• 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.1009-1029
• /
• 2023

Urban trees play a vital role in urban ecosystems,significantly reducing impervious surfaces and impacting carbon cycling within the city. Although previous research has demonstrated the efficacy of employing artificial intelligence in conjunction with airborne light detection and ranging (LiDAR) data to generate urban tree information, the availability and cost constraints associated with LiDAR data pose limitations. Consequently, this study employed freely accessible, high-resolution multispectral satellite imagery (i.e., Sentinel-2 data) to estimate fractional tree canopy cover (FTC) within the urban confines of Suwon, South Korea, employing machine learning techniques. This study leveraged a median composite image derived from a time series of Sentinel-2 images. In order to account for the diverse land cover found in urban areas, the model incorporated three types of input variables: average (mean) and standard deviation (std) values within a 30-meter grid from 10 m resolution of optical indices from Sentinel-2, and fractional coverage for distinct land cover classes within 30 m grids from the existing level 3 land cover map. Four schemes with different combinations of input variables were compared. Notably, when all three factors (i.e., mean, std, and fractional cover) were used to consider the variation of landcover in urban areas(Scheme 4, S4), the machine learning model exhibited improved performance compared to using only the mean of optical indices (Scheme 1). Of the various models proposed, the random forest (RF) model with S4 demonstrated the most remarkable performance, achieving R² of 0.8196, and mean absolute error (MAE) of 0.0749, and a root mean squared error (RMSE) of 0.1022. The std variable exhibited the highest impact on model outputs within the heterogeneous land covers based on the variable importance analysis. This trained RF model with S4 was then applied to the entire Suwon region, consistently delivering robust results with an R² of 0.8702, MAE of 0.0873, and RMSE of 0.1335. The FTC estimation method developed in this study is expected to offer advantages for application in various regions, providing fundamental data for a better understanding of carbon dynamics in urban ecosystems in the future.

• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.641-649
• /
• 2023

This study compares and analyzes the performance of a shield manufactured using 3D printing technology to find out its applicability as a shield in high-energy electron beam therapy. Actual measurement and monte carlo simulations were performed to evaluate the shielding performance of 3D printing materials for high-energy electron beams. First, in order to secure reliability for the simulation, a source term evaluation was conducted by referring to the IAEA's TRS-398 recommendation. Second, to analyze the shielding performance of PLA+W (93%), a specimen was manufactured using a 3D printer, and the shielding rate by thickness according to electron beam energy was evaluated. Third, the shielding thickness required for electron beam treatment was calculated through a comparative analysis of shielding performance between PLA+W (93%) and existing shielding bodies. First, as a result of the evaluation of the source term through actual measurement and simulation, the TRS-398 recommendation was satisfied with an error of less than 1%, thereby securing the reliability of the simulation. Second, as a result of the shielding performance analysis for PLA+W (93%), 6 MeV electron beams showed a shielding rate of more than 95% at 3.12 mm, and 15 MeV electron beams showed a shielding rate of more than 90% at 10 mm thickness. Third, through simulations, comparative analysis between PLA+W (93%) materials and existing shields showed high shielding rates within the same thickness in the order of tungsten, lead, copper, PLA+W (93%), and aluminum. 6 MeV electron beams showed almost similar shielding rates at 5 mm or more and 15 MeV electron beams. Through this study in the future, it is judged that it can be used as basic data for the production and application of shielding bodies using PLA+W (93%) materials in high-energy electron beam treatment.

• Journal of Korea Water Resources Association
• /
• v.57 no.1
• /
• pp.35-44
• /
• 2024

Research in dam inflow prediction has actively explored the utilization of data-driven machine learning and deep learning (ML&DL) tools across diverse domains. Enhancing not just the inherent model performance but also accounting for model characteristics and preprocessing data are crucial elements for precise dam inflow prediction. Particularly, existing rainfall data, derived from snowfall amounts through heating facilities, introduces distortions in the correlation between snow accumulation and rainfall, especially in dam basins influenced by snow accumulation, such as Soyang Dam. This study focuses on the preprocessing of rainfall data essential for the application of ML&DL models in predicting dam inflow in basins affected by snow accumulation. This is vital to address phenomena like reduced outflow during winter due to low snowfall and increased outflow during spring despite minimal or no rain, both of which are physical occurrences. Three machine learning models (SVM, RF, LGBM) and two deep learning models (LSTM, TCN) were built by combining rainfall and inflow series. With optimal hyperparameter tuning, the appropriate model was selected, resulting in a high level of predictive performance with NSE ranging from 0.842 to 0.894. Moreover, to generate rainfall correction data considering snow accumulation, a simulated snow accumulation algorithm was developed. Applying this correction to machine learning and deep learning models yielded NSE values ranging from 0.841 to 0.896, indicating a similarly high level of predictive performance compared to the pre-snow accumulation application. Notably, during the snow accumulation period, adjusting rainfall during the training phase was observed to lead to a more accurate simulation of observed inflow when predicted. This underscores the importance of thoughtful data preprocessing, taking into account physical factors such as snowfall and snowmelt, in constructing data models.

