Processing of earthquake catalog data of Western Turkey with artificial neural networks and adaptive neuro-fuzzy inference system

Turkey is one of several countries frequently facing significant earthquakes because of its geological and tectonic position on earth. Especially, graben systems of Western Turkey occur as a result of seismically quite active tensional tectonics. The prediction of earthquakes has been one of the most important subjects concerning scientists for a long time. Although different methods have already been developed for this task, there is currently no reliable technique for finding the exact time and location of an earthquake epicenter. Recently artificial intelligence (AI) methods have been used for earthquake studies in addition to their successful application in a broad spectrum of data intensive applications from stock market prediction to process control. In this study, earthquake data from one part of Western Turkey (37-39.30 degrees N latitude and 26 degrees-29.30 degrees E longitude) were obtained from 1975 to 2009 with a magnitude greater than M >= 3. To test the performance of AI in time series, the monthly earthquake frequencies of Western Turkey were calculated using catalog data from the region and then the obtained data set was evaluated with two neural networks namely as the multilayer perceptron neural networks (MLPNNs) and radial basis function neural networks (RBFNNs) and adaptive neuro-fuzzy inference system (ANFIS). The results show that for monthly earthquake frequency data prediction, the proposed RBFNN provides higher correlation coefficients with real data and smaller error values.