• Spatial Information Research
• /
• v.10 no.2
• /
• pp.233-246
• /
• 2002

The purpose of this paper is to quantitatively measure the effect of location in evaluating the land value through the implementation of GIS coupled with spatial statistical analysis. We assumed that the hedonic price model, which was commonly used in modelling the land value, could not explain the spatial factor effectively. In order to add the spatial factor, the analysis of the spatial autocorrelation was used. The present project used 54 standard land price samples from 1421 parcel land values and applied Kriging to predict stochastically the unsampled values on the basis of spatial autocorrelation between location of vector data. This study confirms that the spatial variogram analysis has an advantage of predicting spatial dependence process and revealing the positive premium and the negative penality on location factor objectively.

• Journal of Information Processing Systems
• /
• v.1 no.1 s.1
• /
• pp.102-106
• /
• 2005

As long as the effective contributions of satellite images in the continuous monitoring of the wide area and long range of time period, Landsat TM and Landsat ETM+ satellite images are surveyed. After quantization and classification of the deviations between TM and ETM+ images based on approved thresholds such as gains and biases or offsets, a correlation analysis method for the compared calibration is suggested in this paper. Four time points of raster data for 15 years of the highest group of land surface temperature and the lowest group of vegetation of the Kunsan city Chollabuk_do Korea located beneath the Yellow sea coast, are observed and analyzed their correlations for the change detection of urban land cover. This experiment based on proposed algorithm detected strong and proportional correlation relationship between the highest group of land surface temperature and the lowest group of vegetation index which exceeded R=(+)0.9478, so the proposed Correlation Analysis Model between the highest group of land surface temperature and the lowest group of vegetation index will be able to give proof an effective suitability to the land cover change detection and monitoring.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.4
• /
• pp.53-61
• /
• 2014

Landsat OLI satellite imagery can be applied to various remote sensing applications, such as generation of land cover map, urban area analysis, extraction of vegetation index and change detection, because it includes various multispectral bands. In addition, land cover map is an important information to monitor and analyze land cover using GIS. In this paper, land cover map is generated by using Landsat OLI and existing land cover map. First, training dataset is obtained using correlation between existing land cover map and unsupervised classification result by K-means, automatically. And then, spectral signatures corresponding to each class are determined based on training data. Finally, abundance map and land cover map are generated by using iterative spectral mixture model. The experiment is accomplished by Landsat OLI of Cheongju area. It shows that result by our method can produce land cover map without manual training dataset, compared to existing land cover map and result by supervised classification result by SVM, quantitatively and visually.

• Korean Journal of Environmental Agriculture
• /
• v.39 no.3
• /
• pp.204-213
• /
• 2020

BACKGROUND: Since the number of crops cultivated in reclaimed land is huge, it is very difficult to quantify the total crop production. Therefore, a non-destructive method for predicting crop production is needed. Salt tolerant root vegetables such as red beets and sugar beet are suitable for cultivation in reclaimed land. If their underground biomass can be predicted, it helps to estimate crop productivity. Objectives of this study are to investigate maximum leaf length and weight of red beet, sugar beet, and turnips grown in reclaimed land, and to determine optimal model with regression analysis for linear and allometric growth models. METHODS AND RESULTS: Maximum leaf length, width, and root fresh weight of red beets, sugar beets, and turnips were measured. Ten linear models and six allometric growth models were selected for estimation of root fresh weight and non-linear regression analysis was conducted. The allometric growth model, which have a variable multiplied by square of maximum leaf length and maximum leaf width, showed highest R² values of 0.67, 0.70, and 0.49 for red beets, sugar beets, and turnips, respectively. Validation results of the models for red beets and sugar beets showed the R² values of 0.63 and 0.65, respectively. However, the model for turnips showed the R² value of 0.48. The allometric growth model was suitable for estimating the root fresh weight of red beets and sugar beets, but the accuracy for turnips was relatively low. CONCLUSION: The regression models established in this study may be useful to estimate the total production of root vegetables cultivated in reclaimed land, and it will be used as a non-destructive method for prediction of crop information.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1911-1923
• /
• 2022

The availability of high-resolution satellite images provides precise information without direct observation of the research target. Korea Multi-Purpose Satellite (KOMPSAT), also known as the Arirang satellite, has been developed and utilized for earth observation. The machine learning model was continuously proven as a good classifier in classifying remotely sensed images. This study aimed to compare the performance of the support vector machine (SVM) model in classifying the land cover of the Delaware River port area on high and medium-resolution images. Three optical images, which are KOMPSAT-2, KOMPSAT-3A, and Sentinel-2B, were classified into six land cover classes, including water, road, vegetation, building, vacant, and shadow. The KOMPSAT images are provided by Korea Aerospace Research Institute (KARI), and the Sentinel-2B image was provided by the European Space Agency (ESA). The training samples were manually digitized for each land cover class and considered the reference image. The predicted images were compared to the actual data to obtain the accuracy assessment using a confusion matrix analysis. In addition, the time-consuming training and classifying were recorded to evaluate the model performance. The results showed that the KOMPSAT-3A image has the highest overall accuracy and followed by KOMPSAT-2 and Sentinel-2B results. On the contrary, the model took a long time to classify the higher-resolution image compared to the lower resolution. For that reason, we can conclude that the SVM model performed better in the higher resolution image with the consequence of the longer time-consuming training and classifying data. Thus, this finding might provide consideration for related researchers when selecting satellite imagery for effective and accurate image classification.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.65 no.6
• /
• pp.15-22
• /
• 2023

