• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1413-1425
• /
• 2023

The increasing frequency of wildfires due to climate change is causing extreme loss of life and property. They cause loss of vegetation and affect ecosystem changes depending on their intensity and occurrence. Ecosystem changes, in turn, affect wildfire occurrence, causing secondary damage. Thus, accurate estimation of the areas affected by wildfires is fundamental. Satellite remote sensing is used for forest fire detection because it can rapidly acquire topographic and meteorological information about the affected area after forest fires. In addition, deep learning algorithms such as convolutional neural networks (CNN) and transformer models show high performance for more accurate monitoring of fire-burnt regions. To date, the application of deep learning models has been limited, and there is a scarcity of reports providing quantitative performance evaluations for practical field utilization. Hence, this study emphasizes a comparative analysis, exploring performance enhancements achieved through both model selection and data design. This study examined deep learning models for detecting wildfire-damaged areas using Landsat 8 satellite images in California. Also, we conducted a comprehensive comparison and analysis of the detection performance of multiple models, such as U-Net and High-Resolution Network-Object Contextual Representation (HRNet-OCR). Wildfire-related spectral indices such as normalized difference vegetation index (NDVI) and normalized burn ratio (NBR) were used as input channels for the deep learning models to reflect the degree of vegetation cover and surface moisture content. As a result, the mean intersection over union (mIoU) was 0.831 for U-Net and 0.848 for HRNet-OCR, showing high segmentation performance. The inclusion of spectral indices alongside the base wavelength bands resulted in increased metric values for all combinations, affirming that the augmentation of input data with spectral indices contributes to the refinement of pixels. This study can be applied to other satellite images to build a recovery strategy for fire-burnt areas.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.979-995
• /
• 2023

As wildfires are difficult to predict, real-time monitoring is crucial for a timely response. Geostationary satellite images are very useful for active fire detection because they can monitor a vast area with high temporal resolution (e.g., 2 min). Existing satellite-based active fire detection algorithms detect thermal outliers using threshold values based on the statistical analysis of brightness temperature. However, the difficulty in establishing suitable thresholds for such threshold-based methods hinders their ability to detect fires with low intensity and achieve generalized performance. In light of these challenges, machine learning has emerged as a potential-solution. Until now, relatively simple techniques such as random forest, Vanilla convolutional neural network (CNN), and U-net have been applied for active fire detection. Therefore, this study proposed an active fire detection algorithm using state-of-the-art (SOTA) deep learning techniques using data from the Advanced Himawari Imager and evaluated it over East Asia and Australia. The SOTA model was developed by applying EfficientNet and lion optimizer, and the results were compared with the model using the Vanilla CNN structure. EfficientNet outperformed CNN with F1-scores of 0.88 and 0.83 in East Asia and Australia, respectively. The performance was better after using weighted loss, equal sampling, and image augmentation techniques to fix data imbalance issues compared to before the techniques were used, resulting in F1-scores of 0.92 in East Asia and 0.84 in Australia. It is anticipated that timely responses facilitated by the SOTA deep learning-based approach for active fire detection will effectively mitigate the damage caused by wildfires.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.42 no.5
• /
• pp.22-30
• /
• 2014

