics. Bulletin of Volcanology, 65(2), pp. 124-135, 2003. DOI: 10.1007/s00445-002-0248-8

Ibs-von Seht, M., Detection and identification of seismic signals recorded at Krakatau volcano (Indonesia) using artificial neural networks, Journal of Volcanology and Geothermal Research, 176(4), pp. 448-456, 2008. DOI: 10.1016/j.jvolgeores.2008.04.015

Curilem, G., Vergara, J., Fuentealba, G., Acuña, G. and Chacón, M., Classification of seismic signals al Villarrica volcano (Chile) using neural networks and genetic algorithms. Journal of Volcanology and Geothermal Research, 180(1), pp. 1-8, 2009. DOI: 10.1016/j.jvolgeores.2008.12.002

Celik, E., Atalay, M. and Bayer, H. Earthquake prediction using seismic bumps with Artificial Neural Networks and Support Vector Machines. Signal Processing and Communications Applications Conference (SIU), 2014. pp. 730-733. DOI: 10.1109/SIU.2014.6830333

Doroslovacki, M., Discrete-time signals and uncertainty relations involving ordinary second moments in time and frequency. Proceedings of the IEEE-SP International Symposium on Time-Frequency and Time-Scale Analysis, 1994. pp. 186-189. DOI: 10.1109/TFSA.1994.467262

Ahuja, N., Lertrattanapanich, S. and Bose, N., Properties determining choice of mother wavelet. IEE Proceedings-Vision, Image and Signal Processing, 152(5), pp. 659-664, 2005. DOI: 10.1049/ip-vis:20045034

Magotra, N., Nalley, D. and Brozek, J., Seismic event detection using three-component data. IEEE Transactions on Geoscience and Remote Sensing, 30(3), pp. 642-644, 1992. DOI: 10.1109/36.142949

Gabarda, S. and Cristóbal, G., Detection of events in seismic time series by time–frequency methods. Signal Processing, IET, 4(4), pp. 413-420, 2010. DOI: 10.1049/iet-spr.2009.0125

Thanasopoulos, I.A. and Avaritsiotis, J.N., Seismic detection and time of arrival estimation in noisy environments based on the haar wavelet transform. Sensor Array and Multichannel Signal Processing Workshop, 2008. SAM 2008. 5th IEEE, Darmstadt, 2008. pp. 433- 436. DOI: 10.1109/SAM.2008.4606906

Lara-Cueva, R.A., Benítez, D.S., Carrera, E.V., Ruiz, M. and Rojo-Álvarez, J.L., Automatic recognition of long period events from volcano tectonic earthquakes at Cotopaxi volcano. IEEE Transactions on Geoscience and Remote Sensing, 54(9), pp. 5247-5257, 2016. DOI: 10.1109/TGRS.2016.2559440

Hurtado, J.E., Henao, R. y Castellanos G. Clasificación de señales sísmicas por medio de onditas y máquinas de soporte vectorial. Universidad Nacional de Colombia. Colombia. Observatorio Sismológico de Quindio. Colombia. INGEOMINAS. sfsl CO, 2002.

Gutiérrez, L., Ibáez, J., Cortes, G., Ramírez, J., Benítez, C., Tenorio, V. and Isaac, A., Volcano-seismic signal detection and classification processing using hidden Markov models. Application to San Cristóbal volcano, Nicaragua. Geoscience and Remote Sensing Symposium, 2009 IEEE International, IGARSS 2009, pp. 12-17. DOI: 10.1109/IGARSS.2009.5417428

Hoffman, A., Hoogenboezem, C., van der Merwe, N. and Tollig, J.A. Seismic buffer recognition using wavelet based features. Geoscience and Remote Sensing Symposium Proceedings, 1998 IEEE International, IGARSS 1998, pp. 1333-1335. DOI: 10.1109/IGARSS.1998.691399

Andrade, D., Hall, M., Mothes, P., Troncoso, L., Eissen, J., Samaniego, P., Egred, J., Ramón, P., Rivero, D. y Yepes, H., Los peligros volcánicos asociados con el Cotopaxi. Corporación Editorial Nacional, 2005.

Salazar, D. y D´Ercole, D., Percepción del riesgo asociado al volcán Cotopaxi y vulnerabilidad en el Valle de Los Chillos (Ecuador), l’Institut Français d’Études Andines, 38 (3), pp. 849-871, 2009.

Rivera, K., Mapa de periodos predominantes del suelo del área urbana de la ciudad de Loja (Ecuador), obtenidos a partir de medidas de ruido ambiental, Tesis, Departamento de Geología y Minas, Universidad Técnica Particular de Loja, Loja, Ecuador, 2013.

Cortes, G., Benitez, M., García, L., Álvarez, I., Ibánez, J., A comparative study of dimensionality reduction algorithms applied to volcano-seismic signals. Journal of Selected Topics in Applied Earth Observations and Remote Sensing, (99), pp. 1-11, 2015. DOI: 10.1109/JSTARS.2015.2479300

Chouet, B., Page, R., Stephens, C, Lahr, J. and Power, J., Precursory swarms of long-period events at Redoubt volcano (1989–1990), Alaska: Their origin and use as a forecasting tool. Journal of Volcanology and Geothermal Research, 62(1), pp. 95-135, 1994. DOI: 10.1016/0377-0273(94)90030-2

Burrus, C., Gopinath, R. and Guo, H., Introduction to wavelets and wavelet transforms: A primer, Prentice-Hall International, 1997.

Mojsilovic, A., Popovic, M. and Rackov, D., On the selection of an optimal wavelet basis for texture characterization. IEEE Transactions on Image Processing, 9(12), pp. 2043-2050, 2000. DOI: 10.1109/83.887972

Bishop, C., Pattern recognition and machine learning, Springer, 2006.

Landgrebe, D., A survey of decision tree classifier methodology. IEEE transactions on Systems, Man and Cybernetics, 21(3), pp. 660-674, 1991. DOI: 10.1109/21.97458

Magerman, D., Statistical decision-tree models for parsing. Proceedings of the 33rd annual meeting on Association for Computational Linguistics, pp. 276-283, 1995. DOI: 10.3115/981658.981695

Dougherty, G., Pattern recognition and classification: An introduction. Springer Science & Business Media, 2012.

Esposito, F., Malerba, D., Semeraro, G. and Kay, J., A comparative analysis of methods for pruning decision trees, IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(5), pp. 476-491, 1997. DOI: 10.1109/34.589207

Dai, Q., A competitive ensemble pruning approach based on cross-validation, Knowledge-Based Systems, 37, pp. 394-414, 2013. DOI: 10.1016/j.knosys.2012.08.024