• Journal of the Korean Association of Geographic Information Studies
• /
• v.27 no.1
• /
• pp.115-127
• /
• 2024

This research aimed to construct models with various structures based on the Transformer module and to perform land cover classification, thereby examining the applicability of the Transformer module. For the classification of land cover, the Unet model, which has a CNN structure, was selected as the base model, and a total of four deep learning models were constructed by combining both the encoder and decoder parts with the Transformer module. During the training process of the deep learning models, the training was repeated 10 times under the same conditions to evaluate the generalization performance. The evaluation of the classification accuracy of the deep learning models showed that the Model D, which utilized the Transformer module in both the encoder and decoder structures, achieved the highest overall accuracy with an average of approximately 89.4% and a Kappa coefficient average of about 73.2%. In terms of training time, models based on CNN were the most efficient. however, the use of Transformer-based models resulted in an average improvement of 0.5% in classification accuracy based on the Kappa coefficient. It is considered necessary to refine the model by considering various variables such as adjusting hyperparameters and image patch sizes during the integration process with CNN models. A common issue identified in all models during the land cover classification process was the difficulty in detecting small-scale objects. To improve this misclassification phenomenon, it is deemed necessary to explore the use of high-resolution input data and integrate multidimensional data that includes terrain and texture information.

• Korean Journal of Environment and Ecology
• /
• v.29 no.5
• /
• pp.785-790
• /
• 2015

As an alternative to large-scale clear cutting silviculture, strip clear cutting (SC) is being considered as a system compatible with ecological conservation and forest regeneration. In South Korea, application and effectiveness of SCC in varying forest types were rarely found. In this study, under the subject of strip clear cutting lands of pinus densiflora forest at Samcheok, Gangwon-do Province, the developmental aspect of low vegetation prior to and after deforestation and the correlation between environmental factor and pine regeneration were analyzed. The cover rate of understory vegetation was appeared to be increased after deforestation and rapidly increased two years after deforestation, and it was evaluated to be affected by vigorous tree species and photophilic species. From the perspective of relative importance value, Quercus mongolica, Artemisia keiskeana, and Rubus crataegifolius that influence the cover rate showed the inclination of continuous growth. The diversity of species showed increment inclination as well due to introduction and settlement of early transient species. As a result of analyzing the correlation between vegetation and environmental factor and generation of pine tree size, the soil exposure rate, intensity of light, and canopy openness showed positive relationship, and the understory vegetation cover and woody debris cover rate showed negative relationship.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.31 no.3
• /
• pp.83-90
• /
• 2003

This study explored effects of urban greenspace on improving atmospheric environment, which is concerned with $CO_2$, SO$_2$ and NO$_2$ uptake, and with reduction of summer air temperatures. The site of this study was focused on Jung-gu in Seoul. Tree density and cover were 1.1 trees/100 $m^2$ and 12.5% respectively for the study area except forest lands. Atmospheric purification by greenspace was associated with changes in tree cover per unit area of each land use type. The mean $CO_2$ storage by woody plants was 19.4t/ha, and annual uptake averaged 2.2t/ha/yr for $CO_2$, 1.9kg/ha/yr for SO$_2$ and 5.0kg/ha/yr for NO$_2$. Entire tree plantings in the study area played a significant role by annually offsetting $CO_2$ emissions of about 1,830t from fossil fuel consumption by 330 persons, SO$_2$ emissions of 1,620kg by 1,080 persons, and NO$_2$ emissions of 4,230kg by 450 persons. The summer air temperature was 3.6$^{\circ}C$ cooler at a location with 54% cover of woody plants and 4.5$^{\circ}C$ cooler at a forest site with 100% cover, compared to a place with no planting. A 10% increase of woody plant cover was estimated to decrease summer air temperature by approximately 0.6$^{\circ}C$ until a certain level of canopy cover. Analyzing data from the Automatic Weather Stations in Seoul revealed that increasing tree cover decreased mean air temperature for the summer season (Jun~Aug) in a nonlinear function. Woody plant cover was the best predictive variable of summer temperature reduction. The results from this study are expected to be useful in emphasizing the environmental benefits and importance of urban greenspace enlargement, and in urging the necessity for planting and management budgets.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2002.10a
• /
• pp.293-296
• /
• 2002

The purpose of this study is to evaluate the hydrological impact due to temporal land cover change urbanization of Anseong-cheon watershed $(585.09km^2)$. WMS (Watershed Modeling System) HEC-1 was adopted, and burned DEM with $200{\times}200m$ resolution and soil map reclassified by hydrologic soil groups were prepared. Land cover for 1985, 1990, 1995 and 2000 were classified by maximum likelihood method, using Landsat MSS and TM imageries. Calibration and verification of HEC-1 were conducted using 4 storm events. Peak flow at Pyeong taek station increased $25.9m^3/sec$ during the past 15 years due to paddy and forest decrease. Streamflow impact by just paddy area decrease and forest area decrease were also analysed keeping watershed CN values unchanged of the given year, respectively.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.888-891
• /
• 2006

