Concrete compressive strength is usually determined 28 days after casting via crushing of samples. However, the design strength may not be achieved after this time-consuming and tedious process. While the use of machine learning (ML) and other computational intelligence methods have become increasingly common in recent years, findings from pertinent literatures show that the gradient-boosting ensemble models mostly outperform comparative methods while also allowing interpretable model. Contrary to comparison with other model types that has dominated existing studies, this study centres on a comprehensive comparative analysis of the performance of four widely used gradient-boosting ensemble implementations [namely, gradient-boosting regressor, light gradient-boosting model (LightGBM), extreme gradient boosting (XGBoost), and CatBoost] for estimation of the compressive strength of quaternary blend concrete. Given components of cement, Blast Furnace Slag (GGBS), Fly Ash, water, superplasticizer, coarse aggregate, and fine aggregate in addition to the age of each concrete mixture as input features, the performance of each model based onR², RMSE, MAPE and MAE across varying training–test ratios generally show a decreasing trend in model performance as test partition increases. Overall, the test results showed that CatBoost outperformed the other models withR², RMSE, MAE and MAPE values of 0.9838, 2.0709, 1.5966 and 0.0629, respectively, with further statistical analysis showing the significance of these results. Although the age of each concrete mixture was found to be the most important input feature for all four boosting models, sensitivity analysis of each model shows that the compressive strength of the mixtures does increase significantly after 100 days. Finally, a comparison of the performance with results from different ML-based methods in pertinent literature further shows the superiority of CatBoost over reported the methods.

The use of recycled aggregates concrete (RAC) contributes effectively to reduce CO₂ emissions from concrete manufacturing process while also protecting natural resources by utilizing existing available concrete as an aggregates source for a new one. Studies on the behaviour of RAC have revealed negative effects on concrete strength and microstructure development, resulting in deterioration of mechanical and durability properties. As a result, numerous practical studies have been implemented to enhance the RAC properties using various treatment techniques such as chemical, physical and heating treatments. However, most of these techniques are ineffective compared to conventional concrete applications due to poor mechanical performance of RAC, insufficient environmental requirements, and prolonged treatment times. Recently, the use of nanomaterials has been given significant concern in RAC research. Their nano-sized particles can help to reduce micropores formation by acting as a filling agent to produce a high-density microstructure, thereby enhancing the mechanical properties and durability of RAC. This had led to a wide range of studies being published on improving RAC properties by using nanomaterials. However, relatively few literatures had been conducted on the effects of different types of nanomaterials on the performance of RAC exposed to various types of loads and various external environmental impacts. Besides, the conditions used by authors in these literatures limit comparisons, and in some cases contradictory findings are observed. Thus, this paper aims to bridge the knowledge gap between researchers. This would allow the potential of nanotechnology in innovations to be applied in appropriate areas of RAC applications to benefit the general public good. This paper aims to provide a critical review and comprehensive conclusions on the performance of nano-modified RAC under external loads, environmental impacts and other various conditions. The effects of nanomaterials on the compressive, tensile, and flexural strength of RAC are discussed. The nanomaterials considered are nano-SiO₂, nano-CaCO₃, nano-TiO₂, nano-Clay, nano-Al₂O₃, and nano-Carbon. Durability characteristics including water absorption, chloride penetration, fire exposure, abrasion resistance, acid and carbonation diffusions are extensively discussed. Microstructure characteristics using SEM, XRD, EDS, and micro-hardness of nano-modified RAC are addressed as well.

The increased demand for cement mortar due to rapid infrastructural growth and development has led to an alarming depletion of fine aggregate. This has prompted the need for a more sustainable material as a total/partial replacement for natural fine aggregate. This study proposes the use of tin slag (TS) as a replacement for fine aggregate in concrete to bridge this sustainability gap. TS was used to replace fine aggregate at replacement levels of 0%, 25%, 50%, 75%, and 100% in cement mortar. Fresh and hardened properties of TS mortar were obtained. Flow tests showed that, as the TS quantity and the w/c ratio increased, the mortar flow increased. Similarly, the compressive strength increased as the TS replacement increased up to 50% replacement, after which a decline in strength was observed. However, with the TS replacement of fine aggregate up to 100%, a compressive strength of 6% above control was attained. The morphological features confirm that specimens with TS had a denser microstructure because of its shape characteristics (elongated, irregular, and rough), and, thus, plugged holes better than the control mortar. The natural sand’s contribution to strength was a result of better aggregate hardness as compared to TS. Hence, TS can be used as alternative for fine aggregate in sustainable construction.

The excellent performance of graphene oxide (GO) in terms of mechanical properties and durability has stimulated its application potential in high-strength lightweight concrete (HSLWC). However, more attention needs to be paid to the long-term drying shrinkage of HSLWC. This work aims to investigate the compressive strength and drying shrinkage behavior of HSLWC incorporating low GO content (0.00–0.05%), focusing on the prediction and mechanism of drying shrinkage. Results indicate the following: (1) GO can acceptably reduce slump and significantly increase specific strength by 18.6%. (2) Drying shrinkage increased by 8.6% with the addition of GO. A modified ACI209 model with a GO content factor was demonstrated to have high accuracy based on the comparison of typical prediction models. (3) GO not only refines the pores but also forms flower-like crystals, which results in the increased drying shrinkage of HSLWC. These findings provide support for the prevention of cracking in HSLWC.