• Journal of the Korea Institute of Building Construction
• /
• v.15 no.5
• /
• pp.515-525
• /
• 2015

Currently, according to the climate change, serious damage by typhoon has been occurred in the world. In this respect, the research on the prediction model to minimize the damage from various natural disaster has been conducted in several developed countries. In the case of U.S, various models to predict building damage costs have been used widely in many organizations such as insurance companies and governments. In South Korea, although studies regarding damage prediction model according to typhoon have been conducted, the scope has been only limited to consider the property of typhoon. However, it is necessary to consider various factors such as typhoon information, geography, construction environment, and socio-economy factors to predict the damages. Therefore, to address this issue, first, correlation analysis is conducted between various variables based on the data of typhoon from 2003 to 2012. Second, the damage prediction model by using regression analysis is developed based on suggested influence factors. The findings of this study can be utilized to develop the model for predicting the damage costs of buildings by typhoon like HAZUS-MH of US.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.4
• /
• pp.603-610
• /
• 2018

The development of industry and the increase in the use of fossil fuels have accelerated the process of global warming and climate change, resulting in more frequent and intense natural disasters than ever before. Since electricity facilities are often installed outdoors, they are heavily influenced by natural disasters and the number of related accidents is increasing. In this paper, we analyzed the statistical status of domestic electrical fires, electric shock accidents, and electrical equipment accidents and hence analyzed the risk associated with climate change. Through the analysis of the electrical accidental data in connection with the various regional (metropolitan) climatic conditions (temperature, humidity), the risk rating and charts for each region and each equipment were produced. Based on this analysis, a basic electric risk prediction model is presented and a method of displaying an electric hazard prediction map for each region and each type of electric facilities through a website or smart phone app was developed using the proposed analysis data. In addition, efforts should be made to increase the durability of the electrical equipment and improve the resistance standards to prevent future disasters.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.69-75
• /
• 2019

The frequency of natural disasters and the scale of damage are increasing due to the abnormal weather phenomenon that occurs worldwide. Especially, damage caused by natural disasters in coastal areas around the world such as Earthquake in Japan, Hurricane Katrina in the United States, and Typhoon Maemi in Korea are huge. If we can predict the damage scale in response to disasters, we can respond quickly and reduce damage. In this study, we developed damage prediction functions for Wind waves caused by sea breezes and waves during various natural disasters. The disaster report (1991 ~ 2017) has collected the history of storm and typhoon damage in coastal areas in Korea, and the amount of damage has been converted as of 2017 to reflect inflation. In addition, data on marine weather factors were collected in the event of storm and typhoon damage. Regression analysis was performed through collected data, Finally, predictive function of the sea turbulent damage by the sea area in 74 regions of the country were developed. It is deemed that preliminary damage prediction can be possible through the wind damage prediction function developed and is expected to be utilized to improve laws and systems related to disaster statistics.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.31-31
• /
• 2023

During December 2022, the northeast monsoon, which dominates the south and the Gulf of Thailand, had significant rainfall that impacted the lower southern region, causing flash floods, landslides, blustery winds, and the river exceeding its bank. The Golok River, located in Narathiwat, divides the border between Thailand and Malaysia was also affected by rainfall. In flood management, instruments for measuring precipitation and water level have become important for assessing and forecasting the trend of situations and areas of risk. However, such regions are international borders, so the installed measuring telemetry system cannot measure the rainfall and water level of the entire area. This study aims to predict 72 hours of water level and evaluate the situation as information to support the government in making water management decisions, publicizing them to relevant agencies, and warning citizens during crisis events. This research is applied to machine learning (ML) for water level prediction of the Golok River, Lan Tu Bridge area, Sungai Golok Subdistrict, Su-ngai Golok District, Narathiwat Province, which is one of the major monitored rivers. The eXtreme Gradient Boosting (XGBoost) algorithm, a tree-based ensemble machine learning algorithm, was exploited to predict hourly water levels through the R programming language. Model training and testing were carried out utilizing observed hourly rainfall from the STH010 station and hourly water level data from the X.119A station between 2020 and 2022 as main prediction inputs. Furthermore, this model applies hourly spatial rainfall forecasting data from Weather Research and Forecasting and Regional Ocean Model System models (WRF-ROMs) provided by Hydro-Informatics Institute (HII) as input, allowing the model to predict the hourly water level in the Golok River. The evaluation of the predicted performances using the statistical performance metrics, delivering an R-square of 0.96 can validate the results as robust forecasting outcomes. The result shows that the predicted water level at the X.119A telemetry station (Golok River) is in a steady decline, which relates to the input data of predicted 72-hour rainfall from WRF-ROMs having decreased. In short, the relationship between input and result can be used to evaluate flood situations. Here, the data is contributed to the Operational support to the Special Water Resources Management Operation Center in Southern Thailand for flood preparedness and response to make intelligent decisions on water management during crisis occurrences, as well as to be prepared and prevent loss and harm to citizens.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.67-74
• /
• 2024