SAR image is not dependent on the weather condition and Sun's electromagnetic energy. But geometric distortions exist in almost all radar image, it need to be correction. The Radarsat-1 SAR images are used to monitoring of moisture acquired in May 1/1998 and May 25/1998. Radarsat-1 C band data is sensitive on moisture condition. Study area is located in Non-san site. It is made up almost agricultural area and a little of forest area. In May, Rice-planting is started in the midland of Korea. So moisture condition is undergoing many changes. Forest area need to be terrain effect removal for accurately results because it is included in layover, shadow, and so on. Results of land-cover moisture condition map are useful tool for fields of agriculture, forestry industry, and disaster.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.12 no.3
• /
• pp.1-8
• /
• 2009

The present study was conducted with the object of measuring sensibility image through an experiment with human bodies and indexing human feelings according to land cover types. The temperature by land cover types formed the lowest temperature in planted areas and the highest temperature in paved areas. The wind velocity is stronger in bare grounds, the surface of water and building areas than planted areas, grassland and paved areas. In the case of using a globe thermometer, a solar controled device confirmed the planted areas. In summer, an increase of thermal sensation are indicated a decrease of amenity, and the sensation which has high correlationship is in order by amenity, thermal sensation, airflow sensation and humidity sensation.

• Korean Journal of Remote Sensing
• /
• v.22 no.5
• /
• pp.433-437
• /
• 2006

SAR image is not dependent on the weather condition and Sun's electromagnetic energy. But geometric distortions exist in almost all radar image, it need to be correction. The Radarsat-1 SAR images are used to monitoring of moisture acquired in May 1/1998 and May 25/1998. Radarsat-1 C band data is sensitive on moisture condition. Study area is located in Non-san site. It is made up almost agricultural area and a little of forest area. In May, Rice-planting is started in the midland of Korea. So moisture condition is undergoing many changes. Forest area need to be terrain effect removal for accurately results because it is included in layover, shadow, and so on. Results of land-cover moisture condition map are useful tool for fields of agriculture, forestry industry, and disaster.

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.411-419
• /
• 2022

DPR Korea has been creating cropland across the country due to its chronic food shortage. Cropland was about 17.4% at the end of the 1980s, but it increased steadily to 19.6% at the end of the 1990s, 24.8% at the end of the first decade of 2000s, and 25.4% at the end of the 2010s. On the other hand, the forest land declined from about 74.8% in the late 1980s to 69.5% in the late 2010s. Urbanization is also progressing, increasing from about 1.15% at the end of the 1980s to 1.68% at the end of the 2010s. Most of the deforestation that occurred in DPR Korea was caused by conversion to cropland. These characteristics of land cover changes in DPR Korea provide useful information and implications for international and inter-Korean cooperation for DPR Korea.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.12 no.6
• /
• pp.123-130
• /
• 2009

Fragmentation due to land developments causes disturbances and changes of composition in forest vegetation. The purpose of the study was to develop the impact assessment model for quantitative distance or degree of disturbance by land developments. This study conducted a survey about structure and composition of forest vegetation to determine degree of impact from land developments. The results of field survey, there was a difference in structure and composition of forest vegetation such as tree canopy, herbaceous cover, and number of vine and alien species the distances from edge to interior area such as 0m, 10m, 20m, 40m, and over 60m. To assess the disturbance of forest vegetation, the factors selected were the rate of vine's cover and appearance of alien species. The impact assessment model about vine species explained by a distance, forest patch size, type of forest fragmentation, and type of vegetation ($R^2$=0.44, p<0.001). The other model about alien species explained by a distance, type of forest fragmentation, type of vegetation, and width of road (85.9%, p<0.005). The models applied to Samsong housing development in Goyang-si, Gyunggi-do. The vines and alien species in the study area have had a substantial impact on forest vegetation from edge to 20 or 40m. The impact assessment models were high reliability for estimating impacts to land developments. The impact of forest vegetation by development activities could be minimized thorough the adoption of the models introduced at the stage of EIA.

• Korean Journal of Agricultural Science
• /
• v.41 no.3
• /
• pp.205-211
• /
• 2014

Focused on Mt. Bogdkhan nature reserve in Mongolia, this study was conducted as a fundamental research to discover a tendency and characteristics of forest damage and to draw up measures for proper plans of forest restoration through an analysis of year-to year change using satellite images. In specific, land cover mapping was conducted by using Landsat images from 1994 to 2011, and then year-to year change was analyzed to investigate the features of forest damage in Mt. Bogdkhan. The results showed that the whole area of a reservation in Mongolia in 2011 was about $416.89km^2$; among them, forest area was $167,87km^2$, accounting for about 40.3%, followed by bare patch and grassland area (58.6%) and urban dry area (1.1%). In particular, compared in 1994, the area of forest in 2011 has increased by $6.12km^2$; while bare patch and grassland area has decreased by $10.81km^2$. Primary causes of forest degradation occurred in Mt. Bogdkhan nature reserve included illegal logging for fuel, forest and grassland degradation caused by domestic animals grazing, man-made forest fire, and disaster caused by insect pest.