• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.5
• /
• pp.535-546
• /
• 2020

Land cover maps are derived from satellite and aerial images by the Ministry of Environment for the entire Korea since 1998. Even with their wide application in many sectors, their usage in research community is limited. The main reason for this is the map compilation cycle varies too much over the different regions. The situation requires us a new and quicker methodology for generating land cover maps. This study was conducted to automatically generate land cover map using aerial ortho-images and Landsat 8 satellite images. The input aerial and Landsat 8 image data were trained by Residual U-Net, one of the deep learning-based segmentation techniques. Study was carried out by dividing three groups. First and second group include part of level-II (medium) categories and third uses group level-III (large) classification category defined in land cover map. In the first group, the results using all 7 classes showed 86.6 % of classification accuracy The other two groups, which include level-II class, showed 71 % of classification accuracy. Based on the results of the study, the deep learning-based research for generating automatic level-III classification was presented.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2005.11a
• /
• pp.93-98
• /
• 2005

u-city의 구축에는 정보통신관련 전문가가 주도적으로 참여하고 있으며, u-city는 정보통신 인프라 설치, 도시정보관제센터 건립 및 시스템 구축 운영, 디지털 컨텐츠서비스 제공으로 구성된다. 디지털 컨텐츠의 주요구성요소는 서비스생활환경컨텐츠, 도시관리컨텐츠, 상거래컨텐츠로서 공공포탈서비스를 통해 지역 사회에 제공된다. 본고는 디지털 컨텐츠에 추가될 수 있는 컨텐츠로서 건설교통부와 한국토지공사에서 추진하고 있는 국토정보화사업의 개요와 장점을 소개하고 u-city와 연계하며, 향후 u-city의 구축에서 도시계획가 참여의 필요성을 제시한다.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.7 no.2
• /
• pp.935-943
• /
• 1965

1. Nation wide soil surver is going of from Oct't by Unkup. According to the sever years program of national high hueld of food production campaign. 2. About eighry of new soil surveryors wee assigned to provincial office of Unkup. 3. Land capability classifieation comes from U.S.D.A method. Bur we fells most adequate land classification should be studied and set uo of the real Korean Natural situation. 4. This theory has been studied by the Unkup soil survey staffs.

• Proceedings of The Korean Society of Agricultural and Forest Meteorology Conference
• /
• 2003.09a
• /
• pp.58-61
• /
• 2003

A land surface parameterization has been used to simulate influences of the terrestrial surface on the atmosphere. A simple biosphere model (SiB2), one of land surface parameterization, calculates exchange of radiation, sensible heat, latent heat, and momentum between the surface and the atmosphere (Sellers, et al., 1996).(omitted)

• 한국디지털정책학회:학술대회논문집
• /
• 2004.05a
• /
• pp.289-311
• /
• 2004

The purpose of this study is to analyze the optimal development direction of the land management information systems in Korea. In order to produce a new LMIS model the existing model of Tulloch(1996) was evaluated. Analysis of the land management information systems(LMIS) is focused on the period of 1998 and 2001. The main results of the study are as follows: First, the government should involve GIS(Geographic Information Systems) into the e-government. Second, the KLIS(Korea Land Information Systems) is required technological and legal infrastructure for the service using optimized land management information systems as combining LMIS and PBLIS(Parcel based Land Information Systems). Third, the spatial data of the LMIS can be promoted by ensuring reliable IT environments. Forth, optimized LMIS should be revised to reflect the new technological environment and collaborative relationship between LIS and GIS boundaries and between LMIS, urban infrastructure, and related information sectors. Fifth, In terms of services LMIS is required focusing end users rather than supplier focused strategy.

• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• pp.3-8
• /
• 1998

Using GIS and socio-economical data the relationship between human activities and global environmental change Is Analysed from the view point of food productivity and CO2 emission. Under the assumption that the population problem, the food problem and global warming due to energy consumption can be stabilized through managing land use, impacts of human activities such as consumption of food, energy and timber on global environment changes, and global population capacity are Analysed using developed system dynamics model in the research. In the model the world is divided into two groups: OECD countries and the others. Used global land use data set Is land cover map derived from satellite data, and potential distribution of arable land is estimated by the method of Clamor and Solomon which takes into consideration spatial distribution of climate data such as precipitation and evapotranspiration. In addition, impacts of CO2 emission from human activities on food production through global warming are included in the model as a feedback. The results of the analysis for BaU scenario and Toronto Conference scenario are similar to the results of existing models. From the result of this study, the human habitability in 2020 is 8 billion people, and CO2 emission in 2020 based on BaU Scenario and on Toronto Scenario is 1.7 and 1.2 times more than the 1986's respectively. Improving spatial resolution of the model by using global data to distribute the environmental variables and sauce-economical indices is left for further studies.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1771-1777
• /
• 2023

With the advancements of deep learning, many semantic segmentation-based methods for land cover classification have been proposed. However, existing deep learning-based models only use image information and cannot guarantee spatiotemporal consistency. In this study, we propose a land cover classification model using geographical coordinates. First, the coordinate features are extracted through the Coordinate Hash Encoder, which is an extension of the Multi-resolution Hash Encoder, an implicit neural representation technique, to the longitude-latitude coordinate system. Next, we propose an architecture that combines the extracted coordinate features with different levels of U-net decoder. Experimental results show that the proposed method improves the mean intersection over union by about 32% and improves the spatiotemporal consistency.

• Journal of Korean Society for Atmospheric Environment
• /
• v.26 no.2
• /
• pp.137-150
• /
• 2010

A meso-urban meteorological model (Urbanized MM5; uMM5) with urban canopy parameterization (UCP) was applied to the high-resolution simulation of meteorological fields in a complex coastal urban area and the assessment of urban impacts. Multi-scale simulations with the uMM5 in the innermost domain (1-km resolution) covering the Busan metropolitan region were performed during a typical sea breeze episode (4~8 August 2006) with detailed fine-resolution inputs (urban morphology, land-use/land-cover sub-grid distribution, and high-quality digital elevation model data sets). An additional simulation using the standard MM5 was also conducted to identify the effects of urban surface properties under urban meteorological conditions. Results showed that the uMM5 reproduced well the urban thermal and dynamic environment and captured well the observed feature of sea breeze. When comparison with simulations of the standard MM5, it was found that the uMM5 better reproduced urban impacts on temperature (especially at nighttime) and urban wind flows: roughness-induced deceleration and UHI (Urban Heat Island)-induced convergence.

• Journal of Korea Spatial Information System Society
• /
• v.11 no.1
• /
• pp.169-176
• /
• 2009

Korean Land Spatialization Program(KLSP) is the R&D program of the National GIS Project for developing ubiquitous GIS core technologies under control of Ministry of Land, Transport and Maritime Affairs(MLTM). The first program of KLSP, from 2006 to 2012, initiated with $132 million (US dollars) of national fund and $42 million of matching fund. KLPS which aims 'Innovation of the GIS technology for the ubiquitous Korean land' consists of 5 core research projects and 1 research coordination project to practically utilize and commercialize the results of core research. Korean Land Spatialization Group(KLSG) is planning the KLSP proving ground for testing, integrating, exhibiting the KLSP's outcomes. In the near future, this proving ground would be utilized as a national ubiquitous GIS proving ground. The key objective of this paper is to present the conceptual designs and basic plans. In addition, this paper discusses characteristics of the outcomes which are applied to KLSP proving ground.

• 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.