• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1591-1604
• /
• 2020

This study is a study on classifying land cover by applying high-resolution satellite images to deep learning algorithms and verifying the performance of algorithms for each spatial object. For this, the Fully Convolutional Network-based algorithm was selected, and a dataset was constructed using Kompasat-3 satellite images, land cover maps, and forest maps. By applying the constructed data set to the algorithm, each optimal hyperparameter was calculated. Final classification was performed after hyperparameter optimization, and the overall accuracy of DeeplabV3+ was calculated the highest at 81.7%. However, when looking at the accuracy of each category, SegNet showed the best performance in roads and buildings, and U-Net showed the highest accuracy in hardwood trees and discussion items. In the case of Deeplab V3+, it performed better than the other two models in fields, facility cultivation, and grassland. Through the results, the limitations of applying one algorithm for land cover classification were confirmed, and if an appropriate algorithm for each spatial object is applied in the future, it is expected that high quality land cover classification results can be produced.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.25 no.5
• /
• pp.15-27
• /
• 2022

Climate change is considered a severe global problem closely related to carbon storage. However, recent urbanization and land-use changes reduce carbon stocks in terrestrial ecosystems. Recently, the role of protected areas has been emphasized as a countermeasure to the climate change, and protected areas allow the area to continue to serve as a carbon sink due to legal restrictions. This study attempted to expand the scope of these protected areas to an evaluation-based environmental spatial information theme map. In this study, the area of each grade was compared, and the distribution of land cover for each grade was analyzed using the Ecological and Nature Map, Environmental Conservation Value Assessment Map and Urban Ecological Map of Sejong Special Self-Governing City. Based on this, the average carbon storage for each grade was derived using the InVEST Carbon model. As a result of the analysis, the high-grade area of the environmental spatial information generally showed a wide area of the natural area represented by the forest area, and accordingly, the carbon storage amount was evaluated to be high. However, there are differences in the purpose of production, evaluation items, and evaluation methods between each environmental spatial information, there are differences in area, land cover, and carbon storage. Through this study, environmental spatial information based on the evaluation map can be used for land use management in the carbon aspect, and it is expected that a management plan for each grade suitable for the characteristics of each environmental spatial information is required.

• Journal of Cadastre & Land InformatiX
• /
• v.53 no.1
• /
• pp.107-121
• /
• 2023

In order to acquire a wide range of land that changes in real time and quickly and accurately grasp it, we plan to utilize the recently released high-resolution S.Korea's satellite image data and artificial intelligence (AI). Compared to existing satellite images, the spectral and periodic resolutions of S.Korea's satellite are higher, making them a more suitable data source for periodically monitoring changes in land. Therefore, this study aims to acquire S.Korea's satellite, select 8 types of objects to detect land changes, construct data sets for them, and apply AI models to analyze them. In order to confirm the optimal model and variable conditions for detecting 8 types of objects of various types, several experiments are performed and AI-based image analysis is technically reviewed.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.3
• /
• pp.57-67
• /
• 2015

Land characteristics should be surveyed in an accurate and objective manner as they are important data to the formation of land prices. The ambiguous survey and estimation guidelines, however, make it possible for surveyors to intervene with their subjective judgments. There is thus a definite need for improvement. It is also extremely important to survey the characteristics of individual land lots in an accurate and objective manner in order to estimate officially assessed land prices in a swift and accurate way. For objective land appraisal and evaluation, this study set out to objectively identify the characteristics of lots according to various topographical conditions by using UAV based high quality geospatial information, panorama VR images, and GIS analysis technique and thus make a contribution to a rational and consistent estimation system of officially assessed land prices. Trying to assess the technique proposed in the study, the investigator analyzed the old data about the officially assessed land prices of the subject areas and then the evaluation data of certified public appraisers.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.57 no.3
• /
• pp.87-92
• /
• 2015

Cultivation on reclaimed tidal land is often difficult in the problem such as high salinity of soil, bad drainage because of high level of groundwater. Many researches have been made efforts to solve these problems, but effect of improvement is low and practicality is insufficient. In this study, through numerical analysis of the transport properties of salt and water, we suggested underground drainage of the reclaimed land and the desalination promotion methods in the soil. The results of characteristic of desalination and seepage analysis of underdrain show that underdrain is able to increase twice of the underground seepage amount when installing perforated pipe with horizontal filter (width 50cm) more than installing only the perforated pipe. For soil which coefficient of permeability is below $1{\times}10^{-4}cm/s$ that desalination with pond water is not possible, a method to increase the permeability of the soil is necessary. Therefore, it was concluded that application of underdrain using perforated pipe with horizontal filter would be low-cost and practical.

