Extreme weather conditions can cause significant damage to transport infrastructure, including railways, and disrupt its services. In this context, rainfall-induced landslides have been extensively studied with respect to failure probability; however, predicting the probability of damage to railway infrastructure remains challenging due to inadequate documentation of historical damage records from past extreme events. To address such data gaps, a hybrid data approach is proposed to quantify the physical vulnerability of railway embankments to rainfall-induced landslides, accounting for multiple damage states. In this study, the volume of a landslide is considered an appropriate damage indicator, and cumulative rainfall is used to assess the impact of rainfall-induced landslides on a railway embankment. The proposed integrated method includes maximum likelihood and best-fit regression to derive the fragility function, and Monte Carlo simulation is employed to estimate uncertainty in soil capacity. Data from a real case scenario in the Sri Lankan railways is used to demonstrate the application of the proposed method. Key parameters influencing rainfall-induced slope failure are identified to predict the fragility of rainfall-induced landslides in natural slope railway embankments using cumulative rainfall, with particular reference to small-scale events where landslide volume is less than 1000 m3. The application can be extended to assess the vulnerability of slope structures and earthworks and, ultimately, to support the development of resilient transportation infrastructure systems, provided that standardized data documentation and appropriate local data representation are adopted.

This study examines the implementation and application of Artificial Intelligence (AI) methodologies for estimating the Remaining Useful Life (RUL) of civil infrastructure assets, with the aim of supporting more effective civil infrastructure maintenance and management practices. A total of 90 publications were reviewed. Although not all were directly related to civil infrastructure RUL, the overall body of work reveals a continuous research activity since 2014, reflecting growing interest in data-driven deterioration forecasting. A key motivation for this review is to identify AI approaches that have been successfully applied to structured datasets and that demonstrate potential for practical integration into civil engineering asset-management environments. While advanced AI techniques exist, their adoption in civil infrastructure engineering and maintenance management remains limited, and many real-world systems require methods that balance predictive capability with interpretability, robustness, and compatibility with existing workflows. This study discusses a range of AI approaches—including Deep Learning (DL), Machine Learning (ML) ensemble regression, and hybrid models—highlighting their ability to capture complex degradation processes and their potential to enhance durability predictions. Challenges such as data quality, generalisability and interpretability of AI models, and the difficulty of embedding advanced analytics into current maintenance systems are identified. Opportunities for future research include improving model stability against noise, leveraging diverse data sources, addressing class imbalance, quantifying predictive uncertainty, exploring alternative degradation models, and integrating maintenance actions within RUL prediction frameworks. Overall, the findings underscore the increasing role of AI in asset-life prediction and highlight the need for approaches that remain technically sound while being feasible for implementation in civil real infrastructure-management settings.

The concept of digital twins (DT)s enhances traditional structural health monitoring (SHM) by integrating real-time data with digital models for predictive maintenance and decision-making whilst combined with finite element modelling (FEM). However, the computational demand of FE modelling necessitates surrogate models for real-time performance, alongside the requirement of inverse structural analysis to infer overall behaviour via the measured structural response of a structure. A FEM-based machine learning (ML) model is an ideal option in this context, as it can be trained to perform those calculations instantly based on FE-based training data. However, the performance of the surrogate model depends on the ML model architecture. In this light, the current study investigates three distinct ML models to surrogate FE modelling for DTs. It was identified that all models demonstrated a strong performance, with the tree-based models outperforming the performance of the neural network (NN) model. The highest accuracy of the surrogate model was identified in the random forest (RF) model with an error of 0.000350, whilst the lowest inference time was observed with the trained XGBoost algorithm, which was at approximately 1 millisecond. By leveraging the capabilities of ML, FEM, and DTs, this study presents an ideal solution for implementing real-time DTs to advance the functionalities of current SHM systems.

