Carbon footprint reduction, recompense depletion of natural resources, as well as waste recycling are nowadays focused research directions to achieve sustainability without compromising the concrete strength parameters. Therefore, the purpose of the present study is to utilize different dosages of marble waste aggregates (MWA) and stone dust (SD) as a replacement for coarse and fine aggregate, respectively. The MWA with 10 to 30% coarse aggregate replacement and SD with 40 to 50% fine aggregate replacement were used to evaluate the physical properties (workability and absorption), durability (acid attack resistance), and strength properties (compressive, flexural, and tensile strength) of concrete. Moreover, statistical modeling was also performed using response surface methodology (RSM) to design the experiment, optimize the MWA and SD dosages, and finally validate the experimental results. Increasing MWA substitutions resulted in higher workability, lower absorption, and lower resistance to acid attack as compared with controlled concrete. However, reduced compressive strength, flexural strength, and tensile strength at 7-day and 28-day cured specimens were observed as compared to the controlled specimen. On the other hand, increasing SD content causes a reduction in workability, higher absorption, and lower resistance to acid attack compared with controlled concrete. Similarly, 7-day and 28-day compressive strength, flexural strength, and tensile strength of SD-substituted concrete showed improvement up to 50% replacement and a slight reduction at 60% replacement. However, the strength of SD substituted concrete is higher than controlled concrete. Quadratic models were suggested based on a higher coefficient of determination (R²) for all responses. Quadratic RSM models yielded R² equaling 0.90 and 0.94 for compressive strength at 7 days and 28 days, respectively. Similarly, 0.94 and 0.96 for 7-day and 28-day flexural strength and 0.89 for tensile strength. The optimization performed through RSM indicates that 15% MWA and 50% SD yielded higher strength compared to all other mixtures. The predicted optimized data was validated experimentally with an error of less than 5%.

Construction industry is indirectly the largest source of ${\text{CO}}_2$ emissions in the atmosphere, due to the use of cement in concrete. These emissions can be reduced by using industrial waste materials in place of cement. Self-Compacting Concrete (SCC) is a promising material to enhance the use of industrial wastes in concrete. However, there are very few methods available for accurate prediction of its strength, therefore, reliable models for estimating 28-day Compressive Strength (C–S) of SCC are developed in current study by using three Machine Learning (ML) algorithms including Multi Expression Programming (MEP), Extreme Gradient Boosting (XGB), and Random Forest (RF). The ML models were meticulously developed using a dataset of 231 points collected from internationally published literature considering seven most influential parameters including cement content, quantities of fly ash and silica fume, water content, coarse aggregate, fine aggregate, and superplasticizer dosage to predict C–S. The developed models were evaluated using different statistical errors including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), coefficient of determination (${\mathrm{R}}^2$) etc. The results showed that the XGB model outperformed the MEP and RF model in terms of accuracy with a correlation ${\mathrm{R}}^2$ = 0.998 compared to 0.923 for MEP and 0.986 for RF. Similar trend was observed for other error metrices. Thus, XGB is the most accurate model for estimating C–S of SCC. However, it is pertinent to mention here that it does not give its output in the form of an empirical equation like MEP model. The construction of these empirical models will help to efficiently estimate C–S of SCC for practical purposes.

This study aims to accurately predict the flexural strength (FS) of glass fiber reinforced concrete (GFRC) using advanced machine learning (ML) techniques. A novel algorithm, tree structured parzen estimator based extreme gradient boosting (TPE-XGB), is proposed by integrating Bayesian optimization (TPE) for automated hyperparameter tuning with the predictive strength of XGB. In addition to TPE-XGB, other ML algorithms including bagging regressor (BR), gene expression programming (GEP), and multi expression programming (MEP) are also employed for comparison. A comprehensive dataset consisting of 227 experimental instances of GFRC flexural strength was compiled from 33 internationally published studies. The models were trained and evaluated using statistical error metrics, k fold cross validation, scatter plots, and residual analysis. Results showed that all models performed reliably, with TPE-XGB achieving the highest prediction accuracy (testing R² value of 0.972). In contrast, GEP and MEP, described as grey box models that produce interpretable mathematical expressions, offered empirical equations for FS prediction which enhanced transparency. To further address the non-transparent nature of black box models like TPE-XGB, explainable machine learning (XML) techniques were applied. These included SHAP (Shapley Additive Explanations), Individual Conditional Expectation (ICE), and Partial Dependence Plots (PDP). The analysis revealed that water to cement ratio, quantities of fine and coarse aggregates, and glass fiber content were the most influential variables affecting the flexural performance of GFRC. Finally, a graphical interface is proposed to demonstrate the practical usability of the developed models. This study contributes both accurate prediction tools and interpretable insights, supporting improved and informed design practices in concrete technology.