• Korean Journal of Soil Science and Fertilizer
• /
• v.46 no.6
• /
• pp.426-433
• /
• 2013

This study was aimed to classify soil desalination area for cultivation using NDVI (Normalized difference vegetation index) of high-resolution satellite image because the soil salinity affects the change of plant community in reclaimed lands. We measured the soil salinity and NDVI at 28 sites in the Saemangeum reclaimed land in June 2013. In halophyte and non-vegetation sites, no relation was found between NDVI and soil salinity. In glycophyte sites, however, we found that the soil salinity was below 0.1% and NDVI ranged from 0.11 to 0.57 which was greater than the other sites. So, we could distinguish the glycophyte sites from the halophyte sites and non-vegetation, and classify the area that soil salinty was below 0.1%. This technique could save the time and labor to measure the soil salinity in large area for agricultural utilization.

• Journal of the Korean Institute of Rural Architecture
• /
• v.14 no.4
• /
• pp.89-96
• /
• 2012

The purpose of the study is to identify land use characteristics which have influence on residents' mental health. Land use and housing types indicators including green areas and parks were selected by analyzing the related environment and health researches. Research database for every variable from 33 neighborhoods in Jeonju city were established through National Health Insurance Corporation, where is available for getting mental and behavioral disabilities (F code) expenses. The relation between those indexes and mental health were analysed. The findings of this study are as follows : First, the higher price area like apartments and raw houses the residents lived in, the more expenditure of F-code was paid. It could be interpreted by the relatively high frequency of medical treatment and interests on the health. Second, the more green area except park were there, the more F-code expenditure was given, which could be explicated with the spatial co-relation between location of green area and apartments of Jeonju city. It was very high, and apartment element's affect on the F-code was much more than the green zone. Third, the nearer to park were the residents, the less F-code expenses was paid.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2000.05a
• /
• pp.28-32
• /
• 2000

There are many different chemical pollutants that originate from atmospheric deposition and transportational activities along roads. This paper review the characteristics of heavy metal pollution, relationships between land use and pollutant load in urban area. Four land use areas in Seoul were selected for sampling and study with different characteristics during the period from April 1998 and February 2000. A series of studies have been carried out concerning the physicochemical characteristics of the sediments settling down in a gully pot to evaluate the contamination for heavy metals. The sediment samples from gully pots were characterized by the chemical extraction experiments. Sediments are characterized by very high concentrations of heavy metals, probably because of a long-term accumulation of vehicle- and industrial-related pollutants. The characteristics of heavy metal pollution show that each land use has different sources of contaminations. Mean Zn concentration in Yeouido and Junggu areas is 2-3 times higher than those in Dobonggu area. This suggests that Zn may be derived from the source of automobile traffic. The mean concentrations of Cu and Cr are very significantly high in Junggu and Gurogu areas and indicate that the industrial activities may contribute to the accumulation of Cu and Cr in sediments. The low Pb levels throughout the whole study areas in Seoul can be accounted for the use of unleaded gasoline since 1987.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1993.10a
• /
• pp.178-185
• /
• 1993

The standard of agricultural mechanization is one of the important indicators for measuring the realized degrees of agricultural modernization in some regions. The Pearl river delta is most fertile, and thereby reputed as a land of fish and rice in the province. Studying the proceedings, profits and experiences of agricultural mechanization in the region obviously possesses the generally guiding significance for Guangdong to realize agricultural modernization by the year 2010. this paper involves these fields such as duainage, irrigation, harrowing, harvesting, transportation, processing and etc, in the Pearl River Delta, Results show as follows: (1) 80% work load in main production links has been mechanized ; (2) changed took place in traditionally agricultural production means and ways so took place in traditional agricultural production means and ways so that individual farmer in this region became commercial producer and then march toward commodity production of moderniza ion with high yields, good guality and high profits ; (3) further taping production potential to improve land output and labour productivity. Results also show that the degrees of agricultural mechanization in the Pearl River Delta are closely related to government' spolices, finance, moderate land scale management, rural industrialization and machine utility as well as talent training, shortage of which will surely; affect the proceeding of agricultural mechanization. Therefore, government must be urged to guarantee it by preferential policies and financial loan so as to greatly run rural industry, to create conditions for land scale management, to set up the socialized service system of agricultural mechanization, to actively train scientific talents and to introduce advanced equipments and technology from aborad in order to quicken the progress of agricultural mechanization in this regions.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.33 no.4 s.111
• /
• pp.1-10
• /
• 2005

Recently, as urban landscape is growing in importance, urban landscape planning is being actively performed. for this purpose, classification of the urban landscape is definitely required. Therefore, this research focuses on classifying urban landscape in Daejeon metropolis by dividing the urban land use pattern. This results are as follows. 1. Urban land use pattern is divided into 20 classes. The residential, commercial and industrial areas, the old market and the bus terminal are evaluated negatively, whereas the areas of school, water reservoir, neighborhood park and train station are appreciated as being positive in landscape characters. 2. As a result of a cluster analysis, urban landscape has five different landscape types. These are: landscapes of medium diversity lacking green area, landscapes of high diversity lacking green area, landscapes rich in green area and with medium diversity, landscapes rich in green area and with high diversity, and landscapes rich in green area and with low diversity. 3. In landscape characters of beauty and harmony, landscapes rich in green area and with medium diversity are more positively evaluated than those rich in green area and with low diversity. This point should be taken into account for planning the urban landscape.