This study addresses the labor shortage and aging workforce in Japan’s construction industry by exploring the effectiveness of training with digital tools that visualize the “knack” of skills through superimposed eye-gaze points during a machine excavation task. The gazing point video of excavator during work was taken prior to the test. A web-based questionnaire test was conducted, with the Test Group watching the eye-gaze superimposed video and the Control Group watching the same video without gaze points. While overall responses between the groups were similar, question-level analysis revealed variations, suggesting that the eye-gaze visualization method shows potential effectiveness, although further exploration is needed to improve methods to express and convey these insights.

In recent years, there has been an increasing demand for efficient and quantitative analysis models in the maintenance and management of existing bridges. For bridges where design diagrams are only available in raster formats, high-precision automatic segmentation techniques are essential for generating finite element method (FEM) models. This study proposes a method for automatically segmenting and recognizing components in raster diagrams, focusing on side, plan, and cross-sectional views of existing bridges. Using supervised learning with the DeepLabv3+ deep learning model, structural elements were extracted from simplified diagrams, and segmentation accuracy was further enhanced using a region-based refinement algorithm. Experimental results demonstrated an average segmentation accuracy of 97.0% with DeepLabv3+ and 97.9% after applying the refinement algorithm, confirming the effectiveness of the approach. The findings of this study are expected to contribute to the three-dimensional modeling and efficient management of existing bridges.

The devastating flood phenomena that hit several cities in Gifu Prefecture, Japan, from 1959 until 1976 remains a potential threat to the communities and properties living around the downstream part of the Nagara River basin. Realizing that the affected population is essential in disaster risk reduction, an accurate and targeted estimation of population exposure is needed to reduce the flood disaster risk. Therefore, this research proposed the use of advanced geospatial technologies, with the integration of MSS data and flood inundation maps, to analyze population exposure to flood risks across different times of day and estimate how many people are exposed to flood in each land use zone of Gifu City. The results by using time-based population exposure from MSS data indicate that population exposure varies with time, land-use zones, and demographic factors, with residential areas particularly at risk during midnight and commercial areas during midday. The study highlights the high exposure of middle-aged and elderly populations, emphasizing the need for targeted disaster mitigation strategies. This novel approach, replacing traditional census data with MSS data, provides a real-time insights on flood disaster which will be beneficial on flood risk management, urban planning, and policy evaluation, especially in regions lacking comprehensive statistical data.

An accurate prediction of pavement condition is essential for effective pavement management systems, enabling road agencies to optimize maintenance strategies and extend the service life of road networks. The Pavement Condition Index (PCI) is one of the most commonly used pavement health indicators for assessing pavement deterioration. However, in many predictive models, PCI is often converted into an ordinal variable, which can result in the loss of valuable information regarding gradual deterioration patterns. This study aims to develop predictive pavement deterioration models treating PCI as a continuous variable to better capture the gradual deterioration of pavements over time. Both statistical and machine learning models were explored, including multiple regression, decision tree, random forest, and Artificial Neural Networks (ANN). Hyperparameter tuning was performed to optimize the performance of machine learning models, ensuring a balance between underfitting and overfitting. The models were evaluated based on R² and Root Mean Square Error (RMSE) values for both training and testing datasets, with performance parameters compared to identify the most effective model for predicting PCI as a continuous value. The findings indicate that random forest and double-layer ANN models possess superior predictive accuracy and generalization capabilities compared to other approaches, particularly in capturing complex deterioration patterns over time. The practical applicability of treating PCI as a continuous variable was explored, showing that it allows road agencies to identify critical deterioration stages and plan timely preventive maintenance and rehabilitation measures.

