NEURAL NETWORKS AND DISCRIMINATION OF SEISMIC SIGNALS

Recent developments in algorithms and computer architecture make neura l networks a useful tool in designing pattern recognition systems. We show how a simple multilayer perceptron with 23 neurons can be trained easily and used to classify seismic signals. Applied to broadband sei smic signal, the perceptron permitted the recognition of different typ es of events on the basis of their frequency. Applied to a real-time, automatic, seismic data acquisition system, it saved more than 50% CPU time in a detection procedure.