In this paper, we present a study aimed at analyzing how different rainfall measurement methods affect the performance of reservoir water level predictions. This work is particularly timely given the increasing emphasis on climate change and the sustainable management of water resources. To this end, we have employed rainfall data from ASOS, AWS, and Thiessen Network-based measures provided by the KMA Weather Data Service to train our neural network models for reservoir yield predictions. Our analysis, which encompasses 34 reservoirs in Jeollabuk-do Province, examines how each method contributes to enhancing prediction accuracy. The results reveal that models using rainfall data based on the Thiessen Network's area rainfall ratio yield the highest accuracy. This can be attributed to the method's accounting for precise distances between observation stations, offering a more accurate reflection of the actual rainfall across different regions. These findings underscore the importance of precise regional rainfall data in predicting reservoir yields. Additionally, the paper underscores the significance of meticulous rainfall measurement and data analysis, and discusses the prediction model's potential applications in agriculture, urban planning, and flood management.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.44 no.4
• /
• pp.443-463
• /
• 2024

This study sought to improve the accuracy of precipitation prediction by utilizing monthly precipitation data for each region over the past 30 years. Using statistical models (ARIMA, SARIMA) and deep learning models (LSTM, GBM), we learned monthly precipitation data from 1983 to 2012 in Gangneung, Gwangju, Daegu, Daejeon, Busan, Seoul, Jeju, and Chuncheon. Based on this, monthly precipitation was predicted for 10 years from 2013 to 2022. As a result of the prediction, most models accurately predicted the precipitation trend, but showed a tendency to underpredict the actual precipitation. To solve these problems, appropriate models were selected for each region and season. The LSTM model showed suitable results in Gangneung, Gwangju, Daegu, Daejeon, Busan, Seoul, Jeju, and Chuncheon. When comparing forecasting power by season, the SARIMA model showed particularly suitable forecasting performance in winter in Gangneung, Gwangju, Daegu, Daejeon, Seoul, and Chuncheon. Additionally, the LSTM model showed higher performance than other models in the summer when precipitation is concentrated. In conclusion, closely analyzing regional and seasonal precipitation patterns and selecting the optimal prediction model based on this plays a critical role in increasing the accuracy of precipitation prediction.

• Journal of Trauma and Injury
• /
• v.18 no.2
• /
• pp.141-147
• /
• 2005

Purpose: Recently, The new Injury Severity Score (NISS) has become a more accurate predictor of mortality than the traditional Injury Severity Score (ISS) in the trauma population. Trauma Score Injury Severity Score (TRISS) method, regarded as the gold standard for mortality prediction in trauma patients, still contains the ISS as an essential factor within its formula. The purpose of this study was to determine whether a simple modification of the TRISS by replacing the ISS with the NISS would improve the prediction of in-hospital mortality in a trauma population with blunt head and neck trauma. Objects and Methods: The study population consisted of 641 patients from a regional emergency medical center in Kyoungsangnam-do. Demographic data, clinical information, the final diagnosis, and the outcome for each patient were collected in a retrospective manner. the ISS, NISS, TRISS, and modified TRISS were calculated for each patients. The discrimination and the calibration of the ISS, NISS, modified TRISS and conventional TRISS models were compared using receiver operator characteristic (ROC) curves, areas under the ROC curve (AUC) and Hosmer-Lemeshow statistics. Results: The AUC of the ISS, NISS, modified TRISS, and conventional TRISS were 0.885, 0.941, 0.971, and 0.918 respectively. Statistical differences were found between the ISS and the NISS (p=0.008) and between the modified TRISS and the conventional TRISS (p=0.009). Hosmer-Lemeshow chi square values were 13.2, 2.3, 50.1, and 13.8, respectively; only the conventional TRISS failed to achieve the level of and an excellent calibration model (p<0.001). Conclusion: The modified TRISS is a more accurate predictor of in-hospital mortality than the conventional TRISS in a trauma population of blunt head and neck trauma.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.2
• /
• pp.125-135
• /
• 2005

