Weibull-Exponential mixture model: A novel approach to predict the earthquake recurrence intervals

Predicting the recurrence intervals of earthquakes is very important in terms of earth sciences. Probability distributions are used to calculate these recurrence intervals. Since destructive earthquakes are defined as rare events, it is important that the distributions to model these data sets have a thick-tailed structure in order to represent the relevant data correctly. In this study, the Weibull-Exponential mixture model is developed and an application study is conducted for the Marmara Region. The statistical properties of the developed model are discussed comprehensively and a simulation study regarding parameter estimates is included. Recurrence intervals are calculated under the Weibull-Exponential mixture model and compared with Weibull-type distributions. It has been observed that the proposed model gives better results than other Weibull type distributions.