• Korean Journal of Remote Sensing
• /
• v.36 no.5_3
• /
• pp.1109-1123
• /
• 2020

In South Korea with forest as a major land cover class (over 60% of the country), many wildfires occur every year. Wildfires weaken the shear strength of the soil, forming a layer of soil that is vulnerable to landslides. It is important to identify the severity of a wildfire as well as the burned area to sustainably manage the forest. Although satellite remote sensing has been widely used to map wildfire severity, it is often difficult to determine the severity using only the temporal change of satellite-derived indices such as Normalized Difference Vegetation Index (NDVI) and Normalized Burn Ratio (NBR). In this study, we proposed an approach for determining wildfire severity based on machine learning through the synergistic use of Sentinel-1A Synthetic Aperture Radar-C data and Sentinel-2A Multi Spectral Instrument data. Three wildfire cases-Samcheok in May 2017, Gangreung·Donghae in April 2019, and Gosung·Sokcho in April 2019-were used for developing wildfire severity mapping models with three machine learning algorithms (i.e., Random Forest, Logistic Regression, and Support Vector Machine). The results showed that the random forest model yielded the best performance, resulting in an overall accuracy of 82.3%. The cross-site validation to examine the spatiotemporal transferability of the machine learning models showed that the models were highly sensitive to temporal differences between the training and validation sites, especially in the early growing season. This implies that a more robust model with high spatiotemporal transferability can be developed when more wildfire cases with different seasons and areas are added in the future.

• Journal of Korean Society of Disaster and Security
• /
• v.10 no.2
• /
• pp.7-19
• /
• 2017

Recently, the incidence of disasters and safety incidents is increasing rapidly, and the interest and demands of the people are increasing. In particular, traffic accidents in Korea are decreasing due to the continuous efforts of the government and the local governments, but still higher than the OECD average. In response to such demands of the times, the 'Regional Safety Index', a numerical value that quantifies the level of safety of each local government, is being publicized every year to awaken public awareness. The Regional Safety Index covers seven categories of accidents (traffic accidents, crimes, suicide, infectious diseases, fire, safety accidents, and natural disasters) in local governments. But, this study focuses on the traffic accident area and analyzed. The target local government is Ulju county of Ulsan Metropolitan City. Based on the traffic accident statistical data of Ulju county, the analysis of the traffic accidents and vulnerable points were analyzed. Among them, 3 key improvement districts were selected and 15 vulnerable branches were selected for each key improvement district. Next, we prepared measures for improvement of each accident vulnerable site through analysis of geographic information through traffic data related to traffic accidents and interview with related organizations. In addition, the improvement measures are divided into the structural infrastructure improvement, the institutional improvement, and the traffic safety culture movement from the viewpoint of traffic accident prevention. Finally, the implications of this study are to clarify the duties and roles of the relevant departments in the municipality, based on the implementation schedule of the improvement projects for the prevention of traffic accidents and the budget plan. In addition, it is very important that the participating agencies involved in traffic accidents and the private sector participate in the project.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.925-938
• /
• 2022

Agricultural reservoirs are an important water resource nationwide and vulnerable to abnormal climate effects such as drought caused by climate change. Therefore, it is required enhanced management for appropriate operation. Although water-level tracking is necessary through continuous monitoring, it is challenging to measure and observe on-site due to practical problems. This study presents an objective comparison between multiple AI models for water-body extraction using radar images that have the advantages of wide coverage, and frequent revisit time. The proposed methods in this study used Sentinel-1 Synthetic Aperture Radar (SAR) images, and unlike common methods of water extraction based on optical images, they are suitable for long-term monitoring because they are less affected by the weather conditions. We built four AI models such as Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN), and Automated Machine Learning (AutoML) using drone images, sentinel-1 SAR and DSM data. There are total of 22 reservoirs of less than 1 million tons for the study, including small and medium-sized reservoirs with an effective storage capacity of less than 300,000 tons. 45 images from 22 reservoirs were used for model training and verification, and the results show that the AutoML model was 0.01 to 0.03 better in the water Intersection over Union (IoU) than the other three models, with Accuracy=0.92 and mIoU=0.81 in a test. As the result, AutoML performed as well as the classical machine learning methods and it is expected that the applicability of the water-body extraction technique by AutoML to monitor reservoirs automatically.

