Predicting the Maximum Seismic Response of the Soil-Pile-Superstructure System Using Random Forests

摘要

ABSTRACT Seismic fragility analysis has been considered an efficient method for seismic performance assessment of soil-pile-superstructure systems (SPSSs). However, seismic fragility analysis based on widely used numerical methods often requires a significant investment of time. In this study, a new approach based on the random forest technique, which can be applied to fragility analysis, is proposed to accurately and efficiently predict the maximum seismic response of SPSSs. Moreover, based on the random forest technique, the velocity RMS is found to exhibit a stronger correlation with the maximum seismic response of SPSSs in liquefiable soils.