In the quest for sustainable construction materials, researchers are increasingly turning to industrial and agricultural waste to create high-performance concrete (HPC). A recent study published in the journal *Scientific Reports* (translated from Arabic as “Scientific Reports”) offers promising insights into the potential of recycled concrete aggregates (RCA) and chemically activated rice husk ash (RHA) to enhance the strength and durability of concrete. The research, led by Ahmed A. Alawi Al-Naghi from the Civil Engineering Department at the University of Ha’il, could have significant implications for the construction and energy sectors.
The study addresses a critical challenge in the construction industry: the strength loss associated with using RCA in concrete. While RCA is an attractive option for reducing waste, its variable performance has limited its widespread adoption. Al-Naghi and his team investigated the synergistic effects of chemically activated RHA, RCA, and foundry sand (FS) on the compressive strength and durability of HPC.
“Our goal was to find a way to effectively reuse industrial and agricultural waste in high-performance concrete without compromising its strength and durability,” Al-Naghi explained. The researchers prepared six experimental groups, one with inactivated RHA and five with chemically activated RHA using 3.5% sodium sulfate (Na2SO4). These were combined with varying levels of RCA replacement (0%, 40%, 60%, 80%, and 100%). All mixes included 20% FS as a partial fine aggregate replacement and a constant amount of silica fume.
The results were promising. Compressive strength was measured at intervals from 3 to 120 days, and durability was evaluated through acid exposure tests over four months. The study found that up to 40% RCA could be effectively used in HPC with activated RHA and FS without compromising long-term strength and acid resistance.
To complement the experimental study, the researchers applied machine learning models, including K-Nearest Neighbors, Random Forest, Artificial Neural Networks, and Extreme Gradient Boosting (XGB), to predict compressive strength. Among these, XGB outperformed the others with an R2 of 0.951, RMSE of 3.222 MPa, and MAE of 1.862 MPa. SHAP and Partial Dependence Plot (PDP) analyses revealed that curing age, RCA content, and Na2SO4 content were key influencing factors.
“This research not only provides a robust framework for sustainable concrete design but also demonstrates the power of machine learning in predicting material performance,” Al-Naghi noted. The integration of interpretable machine learning models with detailed experimental validation offers a comprehensive approach to optimizing the use of waste materials in construction.
The findings have significant commercial implications for the energy sector, particularly in the construction of energy-efficient buildings and infrastructure. By utilizing recycled and waste materials, the construction industry can reduce its environmental footprint while maintaining high performance standards. This research could pave the way for more sustainable and cost-effective construction practices, ultimately benefiting both the environment and the economy.
As the construction industry continues to seek sustainable solutions, the insights from this study offer a promising path forward. By leveraging the potential of recycled materials and advanced machine learning techniques, researchers and practitioners can work towards a more sustainable future.