Revolutionizing engineered cementitious composite materials (ECC): the impact of XGBoost-SHAP analysis on polyvinyl alcohol (PVA) based ECC predictions

Abstract

This study integrates previous experimental data and employs machine learning (ML) methods, including Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Network (ANN), and eXtreme Gradient Boosting (XGBoost), to predict the compressive strength (CS) and tensile strength (TS) of engineered cementitious composites (ECC). XGBoost emerged as the superior model among the four ML models, providing an interpretable and highly accurate predictive framework. To optimize the model performance, hyperparameter tuning using a fivefold cross-validation approach with the data divided into 80% training and 20% testing subsets. The Shapley Additive Explanations (SHAP) algorithm was also employed to reveal the impact of important features, such as the water/binder ratio, fly ash content, and water reducer dosage, on the model’s predictions and their interrelationships. The XGBoost demonstrates the most exemplary performance, as reflected in the R2 values of 0.92 and 0.97 for CS and TS testing, respectively. The SHAP analysis provided insights into the impact of individual features on CS and TS, shedding light on how specific characteristics influence the predictive accuracy of these properties. This highly accurate prediction model uncovers insights into correlated features, aids in creating new mix designs of ECC, and supports global efforts toward a low-carbon future in the construction industry by reducing carbon emissions.