In recent years, the Discrete Element Method (DEM) has been widely utilised for the virtual reconstruction of porous asphalt (PA) mixes. However, limited attention has been directed toward aggregate size selection in DEM modelling. To address this, a numerical approach integrating DEM and Computational Fluid Dynamics (CFD) was developed in this study to explore the relationship between aggregate size and pore characteristics, incorporating computed tomography (CT)-scanned and computational PA mixes. Various particle size distributions (PSDs) and realistic aggregate configurations captured from laboratory samples were used in DEM model preparations to compare pore characteristics with CT-scanned PA mixes. This study investigated variations in pore structures, including porosity, pore size, air void (AV) distribution, and tortuosity, under different aggregate gradations. Differences in pore structures between experimental and computational samples were examined across three gradation ranges: (i) 4.75-13.2 mm, (ii) 2.36-13.2 mm, and (iii) 1.18-13.2 mm. Results indicate that numerical PA samples exhibit high similarity to experimental data in terms of AV distribution and pore number distribution when the minimum aggregate size is smaller than 2.36 mm. The tortuosity of numerical PA mixes is approximately two times lower than that of experimental samples and remains largely unaffected by changes in aggregate gradation. While numerical samples contain significantly fewer pores smaller than 0.1 mm2 or larger than 10 mm2 compared to experimental samples, the cumulative distribution curves maintain high similarity, particularly as the minimum aggregate size decreases.

The structural health monitoring (SHM) of bridge infrastructure has become essential for ensuring safety, serviceability, and long-term functionality amid aging structures and increasing load demands. SHM leverages sensor networks to enable real-time data acquisition, damage detection, and predictive maintenance, offering a more reliable alternative to traditional visual inspection methods. A key challenge in SHM is optimal sensor placement (OSP), which directly impacts monitoring accuracy, cost-efficiency, and overall system performance. This review explores recent advancements in SHM techniques, sensor technologies, and OSP methodologies, with a primary focus on bridge infrastructure. It evaluates sensor configuration strategies based on criteria such as the modal assurance criterion (MAC) and mean square error (MSE) while examining optimisation approaches like the Effective Independence (EI) method, Kinetic Energy Optimisation (KEO), and their advanced variants. Despite these advancements, several research gaps remain. Future studies should focus on scalable OSP strategies for large-scale bridge networks, integrating machine learning (ML) and artificial intelligence (AI) for adaptive sensor deployment. The implementation of digital twin (DT) technology in SHM can enhance predictive maintenance and real-time decision-making, improving long-term infrastructure resilience. Additionally, research on sensor robustness against environmental noise and external disturbances, as well as the integration of edge computing and wireless sensor networks (WSNs) for efficient data transmission, will be critical in advancing SHM applications. This review provides critical insights and recommendations to bridge the gap between theoretical innovations and real-world implementation, ensuring the effective monitoring and maintenance of bridge infrastructure in modern civil engineering.

Over recent decades, the implementation of Artificial Intelligence (AI) across various industrial fields from automation to cybersecurity has been transformative. Whilst the implementations of linking AI and data sciences remain complex and thus limited, they both aim to harness data for actionable insights and future predictions. A research focal point in the application of AI in maintenance is crucial for the sustainability and efficiency of assets. Typically, in the civil infrastructure, there are significant benefits to be gained from AI-driven applications. This study reviews the implementation of the AI in bridge maintenance decision-making by conducting a review of literature on major works undertaken by researchers and analysing 102 scientific articles published from 2010 to 2023. Our literature review revealed an emerging trend in recent studies, focusing on the exploration of defect prognosis in bridge maintenance. However, upon further analysis, it becomes evident that there is a notable gap in the existing literature, in the studies related to performance-based prognostic maintenance strategies for bridges. This gap presents an opportunity for future research, one that could yield valuable insights in the field of bridge maintenance and asset management. The review also reveals the focus of the existing literature on defect identification by using the bridge imagery processing. While the AI’s potential in damage detection using bridge imagery is evident, challenges persist including the computational processing and data availability. This review of the literature includes a comprehensive overview of the current implementation of AI in bridge maintenance, highlighting limitations, challenges, and prospective directions.

