Sang-Won Lee

The risk and damage caused by steep slope collapses within the Korean Peninsula are increasing because of abnormal weather patterns resulting from climate change. Consequently, there is a growing need for proactive disaster management, leading to the registration and management of steep slopes prone to collapse within the jurisdiction through nationwide surveys. The necessity for domestic steep slope management has recently become apparent although the management system has some issues in establishing and refining it to reflect reality. In this study, the appropriateness of the results obtained from the 2022 nationwide survey of steep slope areas was evaluated utilizing the characteristics of steep slopes (types, structures, heights, lengths, slopes, and landowners.), disaster risk (disaster risk grades and risk factors), and risk mitigation measures (structural and nonstructural), to propose improvement measures. Through this, we identified problems with the methodology for selecting target areas, funding for steep slope management, impact assessment of disasters, and results of reviewing non-structural measures, thereby proposing improvements in the management of privately owned steep-slope areas. By improving the survey system, which is an essential element for responding to steep slope disasters, to reflect reality, the costs of damage and recovery caused by steep-slope collapses are expected to significantly decrease.

This study outlines the preliminary stages of the development of an algorithm to predict the optimal WQ of the Hwanggujicheon Stream. In the first stages, we used the AdaBoost algorithm model to predict the state of WQ, using data from the open artificial intelligence (AI) hub. The AdaBoost algorithm has excellent predictive performance and model suitability and was selected for random forest and gradient boosting (GB)-based boosting models. To predict the optimized WQ, we selected pH, SS, water temperature, total nitrogen(TN), dissolved total phosphorus(DTP), NH₃-N, chemical oxygen demand (COD), dissolved total nitrogen (DTN), and NO₃-N as the input variables of the AdaBoost model. Dissolved oxygen (DO) was used as the target variable. Third, an algorithm showing excellent predictive power was selected by analyzing the prediction accuracy according to the input variable by using the random forest or GB series algorithm in the initial model. Finally, the performance evaluation of the ultimately developed predictive model demonstrated that RMS was 0.015, MAE was 0.009, and R² was 0.912. The coefficient of the variation of the root mean square error (CVRMSE) was 17.404. R² 0.912 and CVRMSE were 17.404, indicating that the predictive model developed meets the criteria of ASHRAE Guideline 14. It is imperative that government and administrative agencies have access to effective tools to assess WQ and pollution levels in their local bodies of water.