• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.506-506
• /
• 2002

S. Korean Government has accelerating its efforts to enhance the quality of the drinking water. The Ministry of Environment has declared the law of securing water-pollutant buffering zone to minimize the inflow of the point and nonpoint sources into the drinking water sources. As a first phase of installing nationa-wide water-pollutant buffering zone, approximately 300km buffering zone has been delineated along the South and North Han river, the major drinking water sources for the capital area of S. Korea, which has the population of more than 12 millions. The buffering zone has the width of 1,000 meter for the special protection area, and 500 meter for the remaining area from both ends of the river. The major works have been done in three stages. Firstly, the boundaries lines of the buffering zone was delineated on the digital topographic maps. Secondly, the maps were overlayed with the cadastral maps to identify individual land parcels, the street address of the major pollutant discharging facilities, and all different types of pollutants including livestocks. Thirdly, the field work has been done as a verification. Once the buffering zone was generated, all the information for the buffering gone were created or imported from other government agencies including official land price, details of the major manufacturing facilities discharging considerable amount of pollutants, major motels and resorts, not to mention of restaurants, etc. Also, major livestock houses were located to identify the path of the pollutant inflow to the drinking water source. Further works need to be continued such as purchasing private lands within the buffering zone and change the land use in the efforts to decrease the pollutant amount and to provide more environmentally friendly space. Also, high resolution satellite imagery should be utilized in the near future as a cost-effective data source to update all the landuse activities within buffering zone.

• Economic and Environmental Geology
• /
• v.38 no.1
• /
• pp.33-43
• /
• 2005

The purpose of this study is to make and validate landslide susceptibility map using artificial neural network and GIS in Kangneung area. For this, topography, soil, forest, geology and land cover data sets were constructed as a spatial database in GIS. From the database, slope, aspect, curvature, water system, topographic type, soil texture, soil material, soil drainage, soil effective thickness, wood type, wood age, wood diameter, forest density, lithology, land cover, and lineament were used as the landslide occurrence factors. The weight of the each factor was calculated, and applied to make landslide susceptibility maps using artificial neural network. Then the maps were validated using rate curve method which can predict qualitatively the landslide occurrence. The landslide susceptibility map can be used to reduce associated hazards, and to plan land use and construction as basic data.

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.395-409
• /
• 2022

The purpose of this study is to evaluate the classification performance and applicability when land cover datasets constructed for AI training are cross validation to other areas. For study areas, Gyeongsang-do and Jeolla-do in South Korea were selected as cross validation areas, and training datasets were obtained from AI-Hub. The obtained datasets were applied to the U-Net algorithm, a semantic segmentation algorithm, for each region, and the accuracy was evaluated by applying them to the same and other test areas. There was a difference of about 13-15% in overall classification accuracy between the same and other areas. For rice field, fields and buildings, higher accuracy was shown in the Jeolla-do test areas. For roads, higher accuracy was shown in the Gyeongsang-do test areas. In terms of the difference in accuracy by weight, the result of applying the weights of Gyeongsang-do showed high accuracy for forests, while that of applying the weights of Jeolla-do showed high accuracy for dry fields. The result of land cover classification, it was found that there is a difference in classification performance of existing datasets depending on area. When constructing land cover map for AI training, it is expected that higher quality datasets can be constructed by reflecting the characteristics of various areas. This study is highly scalable from two perspectives. First, it is to apply satellite images to AI study and to the field of land cover. Second, it is expanded based on satellite images and it is possible to use a large scale area and difficult to access.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.6 no.2
• /
• pp.101-112
• /
• 2003

This paper designs and implements the management system that can calibrate the contamination vulnerability of the ground water, using an object oriented data model. Geographic-objects are specified by features extracted from an applicable geographic domain, and geographic-fields are defined by chemical factors extracted from each driven water. To show the topological relationships among the geographic-objects and the geographic-fields, this paper attach the weight and the ratio of the drastic model to chemical factors represented on the land use digital map and the ground water digital map. The geographic feature class, administrative boundary class, land use class and driven water class consist of a class composition hierarchy for evaluating the convenient contamination vulnerability calibration with spatial relationships among the well objects. Therefore, this management system for evaluating the contamination vulnerability can also contribute to the application of other natural environments.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.4
• /
• pp.25-33
• /
• 2015

The study of ecosystem assessment(ES) is based on land cover information, and primarily it is performed at the global scale. However, these results as data for decision making have a limitation at the aspects of range and scale to solve the regional issue. Although the Ministry of Environment provides available land cover data at the regional scale, it is also restricted in use due to the intrinsic limitation of on screen digitizing method and temporal and spatial difference. This study of objective is to generate UAV land cover map. In order to classify the imagery, we have performed resampling at 5m resolution using UAV imagery. The results of object-based image segmentation showed that scale 20 and merge 34 were the optimum weight values for UAV imagery. In the case of RapidEye imagery;we found that the weight values;scale 30 and merge 30 were the most appropriate at the level of land cover classes for sub-category. We generated land cover imagery using example-based classification method and analyzed the accuracy using stratified random sampling. The results show that the overall accuracies of RapidEye and UAV classification imagery are each 90% and 91%.

