No abstract

Abstract.The results of the application of an unsupervised learning (neural network) approach comprising a Self Organizing Map (SOM), to distinguish micro-earthquakes from quarry blasts in the vicinity of Istanbul, Turkey, are presented and discussed. The SOM is constructed as a neural classifier and complementary reliability estimator to distinguish seismic events, and was employed for varying map sizes. Input parameters consisting of frequency and time domain data (complexity, spectral ratio, S/P wave amplitude peak ratio and origin time of events) extracted from the vertical components of digital seismograms were estimated as discriminants for 179 (1.8 < M d < 3.0) local events. The results show that complexity and amplitude peak ratio parameters of the observed velocity seismogram may suffice for a reliable discrimination, while origin time and spectral ratio were found to be fuzzy and misleading classifiers for this problem. The SOM discussed here achieved a discrimination reliability that could be employed routinely in observatory practice; however, about 6% of all events were classified as ambiguous cases. This approach was developed independently for this particular classification, but it could be applied to different earthquake regions.

Abstract. Two unsupervised pattern recognition algorithms, k-means, and Gaussian mixture model (GMM) analyses have been applied to classify seismic events in the vicinity of Istanbul. Earthquakes, which are occurring at different seismicity rates and extensions of the Thrace-Eskisehir Fault Zone and the North Anatolian Fault (NAF), Turkey, are being contaminated by quarries operated around Istanbul. We have used two time variant parameters, complexity, the ratio of integrated powers of the velocity seismogram, and S/P amplitude ratio as classifiers by using waveforms of 179 events (1.8 < M < 3.0). We have compared two algorithms with classical multivariate linear/quadratic discriminant analyses. The total accuracies of the models for GMM, k-means, linear discriminant function (LDF), and quadratic discriminant function (QDF) are 96.1 %, 95.0 %, 96.1 %, 96.6 %, respectively. The performances of models are discussed for earthquakes and quarry blasts separately. All methods clustered the seismic events acceptably where QDF slightly gave better improvements compared to others. We have found that unsupervised clustering algorithms, for which no a-prior target information is available, display a similar discriminatory power as supervised methods of discriminant analysis.

No abstract

No abstract