Developing bearing capacity model for geogrid-reinforced stone columns improved soft clay utilizing MARS-EBS hybrid method

Abstract

Because of the complicated geometry and a lack of knowledge about the parameters that impact it, estimating the ultimate bearing capacity (qrs) of a geogrid-reinforced sandy bed on vertical stone columns in soft clay is challenging. In practical applications, developing an accurate prediction model can be beneficial due to the difficulty and expense of estimating qrs. The objective of this study is to develop a model for predicting the bearing capacity of geogrid-reinforced stone columns using Multivariate Adaptive Regression Splines (MARS) and Escaping Bird Search optimization algorithm (EBS). In order to accomplish this, 219 constructed experimental samples were used. Feature selection based on the Neighborhood Component Analysis (NCA) method showed that due to the strong correlation between undrained shear strength of unreinforced clay (qu) and the ratio of stone columns distance to foundation diameter (s/D) variables, only qu should be included in the modeling. A developed model for estimating the bearing capacity was found to have coefficients of determination (R2) of 0.997 for training, 0.993 for testing, and 0.995 for total data. This study confirms that the undrained shear strength of unreinforced clay (qu) is the most essential input parameter for assessing bearing capacity, while the the ratio of sandy bed thickness to foundation diameter (t/D) is the least essential input parameter. In addition, the parametric analysis shows that increasing all input parameters increases bearing capacity.