Japan’s extreme environmental conditions have some potential challenges in the offshore wind development, and it requires enhancing the monitoring and maintenance practices. This study proposed an offshore wind turbine remote monitoring and advanced visual inspection by integrating digital twin technology, virtual reality, drones, and artificial intelligence (AI). An overview of Ramboll’s digital enabled asset management (DEAM) approach was elaborated, and its current advantages such as possible structure’s lifetime extension, failure mechanism detection and prevention, understanding the structure’s actual dynamic properties, environment monitoring, etc. In addition to that, two deep learning models that aimed to identify the OWT component and segment damages were trained, this might help to reduce the manpower, equipment cost, and lessen the visual inspection time. Furthermore, the challenges and conceptual possible integration of AI to drones during visual inspection were elaborated. The proposed method will include risk assessment and drone flight planning optimization in future studies.

The method was developed to automatically generate an FEM model of a steel highway pier, which is expected to behave in a complex manner during earthquakes, from point cloud data that can measure the three-dimensional shape of the object, without relying on drawings. The FEM model generated by the proposed method (point cloud model) and the FEM model created manually from the information in the drawings (drawing model) were subjected to the same loads and their behaviors were verified. It was found that the point cloud model tended to be slightly lower in terms of yield load, maximum load, and stress distribution near local deformation. There are two possible explanations for this factor: the discrepancy between the actual structure and the drawing due to initial imperfections, or the insufficient accuracy of the proposed method.

The upsurge in road crashes is a global challenge, and it poses a serious threat especially in low-and-middle-income countries due to incessant road crashes claiming many lives. Road safety management focuses on mitigating crashes by predicting the frequency and severity of the crashes and building safer roads. Predicting crash severity is essential because it is always preferred to avoid severe crashes. Factors like the time of the crash, type of collision, type, and number of vehicles involved in the crash, and the road features like geometric properties, pavement condition, and surrounding environment of the crash location can govern the severity of crashes. Due to the involvement of numerous factors in crash occurrence, predicting crash severity with high accuracy is a difficult task. Tree-based classification models like decision trees and random forests are two types of machine learning algorithms widely used to predict crash severities because they are considered to produce accurate predictions. The objective of this study is to develop road crash severity prediction models for a mountainous highway using the two tree-based algorithms and to assess various factors that affect the severity of the crashes by taking into account two different data treatment approaches: a) only considering the type of vehicle involved in a crash, and b) considering both the type and number of vehicles involved in a crash. The performance of the two treebased models: decision tree and random forest models for two separate types of data treatment will be assessed and compared. The models can be used to predict crash severity and the results may be useful for road agencies to identify and select safety countermeasures that can contribute to lower crash severity.

In recent years, laser ultrasonic visualization testing (LUVT) has attracted much attention because of its ability to efficiently perform non-contact ultrasonic non-destructive testing. Despite many success reports of deep learning based image analysis for widespread areas, attempts to apply deep learning to defect detection in LUVT images face the difficulty of preparing a large dataset of LUVT images which is prohibitively expensive and time-consuming to scale. To compensate for the scarcity of such training data, we propose a data augmentation method that generates artificial LUVT images by simulating artificial LUVT images and then applying a style transfer to these simulated images. The experimental results showed that the effectiveness of data augmentation based on the style-transformed simulated images improved the prediction performance of defects, rather than directly using the raw simulated images for data augmentation.

This paper proposes generalizing deep learning-based distress segmentation models for subway tunnel images by test-time training. Although it is promising to see that deep learning-based models are greatly alleviating the burden on subway tunnel maintenance workers, practical use of deep learning-based models for distress detection in subway tunnel images faces an obstacle, difficulty in training a generalizable model. Due to the diverse characteristics and different tunneling methods of the numerous subway tunnels, a model trained with data collected from one tunnel may not work well for another tunnel. Whereas training with data of a wide range of tunnels would be an ideal way, collecting such a large amount of well-labeled data is expensive. As an alternative to pursuing a highly generalizable model, it is more flexible and low-cost to generalize the model to specific test data at test time. In tasks of which the inference is not necessarily realtime, finetuning the model with the unlabeled test data may significantly improve the performance, not increasing too much inference time. In this paper, we focus on semantic segmentation of distress region in subway tunnel images and develop a test-time training method for generalizing the segmentation model to test data of different subway tunnels from the training data. Our method is simple yet effective, predicting pseudo labels with test-time batch normalization and finetuning the model with the pseudo labels. Extensive experimental results demonstrate that our method improves the distress segmentation performance in various scenarios, especially for crack which is a major and hard-to-detect distress type.

