This study investigates the prediction of carbon emissions from fly ash and ground granulated blast furnace slag-based geopolymer concrete (GPC) using advanced ensemble machine learning (ML) techniques. Although ML has been extensively utilized to model GPC’s mechanical performance, its application in estimating environmental impacts, specifically carbon emissions, is limited. The research employs six ensemble ML models, such as random forest, gradient boosting, extreme gradient boosting (XGB), CatBoost, and light gradient boosting machine (LGBM), including versions optimized using ant colony optimization (ACO). Among them, the ACO-enhanced XGB model demonstrated the highest predictive accuracy with a coefficient of determination (R²) of 0.97, with low prediction errors (MAE = 3.92, RMSE = 6.17). However, cross-validation and uncertainty analyses indicate that the performance differences among top models are relatively small. Conversely, LGBM exhibited the least predictive reliability. Feature importance analysis revealed that curing parameters, specifically initial curing time, curing temperature, and the dosage of dry sodium hydroxide, had the most influence on carbon emissions. To evaluate model robustness and interpretability, Monte Carlo simulation and Gaussian white noise analyses were conducted. Results confirmed that CatBoost and ACO–gradient boosting (ACO-GB) demonstrated greater stability under varying and noisy conditions, whereas XGB-based models, although highly accurate, were comparatively more sensitive to input variability. Overall, the research establishes a data-driven, efficient framework for quantifying carbon emissions in GPC, highlighting the importance of evaluating both predictive accuracy and model robustness, advancing sustainable material design through intelligent modelling.

The deterioration of steel reinforcement through corrosion triggers cracking and loss of concrete cover, ultimately weakening the structure’s strength and ductility. In practical design and assessment, it is vital to precisely quantify the shear capacity of corroded reinforced concrete beams (CRCBs). In this paper, machine learning (ML) models are developed to predict the shear capacity of CRCBs, including kernel ridge regression (KRR), K-nearest neighbors (KNN), decision trees (DT), random forest (RF), gradient-boosted regression trees (GBRT), and extreme gradient boosting (XGBoost). A total of 408 data entries on the shear strength of CRCBs under different corrosion conditions were collected to establish an extensive database. The reliability of the proposed ML models is examined by contrasting their outputs with the experimental data. The XGBoost model demonstrated superior predictive capability, achieving an R² value of 0.994 and outperforming all other tested models, including RF, GBRT, and DT. The Shapley Additive Explanations (SHAP) algorithm is adopted to reveal the contribution of each input feature to the predicted shear capacity of CRCBs. The interpretive SHAP results show that the ultimate shear capacity of CRCBs is most influenced by beam depth (h), with the shear span-to-depth ratio (λ) and concrete compressive strength ((Formula presented.)) being the subsequent key contributors. A comparative assessment between the XGBoost model and traditional analytical models was carried out to estimate the shear strength of CRCBs. Results demonstrate that the XGBoost model delivers enhanced predictive accuracy and improved performance. A parametric investigation examined its robustness under variations in geometry and material properties, while a user-friendly interface was created to support its practical use.

This study investigates the combined use of fly ash (FA) and plastic waste (PW) as partial replacements for cement and coarse aggregates in the production of paver blocks. Experimental mixes were developed with a substitution level of FA (10% to 30%) and PW (3% to 15%). The performance of the modified concrete block was evaluated in terms of compressive strength (CS), flexural strength (FS), ultrasonic pulse velocity (UPV), water absorption (WA), Cantabro abrasion resistance (CAR), and rapid chloride permeability test (RCPT). Experimental results revealed that the optimal mixture, containing 25% FA and 12% PW (M4), exhibited superior performance. Compared with the control mix, the 56-day compressive and flexural strengths increased by 14.1% and 15.3%, respectively. The UPV value increased to 5.1 km/s, indicating improved concrete quality and matrix densification. Durability performance was significantly enhanced, with water absorption reduced by 25.4%, Cantabro abrasion mass loss decreased by 23.7%, and chloride ion penetrability reduced by 50.0% at 56 days. Statistical analysis using two-way ANOVA confirmed that FA and PW contents significantly influenced paver block performance (p < 0.05). The economic assessment further demonstrated cost savings of up to 3.0% compared with conventional concrete paver blocks. The study demonstrates that FA and PW can be effectively valorized in paver block production, offering both economic and environmental benefits. This green approach supports sustainable construction practices and promotes efficient waste management.

The growing demand for construction materials has intensified concerns regarding natural sand depletion and the accumulation of industrial waste. Among these wastes, oil-contaminated sand (OCS) generated from petroleum-related activities presents environmental challenges while also offering potential for beneficial reuse. Previous studies have reported that low OCS contents can enhance workability and improve mechanical properties, highlighting its potential as a sustainable construction material. This study investigates the feasibility of incorporating OCS as a partial replacement for natural sand in 3D concrete printing (3DCP). Three mixes containing 0%, 0.5%, and 1% OCS were evaluated in terms of flowability, setting behaviour, printability, rheological response, hydration behaviour, mechanical performance, anisotropic response, and microstructural characteristics. The results showed that OCS incorporation had only a limited influence on flowability, while both the initial and final setting times exhibited noticeable delays. The maximum printable layers reached from 19 for the control mixture to 22 and 26 layers for the 0.5% and 1% OCS mixes, respectively, accompanied by reduced settlement and structural deformation. Rheological analysis revealed higher static yield stress and structuration rates for the OCS-modified mixes, contributing to enhanced buildability and geometric stability. Hydration calorimetry showed comparable heat-flow behaviour between the control and OCS-modified mixes, suggesting only a limited influence of OCS on cement hydration kinetics. The incorporation of OCS improved the compressive strength of the printed mixes and reduced compressive anisotropy, while SEM observations revealed a denser and more homogeneous microstructure, particularly for the 0.5% OCS mix. Thus, the findings indicate that low-level incorporation of oil-contaminated sand is a viable strategy for improving the printability and performance of 3D-printed concrete, promoting the sustainable reuse of contaminated industrial waste.