Climate change caused by global warming has resulted in an increase in average temperature and changes in precipitation pattern and intensity. Consequently, this has led to an increase in localized heavy rain which intensifies the uncertainty of the development of urban areas. To minimize flood damage in an urban area, this study aims to analyze the flood risk effect on buildings by ranking the risk of flood damage for each building type and sorting the long-term land use plan and the building type that requires particular consideration. To evaluate the flood risk of each building type, vulnerability analysis and exposure analysis were conducted in five regions of the Ulsan City. The vulnerability analysis includes determination of each building type by using the building elements which are sensitive to flood damage. In terms of the exposure analysis, environmental factors were applied to analyze the flood depth. The mapping based on the results from two analyses provided the basis for classifying the flood risk into five classes (green, yellowish green, yellow, orange, red). The results were provided in the urban spatial form for each building type. This analysis shows that the district near the Taehwa river is the area with the highest risk class buildings (red and orange class buildings). Notably, this area plays a pivotal functional role in administrating the Ulsan City and has a high density of buildings. This phenomenon is explained by city development which is centered around the lowland; however, given the high value of property, the potential risk is proven to be high.

Air pollution is a critical problem that is of major concern worldwide. South Korea is one of the countries most affected by air pollution. Rapid urbanization and industrialization in South Korea have induced air pollution in multiple forms, such as smoke from factories and exhaust from vehicles. In this paper, we perform a comparative analysis of predictive models for fine particulate matter in Daejeon, the fifth largest city in South Korea. This study is conducted for three purposes. The first purpose is to determine the factors that may cause air pollution. Two main factors are considered: meteorological and traffic. The second purpose is to find an optimal predictive model for air pollutant concentration. We apply machine learning and deep learning models to the collected dataset to predict hourly air pollutant concentrations. The accuracy of the deep learning models is better than that of the machine learning models. The third purpose is to analyze the influence of road conditions on predicting air pollutant concentration. Experimental results demonstrate that considering wind direction and wind speed could significantly decrease the error rate of the predictive models.

As the usage of solar power generation increases, it has become essential to predict power generation accurately. Among the various factors that affect solar power generation, soiling on the panel surface drastically reduces solar power generation. Therefore, accurately identifying the area of soiling on the panel surface helps predict solar power generation. However, most existing studies classify the presence or absence of soiling on the panel or the type of soiling. Additionally, current datasets used for training these models, such as the Solar Panel Soiling Image (SPSI) dataset, suffer from limitations, including a lack of diversity in panel types and a small number of unique soiling shapes. To address these issues, we propose three novel data augmentation techniques—Naïve, Realistic, and Translucent—that generate diverse solar panel images with various soiling patterns. Using Pix2Pix and Copy-Paste methods, we created three corresponding datasets to address the imbalances in the existing SPSI dataset. We trained the DeepLabV3+ model for soiling localization using both the original SPSI dataset and our augmented datasets. Experimental evaluations on real-world solar panels installed at Chungbuk National University demonstrated that models trained on our proposed datasets significantly outperform those trained on SPSI data, with improvements in the Jaccard Index of 3.3%, 2.4%, and 14.6% for the Naïve, Realistic, and Translucent datasets, respectively. These results highlight the effectiveness of our data augmentation techniques for improving soiling localization in solar panels.

Ensemble deep learning methods have demonstrated significant improvements in forecasting the solar panel power generation using historical time-series data. Although many studies have used ensemble deep learning methods with various data partitioning strategies, most have only focused on improving the predictive methods by associating several different models or combining hyperparameters and interactions. In this study, we contend that we can enhance the precision of power generation forecasting by identifying a suitable data partition strategy and establishing the ideal number of partitions and subset sizes. Thus, we propose a feasibility study of the influence of data partition strategies on ensemble deep learning. We selected five time-series data partitioning strategies—window, shuffle, pyramid, vertical, and seasonal—that allow us to identify different characteristics and features in the time-series data. We conducted various experiments on two sources of solar panel datasets collected in Seoul and Gyeongju, South Korea. Additionally, LSTM-based bagging ensemble models were applied to combine the advantages of several single LSTM models. The experimental results reveal that the data partition strategies positively influence the forecasting of power generation. Specifically, the results demonstrate that ensemble models with data partition strategies outperform single LSTM models by approximately 4–11% in terms of the coefficient of determination (R²) score.

Glove detection in manufacturing environments is challenging due to glove-background blending and limited dataset diversity. To address this, we propose a multimodal detection framework that enhances segmentation models through wrist keypoint-guided feature fusion, effectively reducing false negatives. We also introduce a unified dataset spanning five manufacturing domains to improve generalizability. Experimental results show our method achieves mAP 0.821, outperforming the baseline YOLOv11-Seg (mAP 0.792). This highlights the effectiveness of feature fusion between segmentation and keypoints for accurate and reliable glove compliance monitoring in industrial settings.

Urban flooding is a global challenge that is expected to worsen as urbanization progresses and climate change worsens. Owing to its uncertainty, however, technical measures to handle this issue are limited. In this light, this study aims to improve the local disaster response capacity in the long-term by focusing on the urban space, especially green infrastructure, and by identifying the impact of green infrastructure on the occurrence of flooding. This study selected urban spatial factors and through a multiple regression analysis found that green infrastructure and urbanization sectors influenced urban flooding. To examine the urban parks with the highest influence in detail, spatial heterogeneity was analyzed through a geographically weighted regression (GWR) analysis of the factors affecting the occurrence of flooding. The study discovered that the more urbanized a city is, the greater the influence that parks have on flooding. This result can be used to reduce the occurrence of urban flooding and bring the hydrological response closer to that of the pre-urban state, as well as to prepare more appropriate green infrastructure designs and plans to improve regional disaster response capacity.