Aug 2026· Civil Engineering Beyond Limits· 0 citations· 11 references
Abstract
The increasing demand for sustainable construction materials has led to the selection of supplementary cementitious materials (SCMs) to minimize the environmental burden of Portland cement manufacturing. This paper experimentally investigates the effect of varied volume of fly ash replacement on some fresh, mechanical and physical properties of M25-grade concrete and also develops machine learning-based models to predict performance. In this study, examining the effect of different fly ash replacement levels (0%-50%) on hardened concrete properties, six distinct concrete mixes were designed with constant water-to-cementitious material ratio (0.48) and 144 cylindrical specimens were casted from all mixtures to determine compressive strength, splitting tensile strength, workability and unit weight at age of 7, 14 and 28 days respectively. Although increasing fly ash content improved workability, high replacement levels reduced compressive and splitting tensile strength because of cement dilution and the relatively slow early-age pozzolanic reaction of Class F fly ash. Containing approximately 20–30% replacement levels, the best all-round performance with moderate compressive and tensile strength alongside cement mass reduction. It also employs the Random Forest and Extreme Gradient Boosting (XGBoost) regression models to predict compressive strength of a mixture from its variables. The prediction performances of the XGBoost model were more accurately represented (R² = 0.951; RMSE=1.128 MPa; MAE=0.966 MPa). The findings demonstrate the potential of ensemble-learning models to support preliminary fly ash concrete mix evaluation, although validation using larger independent datasets is necessary.
The increasing demand for sustainable construction materials has accelerated the incorporation of industrial by-products such as fly ash, ground granulated blast furnace slag (GGBFS), silica fume, rice husk ash, marble dust, and waste glass powder into composite concrete. These supplementary cementitious materials not only reduce environmental impacts associated with cement production but also enhance specific mechanical and durability properties of concrete. However, predicting the mechanical performance of composite concrete remains a complex challenge due to the nonlinear interactions among constituent materials, curing conditions, mix proportions, and environmental factors. Recent advancements in machine learning (ML) have provided innovative solutions for accurately predicting concrete properties while minimizing experimental costs and time.
This study presents a comprehensive review and conceptual framework for machine learning-based prediction of mechanical properties of composite concrete incorporating industrial by-products. A systematic examination of recent studies published between 2018 and 2026 is conducted to evaluate the effectiveness of various ML algorithms, including Artificial Neural Networks (ANN), Random Forest (RF), Support Vector Machines (SVM), Gradient Boosting Machines (GBM), Extreme Gradient Boosting (XGBoost), and Deep Learning models. The findings reveal that ensemble learning techniques frequently outperform traditional statistical methods, achieving prediction accuracies exceeding 90% in several applications. Furthermore, the review identifies critical challenges such as data scarcity, lack of standardized datasets, model interpretability issues, and limited real-world implementation.
The study proposes a conceptual framework integrating sustainable concrete design with advanced machine learning methodologies. It highlights future research opportunities involving explainable artificial intelligence, hybrid optimization algorithms, digital twins, and Internet of Things (IoT)-enabled monitoring systems. The research contributes to sustainable construction practices by demonstrating how intelligent prediction models can support material optimization, resource conservation, and reduced carbon emissions in the construction industry.
Keywords: Machine Learning, Composite Concrete, Industrial By-Products, Mechanical Properties Prediction, Sustainable Construction, Artificial Intelligence, Smart Materials
Ruchita K. Ingole· International Journal of Cre...· 0 citations
There has been a rise in the need of concrete leading to high consumption of cement and emission of carbon. Sustainable concrete incorporating supplementary cementitious materials (SCMs) is an alternative that is eco-friendly, but the mechanical behavior is complicated and hard to predict using the traditional tests. The work presents a framework involving machine learning because of predicting the mechanical properties of sustainable concrete, namely, compressive, split tensile, and flexural strength. Four models such as Linear Regression, Support Vector Regression, Random Forest, and Artificial Neural Network were constructed based on a data of nearly 1000 sustainable concrete mixes. To estimate the model performance, R 2, RMSE and MAE were used. The findings indicated that ANN and RF had the greatest prediction accuracy. The feature analysis established the most influential factors to be water content, cement dosage, replacement ratio of SCM, and curing age. The mix design approach proposed here is a fast, economical, and sustainable approach to the design of concrete mix.
Arti Chouksey, Santosh Reddy P, P. S et al.· 2026 International Conferenc...· 0 citations
The increased demand for sustainable building materials has promoted the use of industrial and agricultural by-products in concrete construction. The paper provides an experimental and machinelearning-based study on durability performance of M30-grade concrete. The partial replacement of conventional coarse aggregate was done with coconut shell (CS) and silica fume (SF) was used as a supplementary cementitious material (SCM). Eight concrete mixtures were experimented upon: the control mix, silica-fume-modified concretes (5%–15% SF replacement) and combined CS-SF concretes (10%–40% coconut shell replacement). Durability properties were evaluated using Water absorption and Effective porosity testing (ASTM C642), Rapid Chloride Permeability Test (ASTM C1202), Sorptivity testing and Sulphate and Acid Attack resistance tests according to CEB-FIP guidelines for durability assessment. The silica fume had a significant effect on the permeability related durability, lowering the Rapid Chloride Permeability Test (RCPT) value from 1120 C for the control mix to 548 C for the optimum CS-SF mix, which is about 51% less penetrable to chloride ions. The refinement of pore resulted in reduction of the sorptivity of silica-fume-modified mixes by approximately 4-5 percent. Coconut shell aggregates were porous and took more water, to a maximum of 6.7% at 40% replacement. Nonlinear correlations of mix parameters and durability performance were modelled using machine learning. Twelve models were used through grid search optimisation. A pipeline-based LOOCV strategy was employed to ensure limited data is assessed in an unbiased manner. R
2
, RMSE and MAE were used to evaluate model performance. The XGBoost model demonstrated predictive ability (R
2
= 0.96). SHAP analysis showed permeability-related properties are determined by silica fume content, while absorption and acid resistance are controlled by coconut shell content. Based on a small dataset, the proposed experimental-AI structure displays a proof-of-concept of explainable durability prediction and performance-based mix design of sustainable concrete.
