Prediction of Strength of Sustainable Concrete with Supplementary Cementitious Materials and Recycled Aggregate Using Artificial Intelligence and Machine Learning: A Review

This review has synthesized 28 studies applying machine learning and artificial intelligence techniques to predict the compressive strength of concrete incorporating supplementary cementitious materials, recycled aggregate, or both. Ensemble tree-based methods — particularly Random Forest, XGBoost, and CatBoost — consistently outperform individual learners such as single decision trees, with reported R² values spanning 0.79–0.92 for SCM-concrete studies built on the widely used 1,030-record benchmark dataset, and 0.842–0.987 for RAC studies built on more heterogeneous, non-standardized datasets. Curing age, binder content, water-to-binder ratio, RA replacement ratio, and — where available — SCM chemical-oxide composition emerge as the most consistently influential parameters across sensitivity and SHAP analyses. Studies addressing SCMs and recycled aggregate simultaneously remain comparatively scarce and report somewhat lower and more variable accuracy than single-variable studies, reflecting smaller, more heterogeneous datasets. Future progress in this domain will depend on the development of standardized, richly featured benchmark datasets for RAC and combined SCM–RA concrete; wider adoption of model-interpretability tools; continued development of hybrid, metaheuristic-optimized ensembles; multi-objective frameworks that jointly optimize strength and sustainability; and, critically, prospective external validation that moves ML-based strength prediction from a research demonstration toward a field-deployable design tool for sustainable concrete.

Abduljaleel, Y. W., Al-Obaidi, B., Khattab, M. M., Usman, F., Syamsir, A., & Albaker, B. M. (2024). Compressive strength prediction of recycled aggregate concrete based on different machine learning algorithms. Al-Iraqia Journal for Scientific Engineering Research, 3(3). https://doi.org/10.58564/IJSER.3.3.2024.221 Ahmad, W., Ahmad, A., Ostrowski, K. A., Aslam, F., Joyklad, P., & Zajdel, P. (2021). Application of advanced machine learning approaches to predict the compressive strength of concrete containing supplementary cementitious materials. Materials, 14(19), 5762. https://doi.org/10.3390/ma14195762 Aslam, F., & Shahab, M. Z. (2024). Supplementary cementitious materials in blended cement concrete: Advancements in predicting compressive strength through machine learning. Materials Today Communications, 38, 107725. https://doi.org/10.1016/j.mtcomm.2023.107725 Ben Chaabene, W., Flah, M., & Nehdi, M. L. (2020). Machine learning prediction of mechanical properties of concrete: Critical review. Construction and Building Materials, 260, 119889. https://doi.org/10.1016/j.conbuildmat.2020.119889 Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324 Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). https://doi.org/10.1145/2939672.2939785 Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297. https://doi.org/10.1007/BF00994018 Ebid, A. M., Ulloa, N., Onyelowe, K. C., Zuñiga Rodriguez, M. G., Andrade Valle, A. I., & Zárate Villacres, A. N. (2024). Multiple AI predictive models for compressive strength of recycled aggregate concrete. Cogent Engineering, 11(1). https://doi.org/10.1080/23311916.2024.2385621