Until now, with the assistance of advanced technologies like drones and artificial intelligence (AI), the worldwide-attention-gained riparian environmental monitoring tasks recently have been gradually solved. However, there are still practical tasks that need to be solved by researchers when they are using drones and AI: How the trained AI model can be tested in practice; What kind of recognition-size can help the researchers get higher object detection accuracy; What kind of background will affect the object detection accuracy. Based on the mentioned issues, even there are several waste-based datasets that can be applied as benchmark globally (i.e., UAVVaste, UAV-BD and MJU-Waste), as yet in Japan, there is still no systematic local benchmark riparian waste-based dataset for application. Derived from the above, this paper takes the local location, the Asahi River Basin, Japan as the study site to design the experiments, and centers on the task of UAV-derived riparian waste-based object detection. The authors set up topics related to the influence of ground sample distance (GSD) and backgrounds (land-cover) on the accuracy of riparian waste-based object detection through various kinds of riparian waste-based images collected at different UAV flight altitudes (GSD) and at different sections (backgrounds) using multiple recognition sizes. In order to systematically analyze the above subjects, the authors set up different types of waste (can, cardboard, bottles and plastic bags), GSD (1.5, 2.0 and 2.5 cm/pixel), land-cover type (artificial- and natural- environment) and pixel-united recognition size (342×342, 900×600 and 5472×3648, pixel-unit) in corresponding groups. As another key point of this research, the authors applied AIGC-based model to detect the large-size objects in section-1 with over 80% detection ratio. This result proved the possibility of applying AIGC-based model in practical remote sensing tasks.

A systematic approach to determining the maintenance priority of road bridges is important for ensuring that limited resources are directed to the bridges in greatest need. Multicriteria decision-making is often used for priority evaluation, but the multiplicity of non-equivalent methods may lead to undesirable results. The goal of this study is to evaluate the effect of methodological uncertainties on the prioritization of road bridges by applying uncertainty analysis to propagate the effect of different criteria selection, criteria weighting, and criteria aggregation methods to the bridge priority ranking. A prioritization framework and data on national road bridges from Lao PDR were used. It was found that the bridges with the highest and lowest average priority were the least sensitive to methodological choice, whereas the sensitivity of bridges with intermediate levels of priority varied widely. In-depth examination revealed that even if two bridges shared a similar level of priority, their sensitivity to methodological uncertainty varied depending on the bridge condition and characteristics and how these were scored. The results illustrate how uncertainty analysis can be utilized for improving the robustness of decision-making for bridge management, but it is important to develop the methodological alternatives by transparent and scientific means.

The core idea of sponge cities is to enhance urban water management by creating systems that absorb, store, and release water in a controlled way. These systems are designed to mitigate urban flooding as well as improve water quality and biodiversity. This paper explores how flood control elements within (sponge) cities could be optimized using advanced technologies like SAM, Hydro-STIV, and Random Forest. SAM was used for land cover classification, STIV and Hydro-STIV for estimating the flow velocity and Random Forest for water level prediction. The proposed methodology offers a path toward smarter and resilient cities.

Urban road projects are crucial for sustainable development but often face challenges such as cost overruns, delays, and inefficiencies. Lean construction principles, focusing on waste reduction and value enhancement, offer a solution to these issues. However, successful implementation relies on understanding diverse stakeholder perspectives involved in the construction industry, which can vary significantly. This study investigates stakeholder views on leanness assessment parameters for urban road projects in Addis Ababa, Ethiopia, through a questionnaire survey. A mixed-method approach was used, combining qualitative and quantitative data, including a Likert scale-based pairwise survey of stakeholders such as clients, contractors, and consultants. The survey results were analyzed using the Analytical Hierarchy Process (AHP) and Hierarchical Clustering on Principal Components (HCPC) to identify key parameters influencing lean outcomes. AHP ranked leanness parameters, including Quality, Time, Sustainability, Safety, Cost, and Risk, and HCPC grouped stakeholders and identified patterns of consensus and divergence. The analysis revealed risk management, quality control, sustainability enhancement, cost efficiency, time management, and quality improvement as top priorities across stakeholders in different clusters. It was observed from the cluster analysis that client stakeholders preferred quality management over other parameters, whereas the stakeholders from construction and site management preferred more cost and time over other parameters. These findings provide actionable insights for fostering collaboration, enhancing decision-making, and embedding sustainability in lean construction, advancing the understanding of stakeholder engagement, and promoting more efficient, sustainable urban infrastructure development.

