Development of a Model for Predicting the Resilient Modulus of Stabilized Clay Soils Using Artificial Neural Network

In road pavement design, soil resilient modulus is one of the factors that play a very important role in determining pavement thickness. In the past, determining the Resilient Modulus of soil directly from laboratory results has not always been practical due to its high costs, both in terms of equipment and labor. Therefore, it is possible to predict and determine this parameter based on past field data using artificial intelligence. Our goal in this paper is to develop a model for predicting the resilient modulus of stabilized clay soils using artificial neural networks. In this study, four different soil samples stabilized with additives, such as lime, fly ash, and cement kiln dust, were examined using the pavement design appendix of the AASHTO 2002 specification. By comparing the results to the laboratory data based on the statistical indicators such as regression coefficient (0.99), root mean square error (less than 6 percent), we found that the artificial neural network was highly accurate in predicting the resilient modulus..