Blast furnace slag (BFS) concrete offers significant environmental and durability advantages over ordinary portland cement (OPC) concrete, including reduced CO₂ emissions, enhanced long-term strength, and stronger resistance to chemical attacks. However, refining its mix design using conventional experimental methods is time-consuming and costly. This study addresses this challenge by developing advanced machine learning (ML) models to predict the compressive strength of BFS-incorporated concrete. A large dataset of 675 samples featuring cement, BFS, fly ash, aggregates, water, superplasticizer (SP), and curing age was assembled. Six ML models—AdaBoost, Decision Tree, Gradient Boosting Regressor, K-Nearest Neighbors, LightGBM, and XGBoost were evaluated. Comprehensive hyperparameter tuning via grid search and cross-validation optimized model performance and mitigated overfitting. Predictive accuracy was assessed using R2, RMSE, MAE, and MAPE metrics. Model interpretability was enhanced through SHAP analysis and partial dependence plots (PDP), revealing curing age, SP, and cement as dominant features influencing compressive strength. Results demonstrated that LightGBM (test R2 = 0.946, RMSE = 4.41 MPa) and XGBoost (test R2 = 0.943, RMSE = 4.52 MPa) exhibited almost comparable predictive performance; however, LightGBM achieved the highest overall accuracy, reflected in its slightly higher test R2 and lower RMSE, which declares LightGBM the best model for predicting CS of BFS-concrete. PDP analysis revealed that the optimal BFS replacement was observed between 30 and 40

Incorporating Granulated Crumb Rubber (GCR) into foamed concrete (FC) is being explored as a sustainable strategy to enhance its physical and mechanical properties. In this work, fine aggregates were partially replaced with GCR at levels of 5-25 % by volume, and the resulting mixes were tested for mechanical, durability, and microstructural properties over curing periods of 7-180 days. Optimum performance occurred at 10 % GCR, where compressive, flexural, and split tensile strengths increased by 16 %, 46 %, and 60 %, respectively, while water absorption, porosity, sorptivity, and thermal conductivity decreased by up to 16 %, 12 %, 35 %, and 43 %, indicating lower moisture propagation and enhanced insulation performance. SEM and MIP analyses confirmed finer, more uniform pores at <= 10 % content, whereas higher levels (>15 %) produced coarser and less stable pore networks that weakened the matrix. The findings demonstrate that incorporating well-graded GCR, compliant with ASTM C33-03, systematically modifies the pore structure and enhances the overall performance of FC in a predictable manner. These findings suggest that moderate GCR incorporation (approximate to 10 %) achieves an optimal balance between sustainability, mechanical performance, and durability, providing a robust scientific basis for developing environmentally sustainable, high-performance lightweight concretes using recycled rubber.

This study compiles and analyzes 376 UHPC mixtures comprising cement, fine and coarse aggregates, silica fume, fly ash, water, superplasticizer, and steel fiber to develop reliable, data-driven compressive strength (CS) predictors with reduced environmental footprint. Six ensemble models- CatBoost, Extra Trees (ETR), XGBoost, Gradient Boosting (GB), Histogram Gradient Boosting (HistGB), and Random Forest (RF) were trained and evaluated using coefficient of correlation (R2), RMSE, MAE, and mean absolute percentage error (MAPE) on stratified train/test splits. Model behavior was further examined with Taylor diagrams and radar plots, while Shapley Additive Explanations (SHAP) and partial-dependence plots (PDPs) were used to interpret variable effects and interactions. CatBoost delivered the best overall performance, attaining the highest test R2 (0.863) and the lowest test RMSE. Extra Trees ranked second with competitive accuracy (test R2 = 0.854) and the lowest MAPE in training/testing. XGBoost was close behind (test R2 = 0.836), while GB, RF and HistGB showed comparatively larger errors. SHAP revealed superplasticizer and cement as the most influential features, followed by silica fume and coarse aggregate; fly ash and fine aggregate had smaller, context-dependent effects. This study highlights the potential of supervised ML-based prediction for sustainable manufacturing of concrete with optimized performance.