Dili, the capital of Timor-Leste, is facing the environmental and economic impacts of increasing urbanization, including traffic congestion, and a deteriorating atmospheric environment. To solve these situations, an evidence-based traffic management policy (EBTMP) based on a digital twin (DT) technology that combines geographical information and construction information modeling (BIM) is essential. This research successfully identified traffic patterns, delays, congestion hotspots, and air pol-lutants such as CO₂, NOx, and PM10 in the target zone the so-called Cathedral zone. Motorcycles were found to be an important contributor to air pollution due to their widespread use. Therefore, it is important to reduce motorcycle users in the future to reduce air pollution. Besides, the most important thing is to take action to provide good public transportation facilities and infrastructure to reduce private transportation users. By doing this, Dili’s urban mobility will be improved.

As with datasets in many fields, pavement management systems suffer from missing data, but machine learning techniques such as random forest analysis make imputation a viable solution. This study applied missForest, one implementation of random forest, to impute missing international roughness index (IRI), structural number (SN), and pavement condition index (PCI) data in the Kenya paved road inventory and condition survey database. The database also contains complete region, road class, carriageway surface type, road usage and visual surface condition rating data. With imputation methods influenced mainly by data distributions, missing mechanisms and correlation between variables and less by other data features such as missing rates, the study examined the distributions of the IRI, SN, and PCI data variables and investigated the missing data mechanism in the subject dataset towards confirming the applicability of missForest for imputation. It was found that the three variables follow highly skewed complex distributions and that the missing data is missing not at random (MNAR). Applying missForest to 19 combinations of impute and predictor variables, it was found that the combination of IRI, SN, and PCI impute variables with visual surface condition rating as the predictor variable gave the most accurate imputation in terms of normalized root mean squared error (NRMSE). A reliability check of variablewise missForest imputation in terms of mean squared error (MSE) revealed that the imputation was accurate for SN and PCI but not for IRI due to an extreme missing data rate of almost 90%. The study highlights that low-cost visual pavement condition survey on an entire road network with measurement of superior condition parameters on a sample of it followed by data-driven imputation sufficiently supports management decisions.

In snowy and cold regions, road surface conditions change rapidly due to snowfall and temperatures. Road surface conditions need to be grasped both in daytime and nighttime to maintain a safe and comfortable road space. However, such a method has not been proposed. Therefore, this paper proposes a method to estimate road surface conditions in both day and night by using confidence levels obtained from the daytime and nighttime classifiers. The proposed method can estimate road surface conditions throughout the daytime and nighttime. In the last part of this paper, the effectiveness of the proposed method is confirmed through experiments using actual images taken by an in-vehicle camera.

In snowy and cold regions, piled snow on road shoulders may cause traffic congestion and even traffic accidents. Maintaining the functionality of urban transportation can be a severe problem. In order to maintain the effective width of roads during the winter, piled snow on the road shoulders is removed and cleared. However, getting road information requires a great deal of time and workforce. In this paper, we propose a novel method for classifying the effective road width, narrowed by piled snow on road shoulders, based on videos captured from in-vehicle cameras using features focused on piled snow. Estimating road narrowing conditions from in-vehicle cameras will enable ordinary vehicles to collect road information and create an environment that does not require much time or workforce to gather road information.

A uniform nationwide survey on riverine space utilization has been conducted approximately every five years as part of the "Census of Rivers and Waterfront Areas" in Japan, for properly promoting river projects and river management. Considering significant effort required for human tasks, the survey is commonly carried out for seven days per year. Then, the present river situation is estimated roughly through the year, based on the limited survey results. Therefore, it is challenging to grasp the actual conditions on weekdays, holidays, and at different times of the day. Accordingly, it is difficult to examine the effect of individual river maintenance work quantitatively over years. For this study, the authors in this research tried to recognize human activities on the river bank automatically from 4K camera images taken near the Asahi River diversion weir in Okayama Prefecture, using the object detection model YOLO (i.e., You Look Only Once) with the large-scale multimodal model LLaVA (i.e., Large Language-and-Vision Assistant). Results showed that the combination of these models has the potential to collect information on not only the number and location of people but also various human activities, such as walking, running, and skateboarding.

