• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1709-1722
• /
• 2022

The rise in temperature induced by global warming caused in El Nino and La Nina, and abnormally changed the temperature of seawater. Rainfall concentrates in some locations due to abnormal variations in seawater temperature, causing frequent abnormal floods. It is important to rapidly detect flooded regions to recover and prevent human and property damage caused by floods. This is possible with synthetic aperture radar. This study aims to generate a model that directly derives flood-damaged areas by using modified U-NET and TerraSAR-X images based on Multi Kernel to reduce the effect of speckle noise through various characteristic map extraction and using two images before and after flooding as input data. To that purpose, two synthetic aperture radar (SAR) images were preprocessed to generate the model's input data, which was then applied to the modified U-NET structure to train the flood detection deep learning model. Through this method, the flood area could be detected at a high level with an average F1 score value of 0.966. This result is expected to contribute to the rapid recovery of flood-stricken areas and the derivation of flood-prevention measures.

• Journal of Korea Water Resources Association
• /
• v.55 no.2
• /
• pp.121-133
• /
• 2022

The drought resulting from insufficient rainfall compared to the amount in an ordinary year can significantly impact a broad area at the same time. Another feature of this disaster is hard to recognize its onset and disappearance. Therefore, a reliable and fast way of predicting both the suffering area and the amount of water shortage from the upcoming drought is a key issue to develop a countermeasure of the disaster. However, the available drought scenarios are about 50 events that have been observed in the past. Due to the limited number of events, it is difficult to predict the water shortage in a case where the pattern of a natural disaster is different from the one in the past. To overcome the limitation, in this study, we applied the four RCP climate change scenarios to the water balance model and the annual amount of water shortage from 360 drought events was estimated. In the following chapter, the deep neural network model was trained with the SPEI values from the RCP scenarios and the amount of water shortage as the input and output, respectively. The trained model in each sub-basin enables us to easily and reliably predict the water shortage with the SPEI values in the past and the predicted meteorological conditions in the upcoming season. It can be helpful for decision-makers to respond to future droughts before their onset.

• Journal of the Korean Geotechnical Society
• /
• v.37 no.11
• /
• pp.93-105
• /
• 2021

In this study, we evaluated the effect of soil fine contents on the formation of underground cavities and ground cave-ins induced by damaged sewer pipes. Simulating the domestic rainfall conditions and ground conditions, model tests were performed under three different fine particle contents conditions (7.5%, 15%, and 25%). By repeating the groundwater supply and drainage twice, ground settlement and the amount of discharged soil were obtained. Also, digital images were taken at regular time intervals during the model tests, and internal displacement and deformation were measured using PIV technique. As the cycles were repeated, the soil with high fine content showed greater resistance to the formation of underground cavities. The ground cave-ins, identified by the collapse of the surface, occurred only when the fine particle content was 15%. It is presumed to be due to the suffusion phenomenon; further study was needed to investigate the effect of fine particle contents on the suffusion phenomenon and associated changes of soil strength.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.2B
• /
• pp.169-177
• /
• 2010

Recently due to the typhoon and extreme rainfall induced by abnormal weather and climate change, the probability of severe damage to human life and property is rapidly increasing. Thus it is necessary to create adequate and reliable flood risk map in preparation for those natural disasters. The study area is Seo-gu in Daegu which is located near Geumho river, one of the tributaries of Nakdong river. Inundation depth and velocity at each time were calculated by applying FLUMEN model to the target area of interest, Seo-gu in Daegu. And the research of creating flood risk map was conducted according to the Downstream Hazard Classification Guidelines of USBR. The 2-dimensional inundation analysis for channels and protected lowland with FLUMEN model was carried out with the basic assumption that there's no levee failure against 100 year precipatation and inflow comes only through the overflowing to the protected lowland. The occurrence of overflowing was identified at the levee of Bisan-dong located in Geumho watershed. The level of risk was displayed for house/building residents, drivers and pedestrians using information about depth and velocity of each node computed from the inundation analysis. Once inundation depth map and flood risk map for each region is created with this research method, emergency action guidelines for residents can be systemized and it would be very useful in establishing specified emergency evacuation plans in case of levee failure and overflowing resulting from a flood.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.21 no.4
• /
• pp.64-80
• /
• 2018

In Korea, citizens can only know general information about crime. Thus it is difficult to know how much they are exposed to crime. If the police can predict the crime risky area, it will be possible to cope with the crime efficiently even though insufficient police and enforcement resources. However, there is no prediction system in Korea and the related researches are very much poor. From these backgrounds, the final goal of this study is to develop an automated crime prediction system. However, for the first step, we build a big data set which consists of local real crime information and urban physical or non-physical data. Then, we developed a crime prediction model through machine learning method. Finally, we assumed several possible scenarios and calculated the probability of crime and visualized the results in a map so as to increase the people's understanding. Among the factors affecting the crime occurrence revealed in previous and case studies, data was processed in the form of a big data for machine learning: real crime information, weather information (temperature, rainfall, wind speed, humidity, sunshine, insolation, snowfall, cloud cover) and local information (average building coverage, average floor area ratio, average building height, number of buildings, average appraised land value, average area of residential building, average number of ground floor). Among the supervised machine learning algorithms, the decision tree model, the random forest model, and the SVM model, which are known to be powerful and accurate in various fields were utilized to construct crime prevention model. As a result, decision tree model with the lowest RMSE was selected as an optimal prediction model. Based on this model, several scenarios were set for theft and violence cases which are the most frequent in the case city J, and the probability of crime was estimated by $250{\times}250m$ grid. As a result, we could find that the high crime risky area is occurring in three patterns in case city J. The probability of crime was divided into three classes and visualized in map by $250{\times}250m$ grid. Finally, we could develop a crime prediction model using machine learning algorithm and visualized the crime risky areas in a map which can recalculate the model and visualize the result simultaneously as time and urban conditions change.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.13 no.2
• /
• pp.54-63
• /
• 2010

