Feature Extraction Using Circular Statistics Applied to Volcano Monitoring

In this work, the applicability of the circular statistics to feature extraction on seismic signals is presented. The seismic signals are captured from Llaima Volcano, located in Southern Andes Volcanic Zone at 38°40'S 71°40'W. Typically, the seismic signals can be divided in long-period, tremor, and volcano-tectonic earthquakes. The seismic signals are time-segmented using a rectangular window of 1 minute of duration. In each segment, the instantaneous phase is calculated using the Hilbert Transform, and then, one feature is obtained. Thus, the principal hypothesis of this work is that the instantaneous phase can be assumed as a circular random variable in [0, 2π) interval. A second feature is obtained using the wavelet transform due to the fact that seismic signals present high energy located in low frequency. Then, in the range 1.55 and 3.11 Hz the wavelet coefficients were obtained and their mean energy is calculated as the second feature. Real seismic data represented using this two features are classified using a linear discriminant with a 92.5% of correct recognition rate.

[1]  Julio J. Valdés,et al.  Computational intelligence in earth sciences and environmental applications: Issues and challenges , 2006, Neural Networks.

[2]  S. R. Jammalamadaka,et al.  Topics in Circular Statistics , 2001 .

[3]  Nicholas I. Fisher,et al.  Statistical Analysis of Circular Data , 1993 .

[4]  Khaled H. Hamed,et al.  Time-frequency analysis , 2003 .

[5]  Takeshi Minakami,et al.  Seismology of Volcanoes in Japan , 1974 .

[6]  Sven Loncaric,et al.  Earthquake - explosion discrimination using genetic algorithm-based boosting approach , 2010, Comput. Geosci..

[7]  Maria Marinaro,et al.  Automatic Classification of Seismic Signals at Mt. Vesuvius Volcano, Italy, Using Neural Networks , 2005 .

[8]  S. Mallat A wavelet tour of signal processing , 1998 .

[9]  Renato Campanini,et al.  Synopsis of supervised and unsupervised pattern classification techniques applied to volcanic tremor data at Mt Etna, Italy , 2009 .

[10]  H. Langer,et al.  Automatic classification and a-posteriori analysis of seismic event identification at Soufriere Hills volcano, Montserrat , 2006 .

[11]  P. Sprent,et al.  Statistical Analysis of Circular Data. , 1994 .

[12]  Jerome Mars,et al.  Applications of autoregressive models and time–frequency analysis to the study of volcanic tremor and long-period events , 2002 .

[13]  A. Mazzarella,et al.  Neural forecasting of seismicity and ground displacements in different volcanic areas , 2004 .

[14]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[15]  Balgobin Nandram,et al.  An empirical bayes estimator of seismic events using wavelet packet bases , 2001 .

[16]  Claudio Agostinelli,et al.  circular: Circular Statistics, from "Topics in circular Statistics" (2001) S. Rao Jammalamadaka and A. SenGupta, World Scientific. , 2004 .

[17]  Silvia Scarpetta,et al.  Support Vector Machines and MLP for automatic classification of seismic signals at Stromboli volcano , 2009, WIRN.

[18]  Max Chacón,et al.  Classification of seismic signals at Villarrica volcano (Chile) using neural networks and genetic algorithms , 2009 .

[19]  R. Schick Volcanic tremor-source mechanisms and correlation with eruptive activity , 1988 .

[20]  Vladimir Cherkassky,et al.  The Nature Of Statistical Learning Theory , 1997, IEEE Trans. Neural Networks.

[21]  Guillermo Cortés,et al.  The classification of seismo-volcanic signals using Hidden Markov Models as applied to the Stromboli and Etna volcanoes , 2009 .

[22]  Jean-Claude Nunes,et al.  Hilbert Transform-Based ECG Modeling , 2005 .

[23]  Farid U. Dowla Neural Networks in Seismic Discrimination , 1996 .

[24]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[25]  Gordon Erlebacher,et al.  A Wavelet Toolkit for Visualization and Analysis of Large Data Sets in Earthquake Research , 2004 .