Continuous earthquake detection and classification using discrete Hidden Markov Models

We present a novel technique to solve the automatic detection and classification problem of earth tremor in a single step by using Hidden Markov Modelling (HMM). While this technique was originally developed in speech recognition, it already showed great promise when applied to volcano induced seismic signals. We apply the HMM classifier to a much simpler problem, that is, the detection and distance dependent classification of small to medium sized earthquakes. Using the smaller and possibly not perfect data set of earthquakes recorded with three stations of the Bavarian Earthquake Service enables us to better evaluate the advantages and disadvantages of the proposed algorithm and to compare the results with simple and widely used detection techniques (e.g. recursive short-term versus long-term average). Overall the performance of HMM shows good results in the pre-triggered classification tasks and reasonable results in the continuous case. The application of HMMs is illustrated step by step so it can be used as recipe for other applications. Special emphasize is given to the important problem of selecting the features, which best describe the properties of the different signals that are to be classified.