Improving Seismic Monitoring System for Small to Intermediate Earthquake Detection

Efficient and successful seismic event detection is an important and challenging issue in many disciplines, especially in tectonics studies and geo-seismic sciences. In this paper, we propose a fast, efficient, and useful feature extraction technique for maximally separable class events. Support vector machine classifier algorithm with an adjustable learning rate has been utilized to adaptively and accurately estimate small level seismic events. The algorithm has less computation, and thereby increased high economic impact on analyzing the database. Experimental results demonstrate the strength and robustness of the method.