Intelligent Prediction Models For UCS Of Cement/Lime Stabilized QLD Soil

The study aims to develop proposed predictive formulas for determining the unconfined compression strength (UCS) of cement/lime stabilized Queensland soil based on Multi-Gene Genetic Programming (MGGP) and Artificial Neural Network (ANN). models evaluate effect three independent variables, including binder type (cement lime), content, curing time, UCS soil. results show that selected optimal MGGP ANN can predict target values with high correlation coefficients (R-value approximately 0.992 0.998, respectively), low errors (e.g., RMSE MAE). sensitivity analysis provide same results, in which time has greatest influence value, followed by content type. performances are compared statistical parameters, several external criteria, distribution properties. finds both their generalization capabilities robust, powerful, accurate prediction ability; however, model slightly outperforms model. equations formulated from could help engineers consultants choose suitable reasonable amount pre-planning pre-design period.