• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.949-965
• /
• 2023

In this study, we propose a method to monitor the surface area of agricultural reservoirs in South Korea using Sentinel-1 synthetic aperture radar images and the deep learning model, Swin Transformer. Utilizing the Google Earth Engine platform, datasets from 2017 to 2021 were constructed for seven agricultural reservoirs, categorized into 700 K-ton, 900 K-ton, and 1.5 M-ton capacities. For four of the reservoirs, a total of 1,283 images were used for model training through shuffling and 5-fold cross-validation techniques. Upon evaluation, the Swin Transformer Large model, configured with a window size of 12, demonstrated superior semantic segmentation performance, showing an average accuracy of 99.54% and a mean intersection over union (mIoU) of 95.15% for all folds. When the best-performing model was applied to the datasets of the remaining three reservoirsfor validation, it achieved an accuracy of over 99% and mIoU of over 94% for all reservoirs. These results indicate that the Swin Transformer model can effectively monitor the surface area of agricultural reservoirs in South Korea.

• 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.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.997-1008
• /
• 2023

Ship detection at sea can be performed in various ways. In particular, satellites can provide wide-area surveillance, and Synthetic Aperture Radar (SAR) imagery can be utilized day and night and in all weather conditions. To propose an efficient ship detection method from SAR images, this study aimed to apply the You Only Look Once Version 5 (YOLOv5) model to Sentinel-1 images and to analyze the difference between individual vs. integrated models and the accuracy characteristics by polarization. YOLOv5s, which has fewer and lighter parameters, and YOLOv5x, which has more parameters but higher accuracy, were used for the performance tests (1) by dividing each polarization into HH, HV, VH, and VV, and (2) by using images from all polarizations. All four experiments showed very similar and high accuracy of 0.977 ≤ AP@0.5 ≤ 0.998. This result suggests that the polarization integration model using lightweight YOLO models can be the most effective in terms of real-time system deployment. 19,582 images were used in this experiment. However, if other SAR images,such as Capella and ICEYE, are included in addition to Sentinel-1 images, a more flexible and accurate model for ship detection can be built.

• 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.

• Korean Journal of Poultry Science
• /
• v.50 no.4
• /
• pp.311-323
• /
• 2023

This study aimed to investigate the impact of Bacillus subtilis-based probiotics and oregano essential oil on the production performance, egg quality, and intestinal morphology of late-phase laying hens (69-weeks). A total of 150 laying hens of 69-week-old were randomly allotted into 6 treatment groups with 5 replicates of 5 birds in each replicate. Laying hens were divided into high (H) and average (A) egg production groups prior to the trial. The hens in each group were supplemented with Bacillus subtilis, or oregano essential oil: CON, a basal diet; BS, basal diet plus 3 × 10⁸ CFU/kg feed Bacillus subtilis; OEO, basal diet plus 0.3 g/kg feed oregano essential oil. Egg performance, blood characteristics, egg quality, and intestinal morphology of the late-phase laying hens were evaluated. Both BS and OEO significantly enhanced (P<0.05) egg production compared to CON in high egg production. The blood characteristics indicated no significant differences based on the egg production and the supplementation of BS and OEO in the late-phase laying hens. The eggshell strength was significantly improved (P<0.05) in both OEO compared to both CON. A significantly decreased (P<0.05) the villus height to crypt depth ratio (VH/CD) in the ileum compared to H, and in the treatment groups supplemented with BS and OEO, VH/CD showed a significant increase (P<0.05) compared to both CON. These results suggest that the supplementation of Bacillus subtilis and oregano essential oil in the diet of late-phase laying hens could serve as a potential strategy to enhance egg production, egg quality, and gut health.

• Korean Journal of Poultry Science
• /
• v.50 no.4
• /
• pp.325-336
• /
• 2023

This study used leaves and stems of 'Tongchaeru', one of the sweet potato varieties, to investigate broiler productivity, meat quality, blood properties, growth hormones, and immune factor levels according to drying method and amount added to feed. For this experiment, a total of 720 1-day-old male Ross 308 broilers were used. Treatments were assigned with 3 replicates per treatment and 20 birds were assigned to each replicate. The treatment group was designed into 12 treatments according to the type of natural product (leaves (L), stems (S)), drying type (natural (N), hot air (H), freeze (F)) and amount added (0.1%, 0.3%). The test was conducted for a total of 5 weeks. In this study, there was no significant difference in productivity depending on the type and amount of additives added (P>0.05). The FS 0.3% group showed high pH and WHC levels, and the shear force was lowest at HL 0.1% group (P<0.05). Blood cell and serum biochemical components were similar in all treatments, and growth hormone IGF-1 was highest in FS 0.1% group (P<0.05). There was no significant difference in IFN-γ, but the highest level of IL-6 was seen in the HS 0.1% group (P<0.05). In conclusion, the meat quality and the level of growth hormone and immune factors in the body were different depending on the type and amount of dried leaves and stems of sweet potato 'Tongchaeru', further study is needed to compare the selected additives and amounts added with those without additions.