Continuous monitoring is significant to ensure the safe operation of infrastructure systems despite the high costs of traditional methods. The current study presents the development of a real-time digital twin of a laboratory-scaled bridge that can assist in the infrastructure monitoring process. Initially, the bridge model was instrumented with strain gauges, and a script was developed to conduct an inverse structural analysis and subsequently, run a finite element analysis to visualize the overall structural response. Three main loading scenarios were tested, and observations highlighted that the digital twin model emulated the actual structural behavior with a high accuracy. Also, the magnitude and the location of the applied loads on the real structure were correctly identified and a linear elastic behavior was identified in the digital model as expected from the actual structure. Further, the rates of change in the strain values and deflections were also evaluated while discussing the significance of digital twin development.

Civil infrastructure assets’ contribution to countries’ economic growth is significantly increasing due to the rapid population growth and demands for public services. These civil infrastructures, including roads, bridges, railways, tunnels, dams, residential complexes, and commercial buildings, experience significant deterioration from the surrounding harsh environment. Traditional methods of visual inspection and non-destructive tests are generally undertaken to monitor and evaluate the structural health of the infrastructure. However, these methods lack reliability due to the need for instrumentation calibration and reliance on subjective visual judgments. Digital twin (DT) technology digitally replicates existing infrastructure, offering significant potential for real-time intelligent monitoring and assessment of structural health. This study reviews the existing applications of DTs across various sectors. It proposes an approach for developing DT applications in civil infrastructure, including using the Internet of Things, data acquisition, and modelling, together with the platform requirements and challenges that may be confronted during DT development. This comprehensive review is a state-of-the-art review of advancements and challenges in DT technology for intelligent monitoring and maintenance of civil infrastructure.

Soil moisture variation plays a key role in maintaining the engineering properties of soils. One of the main factors that impact the soil moisture content is the temperature, which has a strong impact to change the initial or design moisture and results in significant soil volume changes. This study aims to investigate the effects of temperature on the performance of enzymatically stabilised soils. The enzyme used in this study is Eko-soil and the soil used is clayey silt of low plasticity (ML). The mechanical behaviour was first assessed through the unconfined compression strength and weight measurements based on samples exposed to a series of operational temperatures. X-ray μCT tomography images were then used to assess the microstructure. Porosity, size and geometrical shape of the pores were analysed at elevated temperatures. Results revealed that the enzyme is effective in maintaining the initial pore structure under the tested temperature range.

Port structures face the constant threat of deterioration due to exposure to dynamic and seismic forces, as well as harsh environmental condition prevalent in a maritime setting. These challenges lead to induced stress concentrations within the structures, resulting in potential catastrophic failures. Despite significant effort, expenses, and time consumption associated with traditional structural health monitoring systems (SHM), regular inspections remain the norm. This study introduces innovative methods to replace traditional approaches, leveraging Artificial Neural Networks (ANNs) as surrogates for real-time finite element (FE) modelling. The goal is to develop FE-based real-time digital twins for port structure by using sensor data, visualizing structural behaviour, and enabling a comprehensive monitoring of its structural response. An ANN model is trained using a validated FE model of the structure, generating immediate deformations based on sensor readings. By implementing this approach, stress variations are efficiently obtained and visualized throughout the structure. Unlike traditional methods that follow an inverse approach in estimating the entire structural response based on sensor values, the ANNs demonstrate high efficiency in addressing ill-conditioning issues inherent in such processes. This integrated methodology showcases the effectiveness of ANNs in providing real-time insights into the structural response of port infrastructure, offering a viable addition to the conventional SHM practices. The trained ANN model generates results in a high accuracy where the testing error is in the order of 10-5 and it generates data within 15 milli seconds demonstrating the near real-time conditions. The development of digital twins, facilitated by ANNs, demonstrates a promising solution for continuous monitoring, predictive maintenance, and risk mitigation in the face of dynamic operational and environmental challenges. The study contributes to the advancement of smart infrastructure by harnessing the capabilities of artificial intelligence and digital twin technology.