• Journal of Korea Water Resources Association
• /
• v.57 no.5
• /
• pp.333-346
• /
• 2024

High-resolution medium-range streamflow prediction is crucial for sustainable water quality and aquatic ecosystem management. For reliable medium-range streamflow predictions, it is necessary to understand the characteristics of forcings and to effectively utilize weather forecast data with low spatio-temporal resolutions. In this study, we presented a comparative analysis of medium-range streamflow predictions using the distributed hydrological model, WRF-Hydro, and the numerical weather forecast Global Data Assimilation and Prediction System (GDAPS) in the Geumho River basin, Korea. Multiple forcings, ground observations (AWS&ASOS), numerical weather forecast (GDAPS), and Global Land Data Assimilation System (GLDAS), were ingested to investigate the performance of streamflow predictions with highresolution WRF-Hydro configuration. In terms of the mean areal accumulated rainfall, GDAPS was overestimated by 36% to 234%, and GLDAS reanalysis data were overestimated by 80% to 153% compared to AWS&ASOS. The performance of streamflow predictions using AWS&ASOS resulted in KGE and NSE values of 0.6 or higher at the Kangchang station. Meanwhile, GDAPS-based streamflow predictions showed high variability, with KGE values ranging from 0.871 to -0.131 depending on the rainfall events. Although the peak flow error of GDAPS was larger or similar to that of GLDAS, the peak flow timing error of GDAPS was smaller than that of GLDAS. The average timing errors of AWS&ASOS, GDAPS, and GLDAS were 3.7 hours, 8.4 hours, and 70.1 hours, respectively. Medium-range streamflow predictions using GDAPS and high-resolution WRF-Hydro may provide useful information for water resources management especially in terms of occurrence and timing of peak flow albeit high uncertainty in flood magnitude.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.1
• /
• pp.59-78
• /
• 2024

In tunnel construction, the stability is evaluated by the settlement of adjacent structures and ground, but the shear strain of the ground is the main factor that determines the failure mechanism of the ground due to the tunnel excavation and the change of the operating load, and can be used to review the stability of the tunnel excavation and to calculate the reinforcement area. In this study, a twin tunnel excavation was simulated on a soft ground in an urban area through a laboratory model test to analyze the behavior of the twin tunnel excavation on the adjacent pile grouped foundation and adjacent ground. Both the displacement and the shear strain of ground were obtained using a close-range photogrammetry during laboratory model test. In addition, two-dimensional finite element numerical analysis was performed based on the model test. The results of a back-analysis showed that the maximum shear strain rate tends to decrease as the horizontal distance between the pillars of the twin tunnel and the vertical distance between the toe of the pile group and the crown of the tunnel were decreased. The impact of the second tunnel on the first tunnel and pile group was decreased as the horizontal distance between the pillars of the twin tunnel was increased. In addition, the vertical distance between the toe of the pile group and the crown of the tunnel had a relatively greater impact on the shear strain results than the horizontal distance of the pillars between the twin tunnels. According to the results of the close-range photogrammetry and numerical analysis, the settlement of adjacent pile group and adjacent ground was measured within the design criteria, but the shear strain of the ground was judged to be outside the range of small strain in all cases and required reinforcement.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.68 no.4
• /
• pp.431-437
• /
• 2023

This study evaluated the ecological characteristics related to spike heading time of three Korean foxtail millet cultivars, i.e., one early and two late maturities, and a finger millet cultivar in the north-central region of the Korean Peninsula, Kangwon Province. The changes in heading time occurred due to the changes in planting time from mid-May to late June. The heading time of the early-maturity cultivars was early August, with 80 days required for heading (DH) for the mid-May planting; late August, with 65 DHs for the late June planting; and mid-late August, with 100 DHs and mid-October, with 65 DHs, respectively, for the late-maturity cultivars. The accumulated temperature at heading time ranged from 1,700℃ of mid-May planting to 1,500℃ of late June planting in the early-maturity cultivars. In contrast, it ranged from 2,100℃ to 1,900℃ in the late-maturity cultivars. The photoperiod at heading time ranged from 14.0 h to 13.2 h in the early-maturity cultivars, whereas it was from 13.2 h to 12.5 h in the late-maturity cultivars. Considering that the limiting heading time of Korean foxtail millet and finger millet in the northern region of Kangwon Povince is late August, the limiting accumulated temperature at the heading time was evaluated to be approximately 1,500℃ and 2,000℃ for early and late-maturity cultivars, respectively. The mean daily temperature from planting to heading time showed a negative correlation with the DH, which was shortened with the increase in mean daily temperature. This suggests that delaying the planting time from May to June in the north-central region of the Korean Peninsula increases the mean daily temperature during vegetative growth periods, resulting in the decrease of the DH and the accumulated temperature.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.26 no.2
• /
• pp.127-139
• /
• 2024