• Journal of Environmental Impact Assessment
• /
• v.27 no.1
• /
• pp.73-82
• /
• 2018

The purpose of this study is the evaluation of the impact of increase in impervious areas due to urbanization on the pollutant discharge using the HSPF model at Musim watershed. Model calibration and validation were performed based on the observed data 2015 and 2014, all simulation items have been successfully simulated such as flow, BOD, and TP. The land cover map used in the model reflected on the land use status of the Musim watershed in 2015 and the application of the development areas and locations. As a result of simulation, during rainfall daily pollutant load with the increased impervious land increased more than that before the development. However, the pollutant load decreased during the non-rainfall time. Annual pollutant load in rainfall time was significantly higher than that in non-rainfall time, BOD and TP increased. The simulation of non-point source pollutant load was applied under two assumptions, such as the increased area of impervious land and the non-change number of point source load before and after development. As the result of a simulation, the non-point source pollutant load after development was bigger than those before development. It was necessary to take measures to control non-point source pollution at the consideration status of development.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.1
• /
• pp.113-121
• /
• 2015

Remote sensing technology using a multi-spectral satellite imagery can be utilized for the analysis of urban heat island effect in large area. However, weather condition of Korea mostly has a lot of clouds and it makes periodical observation using time-series of satellite images difficult. For this reason, we proposed the analysis of urban heat island effect using time-series of Landsat TM images and ATC model. To analyze vegetation condition and urbanization, NDVI and NDBI were calculated from Landsat images. In addition, land surface temperature was calculated from thermal infrared images to estimate the parameters of ATC model. Furthermore, the parameters of ATC model were compared based on the land cover map created by Korean Ministry of Environment to analyze urban heat island effect relating to the pattern of land use and land cover. As a result of a correlation analysis between calculated spectral indices and parameters of ATC model, MAST had high correlation with NDVI and NDBI (-0.76 and 0.69, respectively) and YAST also had correlation with NDVI and NDBI (-0.53 and 0.42, respectively). By comparing the parameters of ATC model based on land cover map, urban area had higher MAST and YAST than agricultural land and grassland. In particular, residential areas, industrial areas, commercial areas and transportation facilities showed higher MAST than cultural facilities and public facilities. Moreover, residential areas, industrial areas and commercial areas had higher YAST than the other urban areas.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.302-305
• /
• 2004

The aim of this study is to apply and crossvalidate a spatial logistic multiple-regression model at Boun, Korea, using a Geographic Information System (GIS). Landslide locations in the Boun area were identified by interpretation of aerial photographs and field surveys. Maps of the topography, soil type, forest cover, geology, and land-use were constructed from a spatial database. The factors that influence landslide occurrence, such as slope, aspect, and curvature of topography, were calculated from the topographic database. Texture, material, drainage, and effective soil thickness were extracted from the soil database, and type, diameter, and density of forest were extracted from the forest database. Lithology was extracted from the geological database and land-use was classified from the Landsat TM image satellite image. Landslide susceptibility was analyzed using landslide-occurrence factors by logistic multiple-regression methods. For validation and cross-validation, the result of the analysis was applied both to the study area, Boun, and another area, Youngin, Korea. The validation and cross-validation results showed satisfactory agreement between the susceptibility map and the existing data with respect to landslide locations. The GIS was used to analyze the vast amount of data efficiently, and statistical programs were used to maintain specificity and accuracy.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.298-301
• /
• 2004

The aim of this study is to cross-validate of spatial probability model, artificial neural network at Boun, Korea, using a Geographic Information System (GIS). Landslide locations were identified in the Boun, Janghung and Youngin areas from interpretation of aerial photographs, field surveys, and maps of the topography, soil type, forest cover and land use were constructed to spatial data-sets. The factors that influence landslide occurrence, such as slope, aspect and curvature of topography, were calculated from the topographic database. Topographic type, texture, material, drainage and effective soil thickness were extracted from the soil database, and type, diameter, age and density of forest were extracted from the forest database. Lithology was extracted from the geological database, and land use was classified from the Landsat TM image satellite image. Landslide susceptibility was analyzed using the landslide­occurrence factors by artificial neural network model. For the validation and cross-validation, the result of the analysis was applied to each study areas. The validation and cross-validate results showed satisfactory agreement between the susceptibility map and the existing data on landslide locations.

• Journal of Environmental Science International
• /
• v.15 no.4
• /
• pp.325-332
• /
• 2006

The purpose of this paper is to suggest practical suggestions to mitigate Urban Heat Island(UHI) problems in Daegu regarding urban surface temperature. Urban street trees's size and the relations between urban land use types and surface temperature are analysed using aerial photos, the numerical value map and Landsat TM image with special reference to Jung-gu. Total urban street tree's crown size is $156,217.6m^2$ and it is equal to 2.24% of study area. In addition, the size of 'city and residential area' is $6,681,870m^2$(95.7% of study area), which causes UHI and the total size of 'river' shows the lowest surface temperature area and 'road' and 'business and service area' are the highest surface temperature zones. Therefore, it is probable that the network between urban street trees and the lowest surface temperature areas mitigate UHI effects.