Prediction of Resilient Modulus of Granular Subgrade Soils and Subbase Materials using Artificial Neural Network

ABSTRACT Experimental estimation of the modulus is excessively costly and complex owing to the large number of factors that affects the modulus. Thus, it is necessary to determine the resilient modulus of granular pavement materials such as subgrade soils and subbase materials from an empirical model for the design of a lower level pavement system. In this study, ANN (Artificial Neural Network) models were used to develop an empirical model for the resilient modulus of subgrade soils and subbase materials from basic material properties and in-situ conditions related to stresses in reference to data obtained from tests conducted in this study. It can be concluded that the ANN models serve as a reliable and simple predictive tool for the resilient modulus of granular subgrade soils and subbase materials.