The purpose of this study was to compare the Solar Radiation(SR) and the Mean Radiant Temperature(MRT) under the shades of the three landscaping trees in clear summer daytimes. The trees were Lagerstroemia indica, Quercus palustris and Ulmus parvifolia. The solar radiation, the globe temperature and the air temperature were recorded every minute from the $1^{st}$ of April to the $30^{th}$ of September 2013 at a height of 1.1m above on the four monitoring stations, with four same measuring system consisting of a solar radiation sensor, two resistance temperature detectors(Pt-100), a black brass globe (${\phi}50mm$) and data acquisition systems. At the same time, the sky view photos were taken automatically hourly by three scouting cameras(lens angle: $60^{\circ}$) fixed at each monitoring station. Based on the 258 daily sky view photos and 6,640 records of middays(10 A.M.~2 P.M.) from the $1^{st}$ of June to the $30^{th}$ of August, the time serial differences of SR and MRT under the trees were analysed and compared with those of open sky, The major findings were as follows; 1. The average ratio of sky views screened by the canopies of Quercus palustris, Lagerstroemia indica and Ulmus parvifolia were 99%, 98% and 97%, and the SR were $106W/m^2$, $163W/m^2$ and $202W/m^2$ respectively, while the SR of open sky was $823W/m^2$. Which shows the canopies blocked at least 70% of natural SR. 2. The average MRT under the canopies of Quercus palustris, Lagerstroemia indica and Ulmus parvifolia were $30.34^{\circ}C$, $33.34^{\circ}C$ and $34.77^{\circ}C$ respectively, while that of open sky was $46.0^{\circ}C$. Therefore, it can be said that the tree canopies can reduce the MRT around $10{\sim}16^{\circ}C$. 3. The regression test showed significant linear relationship between the SR and MRT. In summary, the performances of the landscaping shade trees were very good at screening the SR and reducing the MRT at the outdoor of summer middays. Therefore, it can be apparently said that the more shade trees or forest at the outdoor, the more effective in conditioning the outdoor space reducing the MRT and the useless SR for human activities in summertime.

• Journal of Wetlands Research
• /
• v.17 no.3
• /
• pp.264-272
• /
• 2015

Understanding bird status is essential for the systematic and sustainable management of the Nakdong River Estuary, taking into consideration the relationship between ecosystems and the bird species. In this study, bird status in the Nakdong River Estuary Bird Sanctuary prior to the Four Major Rivers Project was analyzed using the bird monitoring data (2003-2011) from surveys conducted by the Busan Development Institute. The high percentage of winter visitors in terms of both species diversity (38.36%) and individual bird numbers (63.14%) suggest that the Nakdong River Estuary is an important wintering site for migratory birds. Cumulative numbers of individual birds were higher in Myungji (208,601), West Nakdong River (202,444), Eulsukdo (153,232), and Baekhap Doyodeung (150,595). The total numbers of migratory species were higher in Eulsukdo (171), Ilungdo (124), Myungji (132), and Samrak (121). Among the 232 species found in the Nakdong River Estuary, Anas platyrhynchos (17.71%) was the most common species, followed by Anas poecilorhyncha (8.85%), Larus crassirostris (6.48%), Anser fabalis (6.09%), Anas penelope (5.16%), and Calidris alpina (4.22%). Most bird taxa, except shelducks, showed annual fluctuations in individual numbers, with increasing frequency during survey periods. Of these, cormorants, swans, and gulls showed higher fluctuations than other taxa. Swans decreased drastically in numbers in 2007-2008 and 2009-2010 compared to previous years. Shore birds, gulls, wagtails, and other forest birds were also less common in 2010-2011. These results suggest that there were some environmental changes that might have affected the birds in the Nakdong River Estuary. Overall, the results suggest that habitat types affect the distribution of dominant species.

• Korean Journal of Soil Science and Fertilizer
• /
• v.31 no.2
• /
• pp.170-176
• /
• 1998

Nitrogen and phosphorus loads from an agricultural watershed of the Yulmun-chon tributary in the Buk-Han River Basin were quantified based on total amounts of water stream flow. The water quality and soil loss were estimated. Levels of the stream were recorded automatically using the water level meter. The flow velocities, along with the cross-sectional areas of the riverbed, were measured to estimate total amounts of water flow at three monitoring sites in this tributary. Water samples were collected at nine sites with two weeks interval from May to August and analyzed for the water quality parameters. Amounts of soil loss were estimated by the USLE. The size of the Yulmunchon watershed was 3,210 ha, of which paddy and upland soil areas were composed about 41%. The total amounts of soil loss from the watershed areas were estimated to be $13,273Mg\;year^{-1}$, showing 53%, 46% and 0.7% of the soil loss ratio from upland, forest, and paddy areas, respectively. Electrical conductivities and Nitrogen concentrations of the stream water were higher in the lower watershed area than in the upper area. Increments of N were higher for $NO_3-N$ than $NH_4-N$. Nitrate nitrogen was the major N form to pollute the water due to the agricultural activity. Total runoff was about 72% of the total precipitation in the watershed. The maximum loads of T-N and T-P due to the runoff were estimated to be 1,500 and $5kg\;day^{-1}$, respectively. Concentrations of $NO_3-N$ and $NH_4-N$ in the runoff were 13.5 and 1.8 times higher than those in precipitation. The N loads were mainly from soil loss, application of fertilizer, and livestock wastes, which were 52% of total N load. Results demonstrated that reduction of fertilizer use and the soil loss would be essential for water quality protection of the agricultural watershed.