Environmental degradation due to waste pollution (i.e., abandon artificial objects in the natural environment) is a growing concern that demands comprehensive understanding and effective solutions. This paper discussed the intricate issue of waste pollution, focusing on the Hyakken River Basin. This study presents of the waste pollution under long-term sunshine and/or water flow brush-up in the area, emphasizing the transformative effects of these environmental factors on the waste pollution. To substantiate this findings, the authors utilized smartphones to capture high-resolution images. To train these images in a YOLOv8 model, the datasets were meticulously annotated using roboflow, incorporating advanced data augmentation techniques. Subsequent testing involved the application of the model to smartphone videos from distinct sections of the field. Engaging actively in the cleanup process alongside dedicated volunteers, the authors successfully cleared the riparian area, providing a firsthand account of the positive impact of collaborative efforts. The on-site waste pollution after long-term in the natural environment is not similar to commercial goods (i.e., color and shape). Several models (i.e., pre-trained and custom-trained) have been tested with the Hyakken River Basin Wild Dataset. Derived from the results, custom-trained YOLOv8n-seg model has better results. Comparing with the SAM result without specified label, custom-trained YOLOv8n-seg model also has potential of improving. Looking ahead, the authors envision the utilization of this dataset as a valuable tool for supporting both volunteers and government staff in waste amount analysis. By contributing to environmental protection initiatives, this research aspires to pave the way for informed decision-making and sustainable solutions in the ongoing battle against waste pollution.

The road surface maintenance of parking areas is important to maintaining public infrastructure and extending its service life. Concave surface rutting detection is the first step in maintenance procedures and has become a tough task because of the increasing number of parking areas. UAVs were employed to collect data from the parking lot’s surface, providing a faster and more cost-effective solution rather than traditional detection methods. Furthermore, the algorithm of Structure from Motion (SfM) was utilized to reconstruct the 3D point cloud of the target area. RANSAC and DBSCAN algorithms were used to extract the road distress, which was further analyzed. The results illustrated that the proposed method can accurately detect and classify parking damage, achieving an accuracy rate of 90%.

This study delves into the escalating challenge of landslides and debris flows in Japan, prompted by its unique topography and climatic conditions that render it vulnerable to geological hazards. Recognizing the pressing need for innovative solutions, the research focuses on the application of the YOLO v8 computer vision model. With a dataset comprising 1,352 aerial images from disaster sites, the study employs YOLO v8 for hazard detection and segmentation. The model exhibits a precision of 0.49 for detection and 0.76 for segmentation, reflecting its accuracy in positive predictions. Noteworthy recall values of 0.42 for detection and 0.54 for segmentation underscore the model’s proficiency in capturing positive cases. The mAP50, a comprehensive accuracy measure, stands at 0.39 for detection and 0.52 for segmentation, underscoring the model’s efficacy in hazard detection. The research emphasizes the instrumental role of AI in disaster management and advocates for the continuous exploration of innovative methodologies.

The aging of concrete structures such as bridges and tunnels has led to the manifestation of damage, posing a significant problem. Particularly, the detection, evaluation, and documentation of cracks, which are a crucial indicator affecting the rate of deterioration, require an immense amount of time and effort. Consequently, the development of automatic detection methods using machine learning techniques has been pursued. However, the automatic pixel-level detection of cracks from captured images necessitates a large quantity of teacher images labeled at the same pixel level, which are costly to produce. Creating these images is not straightforward and has been a barrier to the practical implementation of image analysis methods. In response, this study developed a technique for detecting cracks at the pixel level while reducing the cost of creating teacher data, utilizing the attention mechanism. Additionally, the accuracy of this method was evaluated using captured images, confirming its equivalence to existing detection methods in terms of precision. This paper is the English translation of the authors’ previous work [Izumi and Chun, (2021). "Crack detection using deep learning with attention mechanisms" Artificial Intelligence and Data Science, 2(J2), 545-555. (in Japanese)].

Since accurate soybean seed sorting is a crucial but time-consuming and labor-intensive process in soybean production, there is a need for an inexpensive and simple sorting method. The objective of this study was to classify soybean external defects by multi-input convolutional neural network (CNN) models with two types of images: color and UV-induced fluorescence images. Color and fluorescent images of soybean seeds were respectively taken by white and UV LED with a wavelength of 365 nm, and visually labeled into four categories: normal, wrinkled, peeled and defect. For classification, the multi-input CNN models were constructed using three patterns of pre-trained networks: AlexNet, ResNet-18 and EfficientNet. The classification accuracy of each model was evaluated with the test data which consists of 20% of the total data. As a result, the multi-input CNN models showed generally higher classification accuracy than single color images or fluorescence images input models. Furthermore, the highest classification accuracy was 93.9% with the multi-input CNN models using ResNet-18, where the accuracy was higher than single color images or fluorescence images input by over 6.0 pt. These results demonstrated that a multi-input CNN model combining conventional color images with fluorescence images has a potential for soybean external defect classification.