Energy-based probabilistic evaluation of soil liquefaction

This paper presents a seismic wave energy-based method with back-propagation neural networks to assess the liquefaction probability. An empirical equation and Fourier spectrum of acceleration are employed, respectively, to calculate the seismic wave energy. Discriminant analysis is used to determine the equation of the boundary curve separating the data points with and without liquefaction. The proposed method shows capability in evaluating the probability of soil liquefaction based on the boundary curve and a logarithm normal distribution.