• The Journal of the Petrological Society of Korea
• /
• v.24 no.4
• /
• pp.347-364
• /
• 2015

The purpose of the work was carried out to contribute the factors related to geologic realm in the disaster stability evaluation items of the national wood culture heritages. Among the total heritages, the study targets mainly include 304 cases interpreted as a rock type in the geologic map of the bedrocks with GIS interpretation. The cases show the geologic ages, geologic provinces and rock types as the following distribution characteristics. In geologic ages, they are decreasing in the orders of Jurassic, Cretaceous, Quaternary, Precambrian, Age-unknown Cambro-Ordovician Carboniferous and Tertiary. Among the ages, the former fours occupy 285 cases (93.8%) of the targets, which show most of the wood culture heritages. In geologic provinces classified into 15, they are decreasing in the orders of Daebo intrusives, alluvium, Gyeongsang supergroup, Bulgugsa intrusives, Yeongnam massif, and Gyeonggi massif which occupy of predominant distribution 271 cases (89.1%) of them. In rock types of 52, those of 6, which are Jgr, Qa, Kp, Krt+Kav+Kav1+Kav2, Kbgr and GC2, occupy total 182 cases (59.9%) showing distinctly dominant trends from the rest of 46.

• Journal of Korea Water Resources Association
• /
• v.44 no.10
• /
• pp.787-795
• /
• 2011

Extreme water events such as heavy rainfalls due to recent climate change are continually increasing and their scale has also shown an increasing trend. To overcome these natural disasters, this policy study suggests securing lateral river space as an effective method for extreme flood. To support the importance of restoration and expansion of lateral river space, Gumi upstream region of the Nakdong River basin was chosen as a target area and flood reduction analysis of the washland by using LISFLOOD model have been examined. The 500-year frequency flood was simulated for the estimation of possibly occurable flood level and it turns out that the secured lateral river space on the selected site effectively lowers about 0.53 m flood level and reduces the flood damage of the city on the lower reaches of the river. In addition, based on this result, multilateral river space securing plans were compared, and conservation easement and natural disaster insurance were suggested for sustainable and cost-effective alternatives. The costs of land purchase and conservation easement for securing the river space were also compared.

• Journal of the Korea Institute of Building Construction
• /
• v.9 no.5
• /
• pp.95-101
• /
• 2009

As buildings increase in height, lifting plans are becoming increasingly important on construction sites. As a critical piece of load-lifting equipment, the tower crane deserves a well thought-out stability review, since it has a significant impact and is very vulnerable to structural safety disaster. To ensure the structural stability of a tower crane, its lateral support or pile supported foundation designs must include consideration for stability, and pile foundation must be used if site conditions prevent soil from providing the required bearing capacity, or prevent the foundation from being increased to the required extent. Pile supported foundation design requires thorough and systematic review, as more stability parameters need to be considered than with an independent foundation. This paper intends to develop an optimal design algorithm that can minimize associated costs while ensuring the fundamental stability of pile supported foundation design, limiting the scope of research to fixed-type trolley tower cranes using pile supported foundations. The findings herein on pile foundation stability review parameters, process and optimal design are expected to improve the operational efficiency of staff concerned, and reduce the time and efforts required for pile foundation design.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.14 no.3
• /
• pp.163-173
• /
• 2011

This paper, as a case study on the evaluation of nationwide-unit forest functions, targeting the entire Gyeongsangnam-do region, examined the integration measures for the evaluation of national, public and private forest functions, as well as GIS data problems and GIS data building methods. Also, the distribution and characteristics of Gyeongsangnam-do's forest functions were examined. First, as integration measures for forest function evaluation, evaluation unit was proposed as watershed unit, and GIS techniques were proposed to correct some patterns of errors shown in the watershed maps. Also, of GIS data used for forest function evaluation, maps of locations of saw mills to be revised, expressway interchange location maps, and population distribution maps were built nationwide. Based on watershed units, the forest functions of 20 cities and counties in Gyeongsangnam-do were evaluated, revealing that wood production function and forest recreation function potentials, high-ranking was high distributed throughout the site, while most functions potentials, low-ranking was low distributed. In forest function maps with the application of priority by city and gun, the area size was ranked in the order of forest recreation, timber production, natural conservation, water yield, living environment conservation, and prevention of natural disaster. Case analysis results for large areas can be used in evaluating nationwide forest functions.

