Application of Artificial Intelligence to Determined Unconfined Compressive Strength of Cement-Stabilized Soil in Vietnam

Cement stabilized soil is one of the commonly used as ground reinforcement solutions in geotechnical engineering. In this study, main object was to apply three machine learning (ML) methods namely gradient boosting (GB), artificial neural network (ANN) and support vector (SVM) predict unconfined compressive strength (UCS) cement soil. Soil samples were collected at Hai Duong city, Vietnam. A total 216 soil–cement mixed laboratory compressed determine UCS. This data set divided into two parts training (80%) testing (20%) build test model, respectively. To verify performance ML various criteria named correlation coefficient (R), mean absolute error (MAE) root square (RMSE) used. The results show that all models effective UCS cement-stabilized Amongst model optimized ANN provided superior compare others with indicator R = 0.925, RMSE 419.82 MAE 292.2 for part. study can provide an tool quickly high accuracy.