AN INTERPOLATION APPLIED WITH BARRIERS MODELING TO PREDICTIONS OF EARTHQUAKE OCCURRENCES USING KERNEL SMOOTHING AND DIFFUSION KERNEL METHODS IN THE MARMARA SEA, TURKEY

In this study, interpolation with barriers applied modeling to predictions of earthquake occurrences using Kernel Smoothing and Diffusion Kernel Methods in the Marmara Sea, Turkey. We used the instrumental and historical catalog for all Ms magnitudes. Kernel methods give a systematic and principled approach to training learning and the good generalization performance achieved can be readily justi?ed using statistical learning theory. Kernel Interpolation with Barriers is a moving window predictor that uses the shortest distance between points so that points on either side of the line barriers are connected. Additionally, Kernel interpolation is a variant of a first-order local polynomial interpolation in which instability in the calculations is prevented using a method similar to the one used in the ridge regression to estimate the regression coefficients. So, the bandwidth of the kernel is determined by a rectangle around the observations. We applied two different Kernel Function (Exponential and Gaussian) with this methods. Respectively, we used e^(-3(r/h)) and e^(-3?(r/h)?^2 )basis formulas in this methods. We are obtained low, medium, high estimations for predictions of earthquake occurrences by taking the faults barrier in each seismogenic source zones. Consequently, we determined an interpolation applied with barriers for making predictions of earthquake occurrences using different Kernel methods in the Marmara Sea. This study, scientists will be benefited to examined of next earthquakes and predictions of earthquake occurrences in Turkey.