• The Journal of Engineering Geology
• /
• v.29 no.4
• /
• pp.483-494
• /
• 2019

This study aimed to determine the extent of artificial aquifer recharge and to evaluate appropriate recharge techniques based on field investigations and comparative analysis of each recharge method. Characteristics of the aquifer determine the target aquifer and the recharge method for artificial groundwater recharge. Electrical conductivity surveys, drilling, permeability tests, and grain-size analysis indicate that the hydraulic conductivity of weathered soil and weathered rock is higher than that of upper unconsolidated soil. Pumping tests indicate that the groundwater level was stable at a depth of 12 m until 9 hours of pumping, but after that it dropped again, indicating anisotropic aquifer characteristics. Three types of artificial recharge method were reviewed, including recharge wells, ditches, and ponds, and a combination of two methods is proposed: a recharge well system directly injecting into weathered soil and rock sections with good permeability, and an injection ditch that can increase the recharge effect by line-type injection in the upstream area. The extent of groundwater recharge by the selected methods will be evaluated through on-site tests and if their applicability is verified, they will contribute to securing water in areas of water shortage.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.3
• /
• pp.155-160
• /
• 2018

The unmanned aerial vehicle (UAV) is used in various fields, such as land surveying, facility management, and disaster monitoring and restoration because it has low operational costs, fast data acquisition, and can generate a digital surface model (DSM). Recently, the UAV has been applied to process management in construction projects. Construction projects are widely distributed not only in urban areas but also in mountainous areas and rural areas where people are rarely in traffic or in vehicles. Projects range from a few hundred meters to several kilometers long. In order to perform a reconnaissance survey, a surveying method using a global positioning system (GPS) or a total station has mainly been used. However, these methods have a disadvantage in that a lot of time is required for data acquisition. This study's purpose is to evaluate the usability of a UAV DSM for surveying a construction area. Data was acquired using the UAV and a three-dimensional (3D) laser scanner, and the DSM of the construction site was created through data processing. The UAV DSM showed accuracy to within 30 cm based on the 3D laser scanner data, and a process comparison between the two work methods was able to present the usability of the UAV DSM in the field of construction surveying. Future utilization of the UAV DSM is expected to greatly improve the efficiency of work in construction projects.

• Economic and Environmental Geology
• /
• v.51 no.2
• /
• pp.149-166
• /
• 2018

Many large earthquakes have continuously been reported and resulted in significant human casualties and extensive damages to properties globally. The accident of Fukushima nuclear power plant in Japan was caused by a mega-tsunami, which is a secondary effect associated with the Tohoku large earthquake (M=9.0, 2011. 3. 11.). Most earthquakes occur by reactivation of pre-existing active faults. Therefore, the importance of paleoseismological study have greatly been increased. The Korean peninsula has generally been considered to be a tectonically stable region compared with neighboring countries such as Japan and Taiwan, because it is located on the margin of the Eurasian intra-continental region. However, the recent earthquakes in Gyeongju and Pohang have brought considerable insecurity on earthquake hazard. In particular, this region should be secure against earthquake, because many nuclear facilties and large industrial facilities are located in this area. However, some large earthquakes have been reported in historic documents and also several active faults have been reported in southeast Korea. This study explains the evaluation methods of geological structures on active fault, fault damage zone, the relationship between earthquake and active fault, and respect distance. This study can contribute to selection of safe locations for nuclear facilities and to earthquake hazards and disaster prevention.