Asbestos is a class 1 carcinogen, and it has become clear that it harms the human body. Its use has been banned in many countries, and now the investigation and removal of installed asbestos has become a very important social issue. Accordingly, many social costs are expected to occur, and an efficient asbestos investigation method is required. So far, the examination of asbestos slates was performed through visual inspection. With recent advances in deep learning technology, it is possible to distinguish objects by discovering patterns in numerous training data. In this study, we propose the use of drone images and a faster region-based convolutional neural network (Faster R-CNN) to identify asbestos slates in target sites. Furthermore, the locations of detected asbestos slates were estimated using orthoimages and compiled cadastral maps. A total of 91 asbestos slates were detected in the target sites, and 91 locations were estimated from a total of 45 addresses. To verify the estimated locations, an on-site survey was conducted, and the location estimation method obtained an accuracy of 98.9%. The study findings indicate that the proposed method could be a useful research method for identifying asbestos slate roofs.

Active research on crack detection technology for structures based on unmanned aerial vehicles (UAVs) has attracted considerable attention. Most of the existing research on localization of cracks using UAVs mounted the Global Positioning System (GPS)/Inertial Measurement Unit (IMU) on the UAVs to obtain location information. When such absolute position information is used, several studies confirmed that positioning errors of the UAVs were reflected and were in the order of a few meters. To address these limitations, in this study, without using the absolute position information, localization of cracks was defined using relative position between objects in UAV-captured images to significantly reduce the error level. Through aerial photography, a total of 97 images were acquired. Using the point cloud technique, image stitching, and homography matrix algorithm, 5 cracks and 3 reference objects were defined. Importantly, the comparative analysis of estimated relative position values and ground truth values through field measurement revealed that errors in the range 24–84 mm and 8–48 mm were obtained on the x- and y-directions, respectively. Also, RMSE errors of 37.95–91.24 mm were confirmed. In the future, the proposed methodology can be utilized for supplementing and improving the conventional methods for visual inspection of infrastructures and facilities.

Currently, firefighter drones in Republic of Korea underperform due to the lack of take-off site reservations in advance. In order to address this issue, this study proposes a GIS-based multi-criteria model for selecting take-off and landing sites for firefighter drones in urban areas. Seven criteria were set for the selection of take-off and landing sites based on building roofs. Buildings at 318 sites in the target area that satisfy all seven criteria were extracted and grouped according to the geographical location. Among the grouped buildings, 11 sites were reselected through network analysis and central feature methods. In addition, two more sites were selected through the relaxation of criteria for take-off and landing sites for firefighter drones. Validation was performed using the data of building fires that occurred in the target area in the past. The results confirmed the effectiveness of the method applied in this study, as potential responses could be verified for ≥95% of the buildings with a past fire incidence. By introducing a simple methodology in which a multi-criteria model is built through spatial information, this study contributes to the literature on improving operational firefighting strategies and provides practitioners and policymakers with valuable insights to support decision-making.

A sufficient supply of water for firefighting is critical for effective responses to urban fires, thus reducing fire hazards. The aim of this study was the development of an analysis method for vulnerable areas with respect to firefighting activities that require the use of fire hydrants. In particular, a method was proposed for the determination of the operational range of firefighting activities based on the distribution of the fire hydrants and the roads that allow for the passage of firefighting vehicles. The proposed method, which employs a geographic information system (GIS), was applied to Buk-gu, Daegu City, South Korea. The research results revealed that the operational range of firefighting activities and vulnerable areas can be determined by studying the connection between the fire hydrant locations and the fire brigade in the analysis of the accessible areas. This study contributes to the development of GIS analysis methods for comprehensive vulnerability analyses of firefighting activities, including accessibility to fire hydrants.

This study analyzed changes in outdoor PM2.5 concentrations at 140 evacuation sites across five municipalities during the first 8 h period after the first evacuation alert was issued in each region following the March 2025 Gyeongbuk wildfire in Uiseong. Hourly spatial distributions of PM2.5 were estimated using inverse distance weighting (IDW) interpolation, and concentrations at each evacuation site were assessed according to the U.S. EPA Air Quality Index (AQI) criteria. The timing of peak PM2.5 concentrations varied among municipalities. Analysis of evacuation site-hour observations showed that Uiseong recorded the highest number of hazardous-category AQI readings (55), indicating repeated periods of elevated smoke exposure during the later stages of the observation period. These findings suggest that the current evacuation framework, centered on firefront arrival time, may not fully capture the temporal variability and overall level of PM2.5 exposure., and underscore the importance of incorporating smoke exposure into wildfire evacuation planning and associated public health guidance.

This study predicts the spatial distribution of heat-related illness occurrences at high resolution using a land cover-based dasymetric mapping technique. To address the limitations of conventional administrative unit-based analyses, we combined detailed land cover maps with location-specific heat illness occurrence data to calculate the Heat Illness Occurrence Possibility Index (HIOPI) at the grid level. Hotspot analysis of the grid-level HIOPI values revealed that high-risk areas were closely aligned with the actual patient distributions. By enabling fine-scale spatial analysis beyond administrative boundaries, this methodology effectively identifies heat-vulnerable areas and demonstrates its potential to support more efficient heatwave response policy development and resource allocation.