Accurate prediction of asphalt mixture performance is essential for improving pavement durability and optimizing mix design efficiency. This study proposes a unified hybrid machine learning framework for the simultaneous prediction of Marshall Stability and Indirect Tensile Stiffness Modulus (ITSM) at 20 degrees C and 30 degrees C, enabling comprehensive thermo-mechanical characterization under intermediate service temperatures. Five advanced hybrid models, MOGB-RC, CatBoost-GA, LightGBM-HHO, ANN-DE, and ELM-WOA, were systematically developed and comparatively evaluated using cumulative error analysis, multi-metric statistical assessment, relative improvement comparison, and Taylor diagram validation. The results demonstrate that boosting-based hybrid models consistently outperform neural-based approaches in terms of absolute error reduction, squared-error control, bias stability, and generalization capability across temperature conditions. The MOGB-RC model achieved the highest predictive accuracy for Marshall Stability, reducing testing MAE to approximately 0.12 kN and RMSE to 0.15 kN, representing up to 44 % lower error compared to ANN-DE and nearly 85 % lower maximum deviation than ELM-WOA. For ITSM at 20 degrees C, boosting-based hybrid models (MOGB-RC and CatBoost-GA) maintained stable performance across the mid-to-high stiffness range, while ANN-DE exhibited nearly double the maximum error (similar to 470 MPa) compared to LightGBM-HHO (similar to 240 MPa), confirming superior robustness of ensemble-based approaches. At 30 degrees C, inter-model performance gaps narrowed; however, MOGB-RC preserved the lowest RMSE (similar to 50 MPa) and limited worst-case deviation to nearly 21 % of the mean stiffness value, whereas ELM-WOA reached nearly 30 %, highlighting significant differences in thermal generalization capability. Additionally, a dedicated graphical user interface (GUI) was developed to operationalize the optimized hybrid model, enabling rapid thermo-mechanical performance prediction and transforming the framework into a practical decision-support tool for intelligent asphalt mix design.

Due to the increasing demand for ready-made clothing, wastewater treatment facilities are producing large amounts of textile effluent sludge (TES), which is often dumped as backfill and contributes to groundwater and land contamination. Compressive strength (CS), a vital property of concrete, is usually measured through experimental tests that are both costly and time-consuming. To promote eco-friendly construction, this study investigates the mechanical, microstructural, environmental, and machine learning (ML) characteristics of concrete containing various TES percentages. The significance of this research lies in integrating TES as a partial cement and aggregate replacement with ML-based compressive strength prediction, providing a rapid cost cost-effective alternative to traditional experimental testing. Random forest (RF), linear regression (LR), extreme gradient boosting (XGB), and support vector regression (SVR) models were developed using 253 datasets from previous studies, with the RF model achieving superior performance with R2 values of 0.927 for training and 0.915 for testing. Analysis revealed that 15% TES replacement reduced compressive strength by 25.21% after 28 days while decreasing the environmental footprint by 13.90%, indicating an optimal balance between sustainability and performance. SEM observations confirmed increased porosity and ettringite formation in TES-modified concrete, correlating with the slight reduction in strength. Overall, this study presents an innovative, eco-friendly concrete solution that transforms hazardous TES into a valuable construction material while enabling reliable ML-based property prediction.

3D concrete printing offers design freedom, eliminates formwork, reduces costs and waste, and accelerates construction, making it a powerful alternative to traditional methods. Reinforcing concrete during 3D printing remains a major challenge. Conventional reinforcement disrupts the extrusion process, while continuous methods using steel cables or wires face issues such as nozzle blockage, misalignment, and poor anchorage, limiting their effectiveness. Incorporating short, discrete fibers into 3DPCM provides self-reinforcement, simplifying the process while enhancing mechanical properties. However, including fibers affects the fresh state properties of 3DPCM, particularly the extrusion. This study reviews the effects of steel fibers addition on the fresh and hardened properties of 3DPCM by analyzing published literature results. Various journal articles are reviewed, and extracted data is summarized to identify the influence of steel fiber on flowability, static yield stress, dynamic yield stress, printability, buildability, compressive strength and flexural strength of 3DPCM. The effect of steel fibers orientational distribution in printed filaments is also analyzed, and efforts to control the distribution to obtain favorable changes in the properties of 3DPCM are also highlighted.

This study explores the sustainable development of road infrastructure by substituting conventional aggregates with waste glass and Type C fly ash in open-graded asphalt mixtures. Performance evaluations through laboratory experiments showed that replacing virgin granite aggregate with waste glass (up to 30

[This retracts the article DOI: 10.1016/j.heliyon.2024.e24263.].