Winter road environments pose significant challenges to transportation safety and maintenance due to adverse weather conditions. This study proposes an anomaly detection model that leverages multiple databased Isolation Forest(iForest) to assess road conditions. This study integrates the data from an on-board edge system with precipitation data from XRAIN. The features related to winter road were selected, and labels were constructed for training iForest, a tree-based unsupervised learning method. This study proposes training the model only on readily obtainable and verifiable normal data and evaluates whether its performance can approximate that of supervised models requiring perfectly labeled datasets. Experiment results demonstrate the proposed model’s effectiveness in detecting anomalies under winter road conditions. Compared with other unsupervised learning techniques, the iForest model achieved the highest performance. Although supervised learning models output higher performance, their reliance on perfectly labeled data, which is difficult to acquire, limits their practicality in this context. In contrast, the results of our model are relatively closer to best performance, so we adopted it.

The findings highlight the practical significance of the proposed method for road monitoring and maintenance, providing a robust, low-cost solution for anomaly detection in complex winter road environments. This research not only enhances decision-making for traffic safety and resource allocation but also contributes to advancing the development of digital twin systems for intelligent transportation management.

Currently, the prediction of rockfall motion for the design of rockfall protection works is generally based on empirical methods or two-dimensional mass point analysis methods. These methods do not consider the detailed three-dimensional topography and shape of falling rocks, and there are concerns about the rational and safety aspects of the designed protection works. Therefore, this study attempts to apply a three-dimensional simulation using a Discontinuous Deformation Analysis. While this method can predict detailed rockfall motion considering the shape and physical properties of falling rocks and slopes, the establishment of the input parameters and the shape of falling rocks is an issue. Therefore, in this study, parametric studies on input parameters and rockfall geometry were conducted and their setting methods were investigated. Then, we compared the results with those of a two-dimensional mass point analysis method in a real site, and discussed a simulation technique for designing a rational and safe rockfall protection system. The results of this study show that the three-dimensional simulation using the Discontinuous Deformation Analysis can obtain good analysis results by considering the shape of falling rocks at the site and the characteristics of energy decay during impact. It was also found that the analysis of the actual site can predict the three-dimensional falling rock motion considering the falling rock and slope geometry, and that a rational and safe design of falling rock protection works can be expected compared to the two-dimensional mass point analysis method.

Cracks in civil engineering infrastructures, such as bridges, tunnels, and retaining walls, are common visual indicators of structural weakening. Damage to these structures can directly or indirectly impact human lives and property. In Japan, many of these infrastructures are ageing, making their maintenance a top priority to ensure safety. Traditional crack inspection methods for concrete structures often involve visual inspection using crack scales or gauges. However, this approach is time-consuming, labour-intensive, costly, and subject to the inspector’s judgement. In recent years, research has focused on leveraging Digital Image Processing techniques to address these challenges. This research aims to automate crack width monitoring by using YOLOv5 (You Only Look Once version 5) and the OpenCV library. Reflective targets are placed on either side of a crack to serve as a reference scale. The eight circles on the targets are automatically detected and measurement of the distance between the pair can be determined. The method was tested over a two-year period on a retaining wall in Tamano, Okayama, Japan, to demonstrate its applicability and feasibility. The results show that the model detects target circles with an accuracy of 95.9% and measures the crack movement. This method, compared to the manual approach currently used by the authors, significantly reduces crack width monitoring time, allowing for more frequent inspections and enhancing overall safety.

When constructing port facilities, the long-term settlement due to ground consolidation should be predicted. For this purpose, numerical analyses based on soil parameters obtained from soil tests are common. However, many uncertainties should be quantified, such as the detailed underlying physics, initial and boundary conditions, and enormous soil parameters. In this study, a deep learning method called physics-informed neural networks (PINN), which integrates physical laws into the loss function, was used to predict the strain distribution and the settlement caused by consolidation. It was demonstrated that, even if the period of observation is short and the initial and boundary conditions are unknown, the model could predict the strain distribution with high repeatability and accuracy. Furthermore, the constructed PINN model can be used to estimate initial and boundary conditions, and the model is capable of highly accurate prediction and estimation without computationally intensive numerical analysis and many laboratory tests, even in the presence of unknown parameters and uncertainties, which are challenges in ground consolidation problems.