Traditional test methods for evaluating concrete self-healing performance, such as scanning electron microscopy, ultrasonic waves including velocity pulse and emissions and x-ray imaging have limited accuracy resulting from the damages during the sample preparation and capability of the instruments. Very limited work has been performed to date to conduct non-destructive evaluations using non-contact test methods, hence obtaining three-dimensional images that can evaluate the self-healing performance in cementitious materials. This study meteorological instruments to obtain three-dimensional surface profiles without any external impacts that could potentially cause damage to the concrete surface has been used. The study aims evaluate the healing efficiency and performance of the crack at different time intervals for 28 days by using different healing agents such as microcapsules, cellulose fibre and applying sodium silicate directly on the developed crack. Healing efficiency and performance assessment is conducted through the maximum visualisation featuring, crack width, depth healed product from the contact angle. Metrological selective roughness parameters such as Sa, Sq, Vvv and Smr2 values are also used to evaluate the self-healing performance at various time intervals. A comparison of the numerically obtained data, both individually and from different surface roughness parameters, indicates that crack healing occurrences can be observed when utilizing different healing agents.

The low bearing capacity of expansive soils often results in serviceability issues and premature failures of infrastructure built upon them. Various studies have demonstrated the use of different soil treatment methods using mechanical or chemical approaches to stabilize the weak ground as a precaution. Most of the reported studies are limited to either lab-based investigations or field monitoring works without the scientific connection between theory and translation. This study aims to verify the field application of a novel soil stabilization method by conducting laboratory-controlled experiments and field performance testing as verification. Enzyme-based soil stabilization was adopted for in-situ clay soil in combination with ordinary portland cement as a sustainable stabilization approach. Soil samples were collected at different regions from the field to evaluate the effectiveness and the mechanism of soil stabilization in the field by the means of replicating stabilization at the laboratory scale using identical mixing proportions of the additives. The mechanical behavior of stabilized soil was assessed through the unconfined compression strength and California bearing ratio test methods. In addition, the changes in the chemical composition of the soil due to the additives were evaluated through the X-ray diffraction testing technique and microporosity test using 2D images translated to 3D profiles from X-ray micro CT tomography. The efficacy of field stabilization was evaluated by conducting the falling weight deflectometer test in the stabilized site. Results from the study are useful to understand the efficacy of field soil stabilization and enhance the reliability of enzyme-based stabilization in practice.

There are numerous manuals to guide practitioners in utilizing traditional additives in the construction of road, rail and dam construction but they fall short of specific guidance for non-standard additive-based ecofriendly and cost-effective soil stabilization. Increased attention has recently been on the use of non-standard additives for stabilizing weak soils due to environmental and cost concerns associated with traditional additives. We summarize the specific guidelines of using environmental-friendly enzymes to treat weak soils. We elaborate on the requirements and specifications for the Eko-Soil multi-enzyme product that is manufactured from water and proteins extracted from fermented exudes of plants. Specific tests (laboratory and field) and conditions required for soil stabilization using Eko-Soil enzyme are elaborated using the experience of past construction projects. The guide also elaborates enhancing the efficiency of enzymatic soil stabilization by correctly incorporating the required mixing proportions and pre-requisite condition tests. Professionals and practitioners will benefit from using novel eco-friendly sustainable stabilization techniques in the treatment of weak soils covering many applications including roads, foundations, water containment areas, landfills, working platforms and slope erosion control.