• Korean Journal of Environment and Ecology
• /
• v.34 no.1
• /
• pp.9-17
• /
• 2020

Domestic cats (Felis catus) introduced to insular environments can be invasive predators that often threaten endemic species and cause biodiversity loss or local extinction on the island. This study was conducted from March to July 2018 to understand the population size, home range, and spatial use of cats introduced to Mara Islet (N 33° 07', E 126° 16') in Jeju Special Governing Province, the Republic of Korea. Observation records based on their natural marks revealed that there were 20 adult cats on Mara Islet. A capture-recapture method also estimated 20 adult individuals (95% confidence interval: 20-24 individuals). According to our telemetry study on ten adults deployed with GPS-based telemetry units, the home range size was 12.05±6.99 ha (95% KDE: kernel density estimation), and the core habitat size was 1.60±0.77 ha (50% KDE). There were no significant differences in the home range and core habitat sizes by sex. The home range of domestic cats overlapped with the human residential area, where they might secure easy foods. Five of ten tracked cats were active at potential breeding colonies for the Crested Murrlet (Synthliboramphus wumizusume), and six approached potential breeding areas of the Styan's Grasshopper Warbler (Locustella pleskei), suggesting the predation risk of the two endangered species by cats. This study provides novel information on the population size and home range of introduced cats on Mara Islet which is an important stopover site of migratory birds as well as a breeding habitat of the two endangered avian species. Reducing the potential negative impacts of the introduced cats on migratory birds and the endangered species on Mara Islet requires monitoring of the predation rate of birds by cats, the population trends of cats and endangered breeding birds as well as the effective cat population control and management.

• Journal of Environmental Impact Assessment
• /
• v.26 no.5
• /
• pp.365-375
• /
• 2017

This study investigated in the vascular plants of special protection zones (the native land of Iris koreana in Gaeamsa Temple and Soeppulbawi Rock) of Byeonsanbando National Park and identified the whole flora. The numbers of vascular plants were summarized as 255 taxa including 71 families, 166 genera, 222 species, 2 subspecies, 27 varieties and 4 forms. Woody plants were identified as 114 taxa (44.7%) and herbaceous plants as 141 taxa (55.3%). A total of 178 taxa were identified in the area of Gaeamsa Temple, and 184 taxa were found in the Soeppulbawi Rock. As a legal protected species, the endangered wild plant II grade Iris koreana designated by the Ministry of Environment was confirmed. A total of 6 taxa of rare plants were identified, each of which was divided into 1 taxa of critically endangered (CR; Iris koreana), 1 taxa of vulnerable (VU; Ilex cornuta), and 4 taxa of least concern (LC; Asarum maculatum, Viola albida, Chionanthus retusa and Tricyrtis macropoda). The Korean endemic plants were 11 taxa (Populus tomentiglandulosa, Lonicera subsessilis, Carex okamotoi, etc.). In the specific plants by floristic region were 38 taxa, a degree I were 23 taxa (Euscaphis japonica, Hedera rhombea, Lophatherum gracile, etc.), 7 taxa of a degree II (Viola violacea, Ainsliaea apiculata, Cephalanthera falcata, etc.), 6 taxa of a degree III (Ilex cornuta, Callicarpa mollis, Mitchella undulata, etc.), 1 taxa of a degree IV (Carex remotiuscula), 1 taxa of a degree V (Iris koreana). The Iris koreana special protection area that is more natural and healthier than any other areas in Byeonsanbando National Park. Therefore, it should be possible to continue its role as a special protection area through regular monitoring in the future.