• Journal of Life Science
• /
• v.33 no.12
• /
• pp.995-1001
• /
• 2023

This study investigated the effects of three music genres (classical, new age, and rock) on the stress levels of six Jeju crossbred horses (Jeju horse × Thoroughbred) in a horse stable. The horses were exposed to the three genres for seven days, and their stress levels were measured by analyzing physiological markers, including neurotransmitter (cortisol, β-endorphin, dopamine, serotonin, and oxytocin) plasma levels and creatine phosphokinase (CPK) and aldolase serum levels. The neurotransmitter analysis showed significant differences in cortisol levels between classical and new age music exposure. Dopamine levels decreased significantly only with new age exposure. Although there were no significant differences in β-endorphin levels between the three genres, β-endorphin levels decreased with increasing classical and new age music playback times and increased with increasing rock music playback times. There were no significant differences in serotonin levels between the three genres. Oxytocin levels decreased significantly with exposure to classical and rock music. The CPK and aldolase analyses showed that CPK levels decreased significantly only with exposure to new age music and increased after playback ended, while aldolase levels decreased significantly with classical and new age music exposure and increased after playback ended. These findings suggest that classical music and new age are the optimal music genres for the psychological stability of Jeju crossbred horses. Playing back an appropriate music genre could be used to improve breeding and promote the welfare of Jeju crossbred horses.

• Korean Journal of Poultry Science
• /
• v.50 no.4
• /
• pp.231-240
• /
• 2023

Infectious bursal disease (IBD) is an acute, highly contagious, and immunosuppressive disease in young chickens, and causes considerable economic losses to the poultry industry. More than 30 years ago, an antigenic variant IBDV (avIBDV) was reported in chicken farms in the United States. Recently, a novel avIBDV exhibited clear differences in molecular characteristics compared with previous variant strains. This study investigated the molecular characteristics of recently isolated avIBDV strains in Korea. Strains of avIBDV were confirmed by reverse transcription PCR (RT-PCR) and were propagated in 10-day-old specific-pathogen-free (SPF) embryonated chicken eggs through chorioallantoic membrane (CAM) inoculation. Multiple sequence alignment and phylogenetic analyses of hypervariable regions VP2 gene revealed that the strains originated from two different avIBDV lineages (G2a and G2d). In our results, we confirmed the co-existence and prevalence of avIBDV genogroup G2a and G2d in chicken farms. It is necessary to study the protective efficacy of current vaccines against avIBDVs.

• Journal of the Korean GEO-environmental Society
• /
• v.24 no.12
• /
• pp.61-67
• /
• 2023

Heat pipes located underground in urban areas and operated under high temperature and pressure conditions can cause large-scale human and economic damage if damaged. In order to predict damage in advance, damage and construction information of heat pipe are analyzed to derive independent variables that have a correlation with frequency of damage, and a simple regression analysis modified model using each variable is applied to the field. However, as the correlation between independent variables applied to the model increases, the independence between variables is harmed and the reliability of the model decreases. In this study, the independence of the pipe diameter, burial depth, insulation level of monitoring system, and disconnection or short circuit of the detection line, which are judged to be interrelated, was tested to derive a method for combining variables and setting categories necessary to apply to the frequency of damage estimation model. For the test of independence, the continuous variables pipe diameter and burial depth were each converted into three categories, insulation level of monitoring system was converted into two categories, and the categorical variable disconnection or short circuit of the detection line status was kept as two categories. As a result of the test of independence, p-value between pipe diameter and burial depth, level of monitoring system and disconnection or short circuit of the detection line was lower than the significance level (α = 0.05), indicating a large correlation between them. Therefore, the pipe diameter and burial depth were combined into one variable, and the categories of the combined variable were set to 9 considering the previously set categories. The insulation level of monitoring system and the disconnection or short circuit of the detection line were also combined into one variable. Since the insulation level is unreliable when the detection line status is disconnection or short circuit, the categories of the combined variable were set to 3.

• Journal of Korea Water Resources Association
• /
• v.56 no.11
• /
• pp.751-764
• /
• 2023

Gangwon State is centered on the Taebaek Mountains with very different climate characteristics depending on the region, and localized heavy rainfall is a frequent occurrence. Heavy rain disasters have a short duration and high spatial and temporal variability, causing many casualties and property damage. In the last 10 years (2012~2021), the number of heavy rain disasters in Gangwon State was 28, with an average cost of 45.6 billion won. To reduce heavy rain disasters, it is necessary to establish a disaster management plan at the local level. In particular, the current criteria for heavy rain warnings are uniform and do not consider local characteristics. Therefore, this study aims to propose a heavy rainfall warning criteria that considers the threshold rainfall for the advisory areas located in Gangwon State. As a result of analyzing the representative value of threshold rainfall by advisory area, the Mean value was similar to the criteria for issuing a