Probabilistic seismic hazard analysis of BPNN predicting PGA

Abstract

Abstract Probabilistic seismic hazard analysis (PSHA) is recognized as a reasonable method for quantifying seismic threats. Traditionally, the method ignores the effect of focal depth and in which the ground motion prediction equations (GMPEs) are applied to estimate the probability distribution associated with the possible motion levels induced by the site earthquakes, but it is limited by the unclear geological conditions, which makes it difficult to give a uniform equation, and the equation cannot express the nonlinear relationship in geological conditions. Hence, this paper proposes a method to consider the seismic focal depth for the PSHA with the example of California, and use a back propagation neural network (BPNN) to predict peak ground acceleration (PGA) instead of the GMPEs. Firstly, the measured PGA and unknown PGA seismic data applicable to this method are collected separately. Secondly, the unknown PGA data are supplemented by applying the BPNN based on the measured PGA data. Lastly, based on the full-probability equation PSHA considering the focal depth is completed and compared with the current California seismic zoning results. The results show that using the BPNN in the PSHA can ensure computational accuracy and universality, making it more suitable for regions with the unclear geological structures and providing the possibility of adding other parameters to be considered for the influence of PSHA.