In this study, We conduct a comparative study of deep learning-based classification of agricultural field attributes using Tagged Image File (TIF) and Enhanced Compression Wavelet (ECW) images. The goal is to interpret and classify the attributes of agricultural fields by analyzing the differences between these two image formats. "FarmMap," initiated by the Ministry of Agriculture, Food and Rural Affairs in 2014, serves as the first digital map of agricultural land in South Korea. It comprises attributes such as paddy, field, orchard, agricultural facility and ginseng cultivation areas. For the purpose of comparing deep learning-based agricultural attribute classification, we consider the location and class information of objects, as well as the attribute information of FarmMap. We utilize the ResNet-50 instance segmentation model, which is suitable for this task, to conduct simulated experiments. The comparison of agricultural attribute classification between the two images is measured in terms of accuracy. The experimental results indicate that the accuracy of TIF images is 90.44%, while that of ECW images is 91.72%. The ECW image model demonstrates approximately 1.28% higher accuracy. However, statistical validation, specifically Wilcoxon rank-sum tests, did not reveal a significant difference in accuracy between the two images.

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.3
• /
• pp.19-27
• /
• 2012

Wind is an important variable for various scientific communities such as meteorology, climatology, and renewable energy. In this study, numerical simulations using WRF mesoscale model were performed to produce temporal and spatial wind information over the Republic of Korea during 2006. Although the spatial features and monthly variations of the near-surface wind speed were well simulated in the model, the simulated results overestimated the observed values as a whole. To correct these simulated wind speeds, a regression-based statistical algorithm with different constants and coefficients by land cover type was developed using the satellite-derived LST and NDWI. The corrected wind speeds for the algorithm validation showed strong correlation and close agreement with the observed values for each land cover type, with nearly zero mean bias and less than 0.4 m/s RMSE. Therefore, the proposed algorithm using remotely sensed surface observations may be useful for correcting simulated near-surface wind speeds and producing more accurate wind information over the Republic of Korea.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.9
• /
• pp.1833-1839
• /
• 2011

In this study, Global Gravitational Model EGM2008, EGM96 and 16,786 gravity points measured on land were compared and analyzed. On the assumption that land gravity data is most accurate, the correlation coefficient, differences, MSE and difference variance along the height were computed between land gravity data and EGM2008, EG96. The correlation coefficient, land gravity data and EGM2008, was computed most largely with 0.824 and the correlation coefficient with EGM96 was computed with 0.538. The standard deviation of differences between land gravity and EGM2008, EGM96 were 13.196 magl, 18.685 mgal respectively. Also the difference variance scope of EGM2008 was smaller than EGM96. There was no large variance of free-air anomaly differences between land gravity data and EGM2008 along the height however free-air anomaly differences with EGM96 varied along the height changes. Consequently EGM2008 nicely expresses Korea gravity field more than EGM96.

• Journal of Korean Society for Geospatial Information Science
• /
• v.18 no.1
• /
• pp.129-134
• /
• 2010

Low-carbon Green Growth is highlighted as the main political issue from in and outof Korea. Recently Korean government announced the vision for low-carbon green growth. Considering this as a starting point the carbon emission estimation has become an important factor in the city planning. In order to realize the carbon reduction planning, this research was focused on the trend analyzes between the carbon exhaust estimation as well as the land use change for the past 40 years in Jinju. The image processing data of past aerial photography and the land suitability assessment databases were used to collect the useful information's for the land trend analysis for 40 years. As the results, the land use changes by new residential developments have led to increase the carbon emissions and population concentration rapidly. The urban management planning for low carbon and green growth should consider carbon emissions by population growth derived from land use change. Further research need to estimate the accurate carbon exhaust using relationship model with fuel consumption, carbon estimation, and land use.

• Journal of Korean Society of Rural Planning
• /
• v.26 no.3
• /
• pp.103-113
• /
• 2020

Land price can be affected by convenience or psychological repulsion like PIMFY (Please In My Front Yard) or NIMBY (Not In My Back Yard) for various facilities. The purpose of this study is to evaluate whether non-preferred facilities are related to NIMBY impact that negatively affect land prices using the spatial econometrics models which are spatial autoregressive models (SAR), spatial errors models (SEM), and general spatial model (SAC). The land price in urban area increases by 0.07-0.2% when the distance from aversion facilities increases by 1%. However, the land price in rural areas decreases when the distance from aversion or pollution facilities increase. Therefore, these facilities in rural areas located in the areas with higher land price because funeral homes located in center of rural administrative areas and charnel house or crematorium located in the fringe of urban areas. That is, this study explain the difference between land price and non-preferred facilities in urban and rural areas and why there are more N IMBY symptoms in urban areas.