Prediction of Peak Ground Acceleration by Artificial Neural Network and Adaptive Neuro-fuzzy Inference System

An attenuation relationship model belonging to a region with high earthquake hazard is important. It used for engineering studies know how the peak ground acceleration (PGA) value depends on distance where there are no stations. This study earthquakes magnitudes greater than 4 that IzmirNET recorded between 2009 and 2017 determine PGA through an artificial neural network (ANN) adaptive neuro-fuzzy inference system (ANFIS), which widely applied in seismology studies. For this purpose, 2925 records from 62 were analysed ANN ANFIS applications. Magnitude, focal depth, hypocentral (Rhyp), site conditions comprise inputs, values outputs. Using Karaburun earthquake, we compared models using different motion prediction equations (GMPE) appropriate criteria. We determined proximate measured at stations of was M = 6.2 2017, test ANFIS. The results examined indicated good candidates obtaining future studied area. In addition, subsequent can be calculated more quickly without any preliminary evaluation