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 accumulation of waste tyres presents a significant environmental challenge owing to their non-biodegradable nature and limited recycling options. The incorporation of tyre-derived rubber into concrete offers a promising strategy to reduce landfill waste and lower the consumption of natural aggregates. This study presents an integrated experimental and machine learning-based framework for evaluating and predicting the performance of rubberized concrete. M25-grade concrete mixtures were prepared with partial replacement of coarse aggregates by waste tyre rubber at proportions of 0%, 10%, 20%, and 30% by volume. Mechanical performance was assessed through compressive and split-tensile strength tests, whereas durability was evaluated using water absorption measurements. Microstructural characterization was conducted using scanning electron microscopy and X-ray diffraction analysis. In parallel, predictive models based on artificial neural networks, adaptive neuro-fuzzy inference systems, and fuzzy logic were developed and validated using statistical measures. The results showed that increasing rubber content reduced mechanical strength and increased water absorption due to weaker interfacial bonding and higher porosity. Nevertheless, concrete containing a 10% rubber replacement retained approximately 90% of the control strength while maintaining satisfactory durability. The machine learning models demonstrated strong predictive accuracy for estimating concrete properties. Overall, the findings suggest that limited incorporation of waste tyre rubber can contribute to the development of sustainable and low-carbon concrete materials with reduced embodied energy and environmental impact.

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.

Ordinary Portland cement (OPC) production contributes approximately 7–8% of global anthropogenic CO2 emissions, driving urgent demand for clinker-efficient binders utilizing industrial by-products. Flue gas desulfurization (FGD) gypsum and ground granulated blast-furnace slag (GGBFS) represent underutilized industrial by-products with documented potential as supplementary cementitious materials. This study investigates the mechanical, durability and microstructural performance of OPC–GGBFS–FGD gypsum ternary concrete mixtures incorporating untreated flue gas desulfurization (FGD) gypsum at 0–20% of total binder mass and ground granulated blast-furnace slag (GGBFS) at 25–50% of total binder mass in M30 structural concrete (w/b = 0.45). Compressive, split tensile and flexural strengths were evaluated at 7–90 days alongside rapid chloride penetration (RCPT), water absorption, strength efficiency index (SEI) and SEM–EDX analyses. Binary GGBFS replacement progressively enhanced long-term compressive strength, with T35F0 attaining 55.6 N/mm² at 90 days (+33.7% relative to the OPC control). Moderate FGD gypsum contents (5–10%) further enhanced overall performance. Among all mixtures, T50F10 exhibited the best overall performance on the mechanical and durability indicators evaluated, achieving 54.2 N/mm² compressive strength at 90 days together with a rapid chloride permeability value of 410 C, corresponding to ‘Very Low’ chloride ion penetrability. Beyond 10% FGD gypsum, progressive multi-parameter deterioration was observed, and mixtures containing 20% FGD gypsum failed to meet the M30 design requirement at 28 days. SEM–EDX confirmed that optimum sulfate activation produced a dense C–(A)–S–H-rich matrix, while excess sulfate caused matrix disruption. The findings establish 10% FGD gypsum by total binder mass as the optimum sulfate activation threshold for the investigated GGBFS and FGD gypsum sources at w/b = 0.45, and demonstrate the potential of untreated industrial FGD gypsum to produce durable, low-clinker structural concrete.