A Machine Learning Approach for Improving the Detection Capabilities at 3C Seismic Stations

We apply and evaluate a recent machine learning method for the automatic classification of seismic waveforms. The method relies on Dynamic Bayesian Networks (DBN) and supervised learning to improve the detection capabilities at 3C seismic stations. A time-frequency decomposition provides the basis for the required signal characteristics we need in order to derive the features defining typical “signal” and “noise” patterns. Each pattern class is modeled by a DBN, specifying the interrelationships of the derived features in the time-frequency plane. Subsequently, the models are trained using previously labeled segments of seismic data. The DBN models can now be compared against in order to determine the likelihood of new incoming seismic waveform segments to be either signal or noise. As the noise characteristics of seismic stations varies smoothly in time (seasonal variation as well as anthropogenic influence), we accommodate in our approach for a continuous adaptation of the DBN model that is associated with the noise class. Given the difficulty for obtaining a golden standard for real data (ground truth) the proof of concept and evaluation is shown by conducting experiments based on 3C seismic data from the International Monitoring Stations, BOSA and LPAZ.

[1]  Christopher John Young,et al.  A comparison of select trigger algorithms for automated global seismic phase and event detection , 1998, Bulletin of the Seismological Society of America.

[2]  Roberto Carniel,et al.  Continuous Hidden Markov Models: Application to automatic earthquake detection and classification at Las Canãdas caldera, Tenerife , 2008 .

[4]  K. Nanjo,et al.  Analysis of the completeness magnitude and seismic network coverage of Japan , 2010 .

[5]  F. Scherbaum,et al.  Unsupervised feature selection for pattern search in seismic time series , 2008 .

[6]  Seismic threshold monitoring for continuous assessment of global detection capability , 1999 .

[7]  Geoffrey Zweig,et al.  The graphical models toolkit: An open source software system for speech and time-series processing , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[8]  Jeff A. Bilmes,et al.  What HMMs Can Do , 2006, IEICE Trans. Inf. Syst..

[9]  Geoffrey Zweig,et al.  Speech Recognition with Dynamic Bayesian Networks , 1998, AAAI/IAAI.

[10]  C. Hammer,et al.  A Seismic‐Event Spotting System for Volcano Fast‐Response Systems , 2012 .

[11]  F. Ringdal,et al.  Optimized Seismic Threshold Monitoring – Part 1: Regional Processing , 2002 .

[12]  T. C. Bache,et al.  The Intelligent Monitoring System , 1990 .

[13]  Gardar Johannesson,et al.  Incorporation of probabilistic seismic phase labels into a Bayesian multiple-event seismic locator , 2008 .

[14]  F. Ringdal,et al.  The detection of low magnitude seismic events using array-based waveform correlation , 2006 .

[15]  Andreas Rietbrock,et al.  Optimized automatic pickers: application to the ANCORP data set , 2010 .

[16]  Toshiro Tanimoto,et al.  Seasonality in particle motion of microseisms , 2006 .

[17]  Geoffrey Zweig,et al.  Bayesian network structures and inference techniques for automatic speech recognition , 2003, Comput. Speech Lang..

[18]  E. Hauksson,et al.  Earthquake Monitoring in Southern California for Seventy-Seven Years (1932-2008) , 2010 .

[19]  Frank Scherbaum,et al.  Dynamic Bayesian Networks for Real-Time Classification of Seismic Signals , 2007, PKDD.

[20]  J. Peterson,et al.  Observations and modeling of seismic background noise , 1993 .

[21]  T. C. Bache,et al.  Knowledge-based interpretation of seismic data in the Intelligent Monitoring System , 1993 .