Sensitivity analysis on a multilayer perceptron model for recognizing liquefaction cases

Abstract

In this paper, a new approach is presented for quantifying the system sensitivity of key parameters influencing the recognition of field liquefaction cases in a multilayer perceptron neural network ( MLP model). A novel index, the average sensitivity factor, SF i , derived from the mathematical formulation of neural network is proposed to quantify the result of the sensitivity analysis. The SF i is a robust index of sensitivity analysis for the MLP model and can be used in the other problems not just in the recognition of field liquefaction problem. A well-trained MLP model is first developed to discriminate between the cases of liquefaction and non-liquefaction. Excellent performance and good generalization is achieved, with the higher recognition rate 98.9% in the training phase, 91.2% in testing phase and 96.6% on the overall cases. Using this model, the SF i values are then calculated and reveal that peak ground acceleration ( PGA) is the most sensitive factor in both the liquefaction and non-liquefaction cases. Earthquake parameters ( M w and PGA), the stress state parameters of the soil layer ( r d , σ V and σ v ′ ), and the soil resistance parameters ( SPT-N, C N , C E and FC) play approximately equal roles. The seismic demand factors ( M w , PGA, r d , σ V , and σ v ′ ) is more sensitive than the liquefaction resistance capacity factors ( SPT-N, C N , C E , and FC) in the two-class liquefaction recognition problem.