Generation and transport of nonpoint source pollution, especially sediment-associated pollutants, are profoundly influenced by hydrologic features of runoff. In order to identify pollutant export rates, hence, clear knowledge of rainfall-runoff relationship is a pre-requisition. In this study, performance of AnnAGNPS model was assessed based on the ability of the model to predict rainfall-runoff relationship. Three catchments, each under different nearly single land use, were simulated. From the results, it was found that the model was likely to produce better predictions for larger catchments than smaller catchments. Because of using the daily time scale, the model could not account for short durations less than 24 hours, especially high intensity events with multiple peak flow that significantly contribute to the generation and transport of pollutants. Since CN information for regional areas has not been built up, a careful selection of CN is needed to achieve accurate prediction of runoff volume. Storm distribution also found to be considered as an important calibration parameter for the hydrologic simulation.

• Journal of Environmental Science International
• /
• v.17 no.2
• /
• pp.195-201
• /
• 2008

Damage from typhoon disaster can be mitigated by grasping and dealing with the damage promptly for the regions in typhoon track. What is this work, a technique to analyzed dangerousness of typhoon should be presupposed. This study estimated 10 m level wind speed using 700 hPa wind by typhoon, referring to GPS dropwindsonde study of Franklin(2003). For 700 hPa wind, 30 km resolution data of Regional Data Assimilation Prediction System(RDAPS) were used. For roughness length in estimating wind of 10 m level, landuse data of USGS are employed. For 10 m level wind speed of Typhoon Rusa in 2002, we sampled AWS site of $7.4{\sim}30km$ distant from typhoon center and compare them with observational data. The results show that the 10 m level wind speed is the estimation of maximum wind speed which can appear in surface by typhoon and it cannot be compared with general hourly observational data. Wind load on domestic buildings relies on probability distributions of extreme wind speed. Hence, calculated 10 m level wind speed is useful for estimating the damage structure from typhoon.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.529-534
• /
• 2009

Climate models, both global and regional, have increased in sophistication and are being run at increasingly higher resolutions. The Land Surface Models (LSMs) coupled to these climate models have evolved from simple bucket models to sophisticated Soil-Vegetation-Atmosphere Transfer (SVAT) schemes needed to support complex linkages and processes. However, some underpinnings of terrestrial hydrologic parameterizations so crucial in the predictions of surface water and energy fluxes cause model errors that often manifest as non-linear drifts in the dynamic response of land surface processes. This requires the improved parameterizations of key processes for the terrestrial hydrologic scheme to improve the model predictability in surface water and energy fluxes. The Common Land Model (CLM), one of state-of-the-art LSMs, is the land component of the Community Climate System Model (CCSM). However, CLM also has energy and water biases resulting from deficiencies in some parameterizations related to hydrological processes. This research presents the implementation of a selected set of parameterizations and their effects on the runoff prediction. The modifications consist of new parameterizations for soil hydraulic conductivity, water table depth, frozen soil, soil water availability, and topographically controlled baseflow. The results from a set of offline simulations are compared with observed data to assess the performance of the new model. It is expected that the advanced terrestrial hydrologic scheme coupled to the current CLM can improve model predictability for better prediction of runoff that has a large impact on the surface water and energy balance crucial to climate variability and change studies.