The integration of artificial intelligence (AI) and machine learning (ML) has revolutionised civil engineering, enhancing predictive accuracy, decision-making, and sustainability across domains such as structural health monitoring, geotechnical analysis, transportation systems, water management, and sustainable construction. This paper presents a detailed review of peer-reviewed publications from the past decade, employing bibliometric mapping and critical evaluation to analyse methodological advances, practical applications, and limitations. A novel taxonomy is introduced, classifying AI/ML approaches by civil engineering domain, learning paradigm, and adoption maturity to guide future development. Key applications include pavement condition assessment, slope stability prediction, traffic flow forecasting, smart water management, and flood forecasting, leveraging techniques such as Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), Support Vector Machines (SVMs), and hybrid physics-informed neural networks (PINNs). The review highlights challenges, including limited high-quality datasets, absence of AI provisions in design codes, integration barriers with IoT-based infrastructure, and computational complexity. While explainable AI tools like SHAP and LIME improve interpretability, their practical feasibility in safety-critical contexts remains constrained. Ethical considerations, including bias in training datasets and regulatory compliance, are also addressed. Promising directions include federated learning for data privacy, transfer learning for data-scarce regions, digital twins, and adherence to FAIR data principles. This study underscores AI as a complementary tool, not a replacement, for traditional methods, fostering a data-driven, resilient, and sustainable built environment through interdisciplinary collaboration and transparent, explainable systems.

The increasing demand for cement, which is being driven by global urbanization and infrastructure expansion, necessitates sustainable alternatives to be used as construction materials. Cement-based composites, a prevalent construction material, are known for their high carbon footprint. Consequently, exploring sustainable alternatives is urgently needed to curb the environmental impact of the construction sector by capturing carbon dioxide (CO₂). Thus, utilizing biochar (BC) in cement-based composites, either as additive or cement, and in aggregate replacement could be a green approach, by producing enhanced composites with the capabilities of CO₂ sequestration. This review investigates the BC-modified cement composites by performing a scientometric assessment of the Scopus database and a thorough manual review. A scientometric assessment of Scopus-indexed publications retrieved from 2010–2024 was conducted to highlight key research trends, including influential authors, frequently cited works, countries, and institutions. The findings provide a comprehensive overview of the current situation of BC research and applications in cement-based composites for sustainable construction. The assessment revealed that the Construction and Building Materials journal was the most prolific source of publications (n = 34), followed by Gupta, with S as the most prolific author (n = 11), and China as the leading country in the field (n = 56). It also highlights the emerging areas for the use of BC in the construction sector for sequestering CO₂ and potential future directions. Additionally, the review discusses BC sources and BC production technologies and characteristics. It also discusses the influence of BC inclusion on the fresh properties, its mechanical properties, durability characteristics, carbon capture capabilities, and the environmental impacts of modified cement-based composites. It has been noted that BC addition to cement-based composites from 1% to 2% can increase its mechanical performance, whereas, beyond a 5% to 6% replacement, they experienced a decline compared to non-modified composites. BC addition has reduced the flow characteristics of the modified composites due to its porous morphology and hydrophobic nature but has shown improved internal curing and reduced shrinkage. It also improved the microstructure of the cement-based composite through pore refinement, due to the filling ability of the BC particles attributed to its specific surface area and size. Additionally, the carbon sequestration potential of BC can be exploited in cement-based composites to create low carbon or carbon-negative building materials with improved mechanical and durability characteristics. The study also highlights the future directions for further studies and implementation strategies of BC as a sustainable construction material at a large scale.

The construction sector makes a major contribution to global greenhouse gas emissions, in which cement alone produces approximately 7–8% of global CO₂ emissions. To abate environmental impact and promote sustainable construction, alternative low-carbon cementitious materials are gaining attention. Biochar (BC), a carbon-rich material obtained from biomass sources through the process of pyrolysis, has surfaced as a capable supplementary cementitious material due to its carbon capture capabilities and positive impact on the characteristics of cement composites. This review investigates the role of BC in cement composites, including its effects on hydration kinetics, microstructural development, fresh-state properties, and its optimal utilisation. The study also highlights the internal curing capabilities of BC when used in cement composites, its role in promoting hydration product formation, and its dual function in enhancing mechanical performance while facilitating carbon capture. Despite the benefits, there are some challenges such as variable BC properties, optimal dosage, and scalability. The review highlights the need for standardisation and further research to fully harness BC’s potential as a sustainable component in low-carbon construction technologies.

Following World War II, the rapid expansion of construction led to intensive use of natural resources, leading to resource depletion and accelerating climate change. Prioritising sustainability in structural design has therefore become essential. This study investigates three reinforced concrete (RC) slab systems typical of office buildings: flat slab, beam and slab, and two-way joist slab, using Eurocode 2 design principles. A 3 × 3 bay model with spans from 4 m to 14 m and three concrete grades (C25/30, C32/40, C40/50) was analysed through nonlinear finite element modelling. The methodology uniquely combines structural optimisation with embodied carbon and cost assessments across multiple slab typologies and span configurations, an approach rarely addressed in prior research. Results show that two-way joist slabs achieve the most favourable balance, reducing embodied carbon by 25–35% and construction cost by up to 15% compared to flat and beam and slab systems. This advantage is particularly evident at spans of 10 m or more, where the ribbed geometry significantly reduces concrete volume. Flat slabs are cost-efficient for short spans of up to 8 m but incur up to 40% higher carbon at longer spans due to increased thickness and punching shear reinforcement requirements. Beam and slab systems consistently recorded the highest cost and carbon values, offering limited environmental benefits despite their structural stiffness. The findings provide practical guidance for span-sensitive slab selection in early design, enabling the delivery of reinforced concrete buildings that are both cost-effective and environmentally responsible.

The demand for concrete has led to increased use of raw materials and significant waste generation. Recycled aggregate concrete (RAC) offers a viable approach to sustainable concrete; however, the use of weakly bonded mortar on aggregate leads to low strength and crack formation. Fiber reinforcement, specifically hybrid fiber reinforcement combining steel, glass, basalt, and polypropylene fibers, can increase the tensile and flexural properties of RAC. This study developed machine learning models to enable the prediction of hybrid fiber-reinforced RAC’s compressive, splitting tensile, and flexural strength performance; these new models overcome the limitations of previous research, which relied on only one fiber type and regular methods of optimization. Two models (a deep neural network (DNN) and an XGBoost model) were trained and optimized using bald eagle search (BES), particle swarm optimization (PSO), and the Bayesian optimization (BO) algorithm to improve performance. Among the three optimization analyses, PSO-XGBoost achieved the highest accuracy for compressive strength and splitting tensile strength, while BES-XGBoost achieved the highest accuracy for flexural strength. The most significant influences on the compressive strength were curing age and silica fume, while the main drivers of splitting tensile strength and flexural strength were fiber volume and fiber characteristics. The use of SHAP-based methodology with a user-friendly interface further improved the design of RAC mixtures, reducing waste from raw materials, enhancing the structural performance of RAC, and enabling data-driven decision-making in the manufacturing of eco-friendly concrete products.