Seismic Liquefaction Resistance Based on Strain Energy Concept Considering Fine Content Value Effect and Performance Parametric Sensitivity Analysis

Liquefaction is one of the most destructive phenomena caused by earthquakes, which has been studied in the issues of potential, triggering and hazard analysis. The strain energy approach is a common method to investigate liquefaction potential. In this study, two Artificial Neural Network (ANN) models were developed to estimate the liquefaction resistance of sandy soil based on the capacity strain energy concept (W) by using laboratory test data. A large database was collected from the literature. One group of the dataset was utilized for validating the process in order to prevent overtraining the presented model. To investigate the complex influence of fine content (FC) on liquefaction resistance, according to previous studies, the second database was arranged by samples with FC of less than 28% and was used to train the second ANN model. Then, two presented ANN models in this study, in addition to four extra available models, were applied to an additional 20 new samples for comparing their results to show the capability and accuracy of the presented models herein. Furthermore, a parametric sensitivity analysis was performed through Monte Carlo Simulation (MCS) to evaluate the effects of parameters and their uncertainties on the liquefaction resistance of soils. According to the results, the developed models provide a higher accuracy prediction performance than the previously published models. The sensitivity analysis illustrated that the uncertainties of grading parameters significantly affect the liquefaction resistance of soils.