Prediction of Compressive Strength for Recycled Rubber Aggregate Concrete Using Hybrid Machine-Learning Algorithms

This study presents an innovative approach to predicting the compressive strength (CS) of recycled rubberized concrete (RC) using advanced hybrid machine learning (ML) algorithms. The integration of recycled rubber in concrete offers significant environmental and sustainability benefits by reducing waste and promoting circular construction practices. Its heterogeneous nature introduces complexity in accurately estimating mechanical properties through traditional empirical models. To address this challenge, five ML models, XGB, RF, GBR, and two hybrid ensembles, XGB–RF and XGB–GBR, were developed and evaluated using a data set comprising 369 experimental samples with seven key mix-design parameters. The innovation of this work lies in the development and comparison of hybrid learning frameworks, which effectively capture nonlinear relationships among input parameters and enhance model generalization beyond conventional ML techniques. Model performance was rigorously validated using statistical metrics, such as the coefficient of determination (R2), mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE). The XGB model achieved the highest predictive accuracy R2 = 0.904, RMSE = 3.835 MPa, and MAE = 2.697, outperforming other individual and hybrid models. The XGB–GBR model achieved a high predictive accuracy of R2 = 0.879, RMSE = 4.012 MPa, further validating the strength of hybrid ensemble approaches. To further interpret model behavior, SHAP (SHapley Additive exPlanations) and partial dependence plot (PDP) analyses were conducted, revealing that rubberized aggregate (RA) content exerts the most significant negative influence on CS, followed by notable effects from fine aggregate, superplasticizer, and water content. The study not only highlights the effectiveness of AI-driven methods in forecasting concrete strength but also identifies optimal material proportions for mix design improvement. This research demonstrates that hybrid ML techniques provide a cost-effective, rapid, and highly accurate alternative to conventional testing for RC, offering valuable insights for sustainable material optimization and decision-making in modern civil engineering.