The intensive rainfall over 455 mm occurred between on 9 to 14 July 2009 triggered debris flows around the mountain area in Jecheon County. We mapped the debris flow area and estimated the debris flow volume using a high resolution digital elevation model (DEM) generated respectively from terrestrial LiDAR (Light Detection And Ranging) and topographic maps. For the LiDAR measurement, the terrestrial laser scanning system RIEGL LMS-Z390i which is equipped with GPS system and high-resolution digital camera were used. After the clipping and filtering, the point data generated by LiDAR scanning were overlapped with digital map and produced DEM after debris flow. The comparison between digital map and LiDAR scanning result showed the erosion and deposition volumes of about $17,586m^3$ and $7,520m^3$, respectively. The LiDAR data allowed comprehensive investigation of the morphological features present along the sliding surface and in the deposit areas.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.15 no.3
• /
• pp.161-170
• /
• 2013

Spatio-temporal distribution of soil moisture was studied to improve understanding of hydrological processes at hillslope scale. Using field measurements for three designated periods during the spring, summer and autumn seasons in 2010 obtained from Beomryunsa hillslope located at the Sulmachun watershed, correlation analysis was performed between soil moisture measurements and 18 different terrain attributes (e.g., curvatures and topographic index). The results of correlation analysis demonstrated distinct seasonal variation features of soil moisture in different depths with different terrain attributes and rainfall amount. The relationship between predicted flow lines and distribution of the soil moisture provided appropriate model structures and terrain indices.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.1
• /
• pp.21-30
• /
• 2020

In this paper, we predicted the propagation loss for the air-to-ground (A2G) channel between the ground control system and the unmanned aerial vehicle (UAV) using the prediction model for the aircraft recommended by the International Telecommunication Union (ITU). We analyzed the network coverage of the aerial relay system based on the medium altitude UAVs by expanding it into the air-to-air (A2A) channel. Climate and geographic factors in Korea were used to predict propagation loss due to atmospheres. We used the measured data published by the Telecommunication Technology Association (TTA) for regional rainfall-rate and effective earth radius factors to increase accuracy. In addition, the aerial relay communication system used the key parameter of the common data link (CDL) system developed in Korea recently. Prediction results show that the network coverage of the aerial relay system broadens at higher altitude.

• Journal of Korea Water Resources Association
• /
• v.53 no.7
• /
• pp.521-531
• /
• 2020

The purpose of this study is to suggest a quantitative assessment of wetland damage considering the effects of topsoil erosion and deposition from rainfall. In the Cheoncheon Basin located upstream of the Yongdam Dam, 16 wetlands are located, but the lacustrine and small palustrine wetland were analyzed for possible damage to erosion and deposition. As a result of applying typhoon events in 2002 and 2003, the sediment load from the upper basin was the highest at 2.30% (22,548 ㎥) of low water capacity. The average sediment load in the mountain areas was found to be 0.03% of the low water capacity, and it was analyzed to be less damaging than the lacustrine with relatively large watershed. as a result of the model, the lacustrine wetland, where a large area is used as agricultural land, shows a high probability of sediment yield, so it is highly likely to damage the wetland by topsoil erosion.

• Journal of Korean Society on Water Environment
• /
• v.34 no.1
• /
• pp.57-66
• /
• 2018

Water disasters such as flash floods and inundation caused by localized heavy rainfall in urban areas have a large impact on climate change but are also closely related to the increase in impervious areas as pointed out in domestic and international studies. It is difficult to secure natural green areas in urban areas that have already been developed. So, urban regeneration can be expected using water management optimized with technologies to secure infiltration and storage capacity such as Low-Impact Development technology. In this study, the water cycle improvement ability was confirmed by applying the LID technology within the district unit plan of the environmentally friendly village, and the economic feasibility of LID application was analyzed by estimating the costs and benefits of installing the facilities. The site was planned to conserve sufficient green and plans for securing the watershed infiltration and storage capacity were formulated with the application of additional LID technology, such as infiltration trenches, rain barrels and permeable pavements. The LID design method applicable to the site was established, and the water balance of the watershed was analyzed through simulations of the SWMM model. The water circulation improvement effect was confirmed through the water balance analysis, and the cost-benefits were determined according to the estimation method, and the economic analysis was conducted. This study confirms that the investment of LID technology is economically feasible for the hydrological improvement effect of the housing complex.