Expansive clays are problematic soils as they contain minerals that swell when wetted and shrink during drying. Highway construction on expansive soils requires some form of chemical stabilisation or other treatments to improve pavement performance. Many commercial and waste by-products, such as cement, lime, fly ash and slag, are used as chemical stabilisers to treat expansive clays. Municipal solid waste incineration (MSWI) fly ash is a product obtained from waste-to-energy plants which have attracted increasing attention to prevent land contamination and to reduce landfill costs. This paper investigates the stabilisation mechanism and hydromechanical performance of MSWI fly ash-stabilised high plasticity expansive clays. In this study, compressive strength, California bearing ratio (CBR), dynamic cone penetration, shrinkage and swelling, X-ray diffraction (XRD), scanning electron microscopy (SEM) and X-ray micro-computed tomography (micro-CT) tests were conducted to understand the performance of MSWI fly ash for the treatment of high-plasticity expansive clay. The study found that MSWI fly ash reduces swelling potential and increases the ten-day soaked CBR to about 80%. Microlevel analysis showed that hydration reaction, cationic exchange, flocculation, and agglomeration between clay sheets are the key phases in MSWI fly ash stabilisation. In addition, the porosity of the clay reduced from 3.43% to 0.18% after stabilisation with 20% MSWI fly ash. The outcomes from the study provide guidance on using MSWI ash for improving problematic soils while enabling an efficient way to manage municipal solid wastes.

One of the critical factors that govern the technology of concrete self-healing evaluation at laboratory scale is the crack induction pattern within the concrete sample. Within the various techniques of inducing artificial cracks, such as the flexural testing or splitting testing methods, there are limitations of inducing the microcracks homogenously throughout the entire volume of the concrete sample. In this study, an innovative technique is utilised to induce the microcracks at a controlled damage level to further study the self-healing phenomena in concrete at the laboratory scale. By placing a concrete sample into an ad-hoc fabricated steel mould and applying fractional compressive strength, the axial-circumferential pressure induces microcracks in the concrete sample, homogenously. A Finite Element Model was also built to investigate the hypothesis on the cracking pattern at various damage levels; jointly, experimental work was conducted with X-ray µCT images to reconstruct the three-dimensional sections at the various damage levels. Qualitative analyses in relation to the two test methods were conducted. Furthermore, quantitative analyses on the individual—artificially generated—cracks were conducted in terms of the crack size crack geometry variation and the orientation of the newly formed cracks. Results revealed that the proposed crack-inducing methodology is highly efficient to induce uniform cracks in the sample, assisting for the evaluation of concrete self-healing process. The novel method can be adapted to identify the optimised strategies for enhancing the structural performance of concrete, thus facilitating the safe operation of concrete infrastructure.

Cracking is intrinsic in cement-based products, although the cementitious material can potentially self-heal cracks. However, the rate of micro-crack formation is comparably higher than that of the self-healing. Researchers are conducting experiments on self-healing phenomena and have shown that the microencapsulation method is one of the most efficient techniques to transport and mix the healing agent in the cementitious matrix. In this study, sodium silicate is stored inside the polyurethane materials to enhance the self-healing efficiency of the cementitious matrix. Initially, compression and stiffness tests are conducted to assess the recovery of mechanical properties. X-ray tomography images are also reconstructed into three-dimensional sections and self-healing recovery was assessed via porosity content, sphericity. reduction of single crack width and volumetric size. A novel method is used to identify the geometrical definition of the single micro-crack during the self-healing process known as the Structure Model Index. Micro-cracks in mortar samples were developed homogeneously through the entire section of the samples. In this process, it was established that cracks up to 203 mu m in thickness were healed. (C) 2019 Elsevier Ltd. All rights reserved.

•The number of articles on concrete healing being generated worldwide is increasing.•Basic mechanical tests are commonly used to prove the efficiency of healing.•Few studies investigate internal crack distribution and morphology during healing.•Healing is assessed using novel methods based on X-ray tomography, MIP tests.•Porosity, sphericity, single crack width, and Structure Model Index are discussed.