K. Anjaneyulu, S. Sekar· Frontiers in Built Environme...· 0 citations
The modern construction industry faces significant challenges in developing sustainable concrete materials while maintaining structural quality requirements. Conventional trial-and-error methods for concrete mix design are time-consuming, costly, and often result in high variability in concrete quality. This study presents an integrated framework that combines machine learning techniques for concrete compressive strength prediction with genetic algorithm optimization to determine optimal mix compositions containing fly ash and blast furnace slag. Two predictive models were developed using the UCI Machine Learning Repository concrete dataset comprising 1,030 samples: Artificial Neural Network (ANN) Ensemble and Support Vector Regression (SVR). The ANN model demonstrated superior performance, achieving R² values ranging from 0.7475 to 0.8372, RMSE values between 6.11 and 7.94 MPa, and classification accuracy of 86.92% for concrete quality categorization across three classes (Class I: <20 MPa, Class II: 20-35 MPa, Class III: >35 MPa). In comparison, the SVR model achieved competitive but slightly lower performance with R² values of 0.7491-0.8378 and classification accuracy of 80.37%. The stability and generalizability of both models were confirmed through five-fold cross-validation. Subsequently, genetic algorithm optimization was applied to determine optimal mix compositions for each quality class while ensuring compliance with Indonesian National Standards (SNI 2847:2019, SNI 2461:2011, and SNI 8297:2016). The optimization process successfully produced concrete mix designs that achieved target compressive strengths of 14.95 MPa for Class I, 27.48 MPa for Class II, and 59.99 MPa for Class III. This framework demonstrates significant potential for developing sustainable concrete with optimal performance while meeting applicable technical standards, thereby contributing to a reduced carbon footprint in the construction industry through strategic utilization of supplementary cementitious materials.
The rapid rise in global population and industrial activity has intensified environmental challenges, particularly carbon dioxide (CO₂) emissions from the cement and concrete industry. Biochar, a carbon-rich byproduct of biomass pyrolysis, has emerged as a promising solution for sustainable construction by enhancing carbon sequestration and improving mechanical performance when partially substituting cement. This study integrates experimental evidence with advanced machine learning (ML) techniques to evaluate the compressive strength, cost-efficiency, and carbon footprint of biochar-incorporated concrete. A comprehensive dataset of nine input parameters, including cement, aggregates, silica fume, fly ash, biochar, water, superplasticizer, and curing age was modeled using multiple ML approaches. Among the models tested, the hybrid XGB-Histogram Gradient Boosting (XGB-HistGB) model consistently achieved the best overall performance, with a testing R2 of 0.958, the lowest mean absolute error (3.03), and minimal prediction bias. This model outperformed standalone algorithms and other hybrids, providing reliable accuracy across compressive strength, cost, and embodied CO₂ predictions. SHAP and partial dependence analyses confirmed fine aggregate, curing age, and superplasticizer as the most influential parameters, while biochar dosage required careful optimization to balance strength retention with sustainability benefits. A user-friendly graphical interface was also developed, enabling real-time prediction of compressive strength, material cost, and CO₂ emissions based on user-defined mix proportions. Overall, the findings demonstrate that biochar can be effectively integrated into sustainable concrete formulations, and the XGB-HistGB model offers a powerful AI-driven predictive framework to optimize both structural performance and environmental outcomes.
M. Uddin, Md. Samsuzzaman Sobuz, Mohamed Ghalla et al.· Scientific Reports· 0 citations
This study investigates the performance of sustainable concrete using Over-Burnt Brick Waste (OBBW) as a partial replacement for natural Coarse Aggregates (CA), with Class C fly ash (F) as a supplementary cementitious material. Concrete mixtures were prepared with OBBW replacement levels ranging from 5% to 55% at a constant 10% F content. Mechanical properties were evaluated experimentally, and statistical analysis and machine learning models were used to assess the relationships among the mix design parameters. The experimental results indicate that OBBW replacement levels of up to 50% improved mechanical performance. Specifically, the optimized concrete mix achieved a Compressive Strength (CS) of 34.65 MPa, representing a 22.7% increase over the control mix (28.24 MPa). Furthermore, flexural strength increased by 4.7%, from 3.4 MPa to 3.56 MPa. The findings demonstrate that the use of OBBW and fly ash enables the production of high-performance, eco-friendly concrete.
N. T. C. Kumar, K. Prakash, Rajani V. Akki· Engineering, Technology &...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