Climate change has increased extreme weather events likewise heatwaves, heavy rain, and drought. Unlike other natural disaster, drought is a slowly developing phenomenon and thus drought damage increases as the drought continues. Therefore, it is necessary to understand the characteristics and mechanism of drought occurrence. Agricultural drought occurs when the water supply needed by crops becomes insufficient due to lack of soil water. Therefore, soil water is used as a key variable affecting agricultural drought. In this study, we examined the spatio-temporal distribution and trends of drought across the Korean Peninsula by determining the soil available water content (SAWC) through a model that integrated soil, meteorological, and crop data. Moreover, an investigation into the correlation between meteorological variables and the SAWC was conducted to assess how meteorological characteristics influence the nature of drought occurrences. During the soybean cultivation period, the average SAWC was lowest in 2018 at 88.6% and highest in 2021 at 103.2%. Analysis of the spatial distribution of SAWC by growth stage revealed that the lowest SAWC occurred during the flowering stage (S3) in 2018, during the leaf extension stage (S2) in 2019, during the seedling stage (S1) in 2020, again during the flowering stage (S3) in 2021, and during the seedling stage (S1) in 2022. Based on the average SAWC across different growth stages, the frequency of upland drought was the highest at 22 times during the S3 in 2018. The lowest SAWC was primarily influenced by a significant negative correlation with rainfall and evapotranspiration, whereas the highest SAWC showed a significant positive correlation with rainfall and relative humidity, and a significant negative correlation with reference evapotranspiration.

• Korean Journal of Environment and Ecology
• /
• v.38 no.3
• /
• pp.277-292
• /
• 2024

In order to manage large-scale forest fires concentrated in Gangwon-do and Gyeongsangbuk-do with severe topographical heterogeneity, a decision-making process through efficient and rapid damage assessment using satellite images is essential. Accordingly, this study targets a large-scale forest fire that ignited in Gangneung and the Donghae, Gangwon-do on March 5, 2022, and was extinguished around 19:00 on March 8, to estimate the fire severity using dNBR and derive environmental factors that affect the grade. As environmental factors, we quantified the regular vegetation index representing vegetation or fuel type, the forest index that classifies tree species, the regular moisture index representing moisture content, and DEM in relation to topography, and then analyzed the correlation with the fire severity. In terms of fire severity, the widest range was 'Unbured' at 52.4%, followed by low severity at 42.9%, medium-low severity at 4.3%, and medium-high severity at 0.4%. Environmental factors showed a negative correlation with dNDVI and dNDWI, and a positive correlation with slope. Regarding vegetation, the differences between coniferous, broad-leaved, and other groups in dNDVI, dNIWI, and slope, which were analyzed to affect the fire severity, were analyzed to be significant with p-value < 2.2e-16. In particular, the difference between coniferous and broad-leaved forests was clear, and it was confirmed that coniferous forest suffered more damage than broad-leaved forest due to the higher fire severity in the Gangwon-do region, including Pinus densiflora, which are dominant species, as well as P. koraiensis, P. rigida and P. thunbergii.

• Journal of Korea Water Resources Association
• /
• v.57 no.7
• /
• pp.481-491
• /
• 2024

Recent droughts make hydroelectric power generation (HPG) decreasing. Due to climate change in the future, the frequency and intensity of drought are expected to increase, which will increase uncertainty of HPG in multi-purpose dams. Therefore, it is necessary to estimate the amount of HPG according to climate change scenarios and analyze the effect of drought on the amount of HPG. This study analyzed the future HPG of the Soyanggang Dam and Chungju Dam according to the SSP2-4.5 and SSP5-8.5 scenarios. Regression equations for HPG were developed based on the observed data of power generation discharge and HPG in the past provided by My Water, and future HPGs were estimated according to the SSP scenarios. The effect of drought on the amount of HPG was investigated based on the drought severity calculated using the standardized precipitation index (SPI). In this study, the future SPIs were calculated using precipitation data based on four GCM models (CanESM5, ACCESS-ESM1-5, INM-CM4-8, IPSL-CM6A) provided through the environmental big data platform. Overall results show that climate change had significant effects on the amount of HPG. In the case of Soyanggang Dam, the amount of HPG decreased in the SSP2-4.5 and SSP5-8.5 scenarios. Under the SSP2-4.5 scenario the CanESM model showed a 65% reduction in 2031, and under the SSP5-8.5 scenario the ACCESS-ESM1-5 model showed a 54% reduction in 2029. In the case of Chungju Dam, under the SSP2-4.5 and SSP5-8.5 scenarios the average monthly HPG compared to the reference period showed a decreasing trend except for INM-CM4 model.