Effects of binder types and other significant variables on the unconfined compressive strength of chemical-stabilized clayey soil using gene-expression programming

Abstract Soil stabilization is an in situ soil treatment which soils are mixed with cementitious or other chemical stabilizing agents. Determining the unconfined compressive strength (UCS) of stabilized a principal task design and construction ground improvement. Hence, this study aims to develop reliable predictive model for UCS clay common binders using gene-expression programming (GEP) technique. Eleven parameters, including characteristics, binder types, contents, mixing method, curing period, were considered as independent variables model. The research results show that selected optimal GEP-based performs well acceptable correlation coefficient ( R = 0.951) low errors (e.g., RMSE MAE). Besides, parametric analyses indicate plastic index, percentage clay, total water content have negative effect on soil. In contrast, silt sand, time positive addition, could be significantly enhanced by combining cement slag, lime, fly ash reasonable ratio, reducing natural findings help engineers choose suitable types cost-effective methods optimize clay.