This research aims to contribute to the advancement of sustainable construction materials using a new composite of coated plastic waste as sand replacement material. This research assessed the predictive capabilities of Random Forest (RF), Particle Swarm Optimization-Support Vector Regression (PSO-SVR), and a Genetic Algorithm Optimized Artificial Neural Network (GA-ANN) that enable accurate, data-efficient prediction of compressive strength in plastic-waste foamed concrete, reducing experimental overhead and guiding sustainable mix optimization to forecast the compressive strength of foam concrete containing plastic waste. The models were evaluated using R2 metrics, where RF scored 0.9872 and 0.9005, and GA-ANN scored 0.9979 and 0.8853 for the training and testing sets, respectively. Sensitivity analyses of the RF and GA-ANN models were conducted to evaluate the compressive strength of the foam concrete and the impact of each associated input parameter. The findings confirmed that both models accurately predicted the compressive strength of the material. The R2 values for both models were calculated: for RF 0.9872 and 0.9005, and for GA-ANN 0.9979 and 0.8853. Sensitivity analysis indicated that the highest Permutation Importance values for cement, foam, sand, water-to-cement ratio, and plastic waste were 0.39, 0.34, 0.17, 0.11, and 0.39, respectively. In the GA-ANN case, the greatest Permutation Importance Values of 0.41, 0.31, 0.13, 0.11, and 0.05 were assigned to cement, sand, water-to-cement ratio, foam, and plastic waste, respectively, in that order concerning compressive strength. The PSO-SVR model in green maintained a good balance (AUC = 0.97 in training and AUC = 0.93) in testing. The PSO-SVR model achieved an average performance between those of the other two models. The MAE value was approximately 1.5 in training and 2.8 in testing, whereas the RMSE value was in the range of 4.5–5.0. The results showed the practicality of AI-based frameworks in the focus optimization of mix design and multi-criteria prediction of performance metrics of sustainable foam concrete containing recycled plastic waste.

This research intends to investigate and evaluate the effects of waste materials from industry, namely lathe machine waste powder (LMWP) on the durability and strength properties of asphalt mixtures. The research involved the preparation of asphalt mixtures specimens using one aggregate gradation with a nominal maximum aggregate size (NMAS) of 12.5 mm, three types of aggregates regular aggregates (RA), recycled concrete aggregate (RCA), and lathe machine waste powder (LMWP) and one type of asphalt binder. Regular aggregates (RA) passing through sieve sizes of 12.5 mm, 9.5 mm, 4.75 mm, and 2.36 mm were partially replaced with recycled concrete aggregate (RCA) at various replacement percentages from 0% to 50%, with and without the addition of lathe machine waste powder as a fine aggregate (sized between 0.075 mm and 1.18 mm). Cantabro test, air void content test and Marshall stability test were conducted to evaluate the durability and strength properties of asphalt mixtures. Based on the test results, it was noted that there was no significant difference in Marshall stability and air void content when regular aggregates (RA) were partially replaced with (RCA) and (LMWP). This research contributes to the development of sustainable pavement materials by promoting the use of alternative aggregates.

Incorporating zinc oxide nanoparticles (N-ZnO) is possible in lightweight foamed concrete (LWFC) construction. This paves the way for studies of the thermal, mechanical, pore structure, and other aspects of the LWFC that make use of the N-ZnO. For this purpose, six LWFC mixtures were formulated as cement additives ranging from 0 to 1

The global environment faces significant challenges due to the massive use of concrete, a dominant material in construction. Addressing this challenge, the present study explores the potential of recycled concrete aggregate (RCA) combined with rice husk ash (RHA) to enhance the durability and strength of recycled aggregate concrete (RAC), particularly in mixes with high RCA content. The research examines RHA as a partial substitute for Ordinary Portland Cement at 5%,10%,15% and 20% replacement levels, alongside RCA substitution rates of 80%, 90%, and 100%. Five RAC mixes were evaluated: Mix-1 served as the control group with varying RCA percentages (80%, 90%, and 100%) without RHA, whereas Mix-2, Mix-3, Mix-4 and Mix-5 incorporated 5%,10%,15% and 20%RHA as a cement substitute. The study evaluated parameters such as workability, compressive strength, tensile strength, water absorption, and acid resistance, in addition to employing non-destructive testing techniques like ultrasonic pulse velocity and rebound hammer tests. After 28 days of curing, Mix-4 (comprising 15% RHA and 80% RCA) exhibited the highest compressive strength among the tested RAC mixes, achieving a value of approximately 27MPa. However, economic analysis revealed that Mix-5 (20% RHA and 100% RCA) offers a 31% reduction in production costs, making it a viable choice for concrete manufacturing. This integration of RCA and RHA presents a sustainable, eco-friendly, and cost-effective approach to enhancing concrete strength and durability.

