Explainable artificial intelligence model for the prediction of undrained shear strength
Ho-Hong-Duy Nguyen, Thanh‐Nhan Nguyen, Thi-Anh-Thu Phan, Ngoc-Thi Huynh, Quoc-Dat Huynh, Tan-Tai Trieu
Abstract
• An explainable machine learning model was first applied to explain the prediction of undrained shear strength. • The results indicate that the relationship between undrained shear strength and the input features involves complex, non-linear interactions. • Pre-consolidation stress has the most significant impact on the prediction of undrained shear strength. Machine learning (ML) models are widely used for predicting undrained shear strength (USS), but interpretability has been a limitation in various studies. Therefore, this study introduced shapley additive explanations (SHAP) to clarify the contribution of each input feature in USS prediction. Three ML models, artificial neural network (ANN), extreme gradient boosting (XGBoost), and random forest (RF), were employed, with accuracy evaluated using mean squared error, mean absolute error, and coefficient of determination ( R 2 ). The RF achieved the highest performance with an R 2 of 0.82. SHAP analysis identified pre-consolidation stress as a key contributor to USS prediction. SHAP dependence plots reveal that the ANN captures smoother, linear feature-output relationships, while the RF handles complex, non-linear interactions more effectively. This suggests a non-linear relationship between USS and input features, with RF outperforming ANN. These findings highlight SHAP’s role in enhancing interpretability and promoting transparency and reliability in ML predictions for geotechnical applications.