• Korean Journal of Soil Science and Fertilizer
• /
• v.37 no.4
• /
• pp.199-206
• /
• 2004

Factors of universal soil loss equation, USLE, and its revised version, RUSLE for Korean soils were reevaluated to estimate the national scale of soil loss based on digital soil maps. Rainfall erosivity factor, R, of 158 locations of cities and counties were spacially interpolated by the inverse distance weight method. Soil erodibility factor, K, of 1321 soil phases of 390 soil series were calculated using the data of soil survey and agri-environmental quality monitoring. Topographic factor, LS, was estimated using soil map of 1:25,000 scale with soil phase and land use type. Cover management factor, C, of major crops and support practice factor, P, were summarized by analyzing the data of lysimeter and field experiments for 27 years (1975-2001) in the National Institute of Agricultural Science and Technology. R factor varied between 2322 and 6408 MJ mm $ha^{-1}$ $yr^{-1}$ $hr^{-1}$ and the average value was 4276 MJ mm $ha^{-1}$ $yr^{-1}$ $hr^{-1}$. The average K value was evaluated as 0.027 MT hr $MJ^{-1}$ $mm^{-1}$. The highest K factor was found in paddy rice fields, 0.034 MT hr $MJ^{-1}$ $mm^{-1}$, and K factors in upland fields, grassland, and forest were 0.026, 0.019, and 0.020 MT hr $MJ^{-1}$ $mm^{-1}$, respectively. C factors of upland crops ranged from 0.06 to 0.45 and that of grassland was 0.003. P factor varied between 0.01 and 0.85.

• Korean Journal of Ecology and Environment
• /
• v.50 no.4
• /
• pp.381-402
• /
• 2017

In order to investigate distribution of vascular plants along elevational gradient in the Nodong valley of Gyebangsan, vascular plants of eight sections with 100-meter-high were surveyed from the Auto-camping site (800 m) to the top of a mountain (1,577 m). There were a total of 382 taxa: 89 families, 234 genera, 339 species, 7 subspecies, 34 varieties, and 2 forms. As a result of analyzing the pattern of species richness, it showed a reversed hump-shaped with minimum richness at mid-high elevation. As a result of analyzing habitat affinity types, the proportion of forest species increased with increasing elevation. But, the ruderal species decreased with increasing elevation, and then increased at the top of a mountain. As for the proportion of life forms, the annual herbs gradually decreased with increasing elevation, but it did not appear between 1,300 m and 1,500 m and then increased at the top of a mountain. The trees gradually increased with elevation and decreased from 1,300~1,400 m. The vascular plants divided into four groups by using DCA. The arrangement of each stands was arranged in order from right to left on the I axis according to the elevation. The distribution of vascular plants is determined by their own optimal ranges of vegetation. Also, rise in temperature due to climate change affects the distribution of vascular plants, composition, and diversity. Therefore, continuous monitoring is necessary to confirm ecological and environmental characteristics of vegetation, distribution ranges, changes of habitat. Furthermore, plans for conservation and management based on these data should be prepared according to climate change.

• Korean Journal of Ecology and Environment
• /
• v.47 no.3
• /
• pp.176-185
• /
• 2014

There are no population ecological research on the natural monument (No. 191) Jeju Cymbidium kanran in South Korea. In this study, we analyzed the population structure and fine-scale habitat affinity of C. kanran in Sanghyo-dong, Jejudo Island from Oct. 2013 to Feb. 2014. We observed total of 1,237 individuals (4,341 pseudobulbs) of C. kanran (989.6 population $ha^{-1}$) within (1.25 ha) and only 17 (1.4%) individuals were inflorescent. In 60.9% of the entire populations, disease symptoms such as spots and blight leaves were observed. C. kanran populaton exhibited reverse-J shaped size distribution based on leaf area classes as individual size parameter. The three size related attributes of C. kanran (no. of pseudobulb $r_s$=-0.159, no. of leaves $r_s$=-0.148 and leaf arera $r_s$=-0.114) and soil temperature revealed a negative relationship (p<0.0001). Most of C. kanran (95.4%) were grown under Castamopsis cuspidata and spatially, C. kanran were strongly clumped at all distances. Population characteristics of C. kanran in the study area were likely originated from species habitat affinity and successional environment. Through this study, base line data for C. kanran's habitat monitoring was established and conservation measures based on population characteristics were discussed.