This review critically examines the role of fly ash (FA) as a sustainable binder and geopolymer precursor in concrete pavements. The purpose of the study is to synthesize existing research on the physicochemical, mechanical, durability, and environmental performance of FA-based materials and to identify their potential for replacing ordinary Portland cement (OPC) in rigid and semi-rigid pavement systems. The paper consolidates evidence from recent studies (2015–2025) and compares the behavior of Class F and Class C fly ash with respect to hydration, geopolymerization, and interfacial transition zone (ITZ) development. The review reveals that optimal performance is generally achieved with 15–20 % fly ash replacement, while higher dosages (up to 70 %) can yield long-term strength benefits. Durability analyses show that FA-blended concretes exhibit improved abrasion resistance, reduced permeability, and superior freeze–thaw and sulfate resistance compared with OPC mixes. Recent life-cycle assessments confirm that FA substitution can reduce embodied CO2 emissions by 40–80 % and lower energy consumption by up to 45 %, contributing significantly to low-carbon pavement infrastructure. This work contributes to the advancement of sustainable construction practices and offers valuable insights for researchers, practitioners, and policymakers in the field of pavement engineering.

This article compromises a three-dimensional numerical study employing the Abaqus program to investigate the behavior of reinforced concrete (RC) beams externally strengthened in shear using aluminum alloy (AA) plates bonded utilizing steel anchors. Based on previous experimental tests, a numerical validation study was conducted in two parts. The first part modeled the interaction behavior using different bonding methods between steel plates and the surface of the RC beams, whether utilizing epoxy adhesive only, steel anchors only, or a dual system between them. The second part modeled the performance of shear-defected RC beams that externally strengthened by the AA plates using epoxy adhesive. To take into account debonding collapse due to epoxy adhesive bonding, the interaction between the AA plates and beam surface was simulated with a cohesivedamage interaction. Comparing the numerical results with previous experimental studies shows the success of the numerical model in simulating the performance of different bonding methods, as well as the behavior of the RC beams defected in shear and strengthened by the AA plates, which qualified it to study some additional variables. From the study it was found that by utilizing only epoxy adhesive, the strengthening technique using the AA plate over the entire shear span zone (AASP method) was capable of increasing the ultimate capacity of the defected beam by 104%, which represents 77% of the load of the non-defected beam. It was also demonstrated that the AA plates were susceptible to collapse by the out -of -plane buckling when bonded using the steel anchors only. By utilizing a dual system for bonding the AA plates consisting of epoxy adhesive and steel anchors, the AASP method was capable of enhancing the ultimate capacity of the defected beam by 164% and changing its failure pattern to the preferred ductile bending pattern.

The primary objective of this study is to investigate the production and performance characteristics of structural concrete incorporating varying proportions (0%, 25%, and 50% by volume) of pumice stone, as well as aluminum lathe as an additive at 0%, 1%, 2%, and 3%, under fire conditions. The experiment will be conducted over a period of up to 1 hour, at temperatures ranging from 24 degrees C, 200 degrees C, 400 degrees C and 600 degrees C. For the purpose of this, a total of twelve test samples were manufactured, and then tests of compressive strength (CS), splitting tensile strength (STS), and flexural strength (FS) were performed on these samples. Next, a comparison was made between the obtained values and the influence of temperature. To achieve this objective, the manufactured samples were placed at temperatures of 200 degrees C, 400 degrees C, and 600 degrees C for a duration of 1 hour, and were subjected to the influence of temperature. These values at 24 degrees C were then contrasted with the CS results obtained from test samples that were subjected to the temperature effect for an hour at 200 degrees C, 400 degrees C, and 600 degrees C. A comprehensive analysis of the test outcomes reveals that the incorporation of aluminum lathe wastes into a mixture results in a significant reduction in the compressive strength of the concrete. As a result of this adjustment, the CS values dropped by 32.93%, 45.70%, and 52.07%, respectively. Furthermore, It was shown that testing the ratios of pumice stone alone resulted in a decrease in CS outcomes. Additionally, it was found that the presence of higher temperatures is clearly the primary factor contributing to the decrease in the strength of concrete. Due to elevated temperatures, the CS values decreased by 19.88%, 28.27%, and 38.61% respectively. After this investigation, an equation that explains the connection between CS and STS was provided through the utilization of the data of the experiments that were carried out.

This paper provides a comprehensive review of ultra-high-performance geopolymer concrete (UHPGPC), an innovative, eco-friendly, and cost-effective variant of ultra-high-performance concrete (UHPC), devised to meet the rising request for ultra-high-strength construction materials. Previous research papers have not thoroughly analyzed and compared the rheological, physical, durability, and microstructural properties of UHPGPC with UHPC. Similarly, review articles scarcely investigate UHPGPC's strength properties and microstructural behavior under high temperatures. This paper includes an assessment of the correlation between compressive strength, splitting tensile strength, and modulus of elasticity (MOE). The current study also compares chloride ion penetration test outcomes, elevated temperature, electrical resistivity, and porosity tests to evaluate durability. To analyze the microstructure of UHPGPC, the paper assesses results from Fourier Transform Infrared Spectroscopy (FT-IR), Thermogravimetric Analysis (TGA), Scanning Electron Microscopy (SEM), and Mercury Intrusion Porosimetry (MIP). The findings from the present paper suggest that UHPGPC effectively meets the ideal mechanical property specifications of UHPC. Compared to UHPC, UHPGPC displayed a higher ion passage propensity due to larger pores (>100 nm). Geopolymer technologies present a greener path for producing UHPC by consuming less energy and emitting reduced CO2. Introducing mineral fillers like silica fume impacts the mixture's flowability and increases its water needs. However, adding an optimal ratio of micro-silica as a partial substitute for granulated blast furnace slag further bolsters the strength characteristics of UHPGPC. The strength of UHPC can also be notably improved by adjusting the water-to-binder ratio, with specific ratios yielding considerable enhancements in compression strength. The selection of an alkaline activator plays a pivotal role in UHPC's heat resilience. Among them, a combination of potassium hydroxide and sodium silicate is the prime chemical activator for boosting strength performance, durability behavior, and microstructural attributes, particularly at temperatures beyond 600 °C. Eco-friendly Geopolymer Composites (EGCs) offer lower embodied energy and CO2 emissions than traditional composites, with certain components like polyvinyl alcohol fibers being key contributors to these emissions. Progress in self-healing materials is driving sustainability in construction through innovative techniques, such as bacterial applications and specific chemical reactions. The strength and workability of Engineered Geopolymer Composites are influenced by their fiber content, with certain fibers interacting weaker than others. On a microstructural level, UHPGPC has a relatively weaker structure than UHPC due to differences in pore size, but its durability is improved when reinforced with fibers.

This paper presents the results of an experimental study of varied properties of lightweight foamed concrete (LFC) at high temperatures. The key objective of this experimental study is to investigate the thermal, rheological, physical, and mechanical properties of LFC after being exposed to high temperatures up to 800 degrees C. To achieve that goal, an extensive study has been carried out to obtain 10 properties, i.e., slump flow, the colour of the surface, mass loss, porosity, thermal conductivity, compressive, split tensile, and flexural strength, modulus of elasticity, and wave velocity tests. In addition, the scanning electron microscopy (SEM) test provides the compositional details of materials. All mixes with varied densities were investigated after exposure to 20, 100, 150, 200, 400, 600, and 800 degrees C predetermined temperatures. Results also showed that mixes have different behaviours after being exposed to elevated temperatures, yet these behaviours, mass losses in particular, can be generally categorized into three phases based on temperature levels, i.e., 20-200 degrees C, 200-400 degrees C, and 400-800 degrees C. According to the SEM images, it is clear that the pore distributions and void sizes were significantly affected by the density value and the level of high temperature. As the temperature elevated, the void sizes also increased, and in some cases, groups of pores combined to form giant pores. However, by increasing the density, the pores' number, size, and distribution are less influenced by increasing temperature.

Ultra-high-performance concrete (UHPC) is a cutting-edge and advanced construction material known for its exceptional mechanical properties and durability. Recently, machine learning (ML) methods have played a pivotal role in predicting the compressive strength (CS) of UHPC and evaluating the dominant input parameters for a suitable mix design. In this research, three hybrid machine learning models were utilized: Random Forest (RF), AdaBoost (AB), and Gradient Boosting (GB) algorithms with particle swarm optimization (PSO), namely AB-PSO, RF-PSO, and GB-PSO, to predict compressive strength and perform SHAP (Shapley additive explanation) analysis. To build predictive hybrid ML models, a dataset of 810 experimental data points was collected for compressive strength (CS) from published literature. Additionally, SHAP interaction plots were generated to visualize the impact of each feature on a specific prediction made by the models. The results indicated that hybrid machine learning models performed better than traditional models, and the hybrid GB-PSO model showed the high prediction accuracy among models. The hybrid GB-PSO model had higher precision compared to the other two models. Hybrid GB-PSO model achieved R2 values of 0.9913 during the training stage and 0.9804 during the testing stage for the prediction of CS. The SHAP analysis revealed that age, fiber, cement, silica fume, and superplasticizer had a significant influence on compressive strength, while the impact of other input parameters was comparatively lower. The PDP (Partial Dependence Plots) analysis results amount of individually input variables material can be calculated simply for the designed CS. These findings are valuable for construction applications and offer essential insights for design engineers and builders, aiding their understanding of the significance of each component in UHPC.

The average content of reclaimed asphalt pavement (RAP) materials in asphalt mixtures for new pavements is around 22% in the current paving practices in the United States. Increasing this content has significant economic and environmental benefits. This study explored the approach of producing asphalt mixtures with 100% RAP materials by adding a small percentage of epoxy asphalt. Specimens of 100% RAP mixtures with low contents of epoxy asphalt were fabricated and evaluated in the laboratory for their properties related to pavement performance, including Marshall stability and flow, indirect tensile strength, resistance to moisture damage, resistance to fatigue damage, and fracture resistance. The results showed that the specimens made of 100% RAP materials selected in this study without a new binder or rejuvenator had low workability and high Marshall stability and indirect tensile strength but poor resistance to moisture damage and fatigue damage. A low percentage (0.5 to 2%) of epoxy asphalt significantly improved the resistance to moisture and fatigue damage of the 100% RAP mixture, and this improvement increased with the epoxy asphalt content. The fracture resistance of the 100% RAP mixture was also significantly improved by a low dosage of epoxy asphalt at a low temperature (8 °C), but the improvement was less significant at a moderate temperature of 25 °C.

In the present investigation, rice husk ash (RHA), bamboo leaf ash (BLA) and palm oil fuel ash (POFA) known as agricultural-waste materials locally available were used to produce ultralightweight foamed concretes (ULFCs). BLA, RHA, and POFA were used as replacements for cement in ULFCs at different weight percentages of 0%, 5%, 10%, 15%, and 20%. To achieve the target density of 350 kg/m3, cement was substituted with agricultural wastes, and a protein foaming agent was added. The properties of ULFCs were examined including, slump test, setting time, fresh density, split tensile, compressive and flexural strengths, thermal insulating, microstructural and transport properties, permeability and pore’s structure. The experimental results demonstrated that BLA and POFA ashes significantly outperforms in terms of efficiency and improved the mechanical and transport qualities of ULFCs than RHA ash. By increasing the weight fractions of BLA, RHA, and POFA from 5% to 20% in ULFC mixes resulted in an improvement in slump, porosity, capillary sorption, water absorption, bulk density, intrinsic air permeability, and specific heat. The ideal results were seen in terms of compressive strength, bending strength, splitting tensile strength, and UPV when 15% POFA and BLA, and 10% RHA were used as substitutes for cement. The increase in weight fraction of BLA, RHA, and POFA resulted in a rise in both thermal conductivity and thermal diffusivity of ULFCs. SEM studies revealed that incorporating different agricultural wastes positively affects the pore size distribution within the microstructure decreasing with increased content of ashes related to the development of ULFCs with stronger matrix. As a result, the formulated ULFCs met the masonry strength criteria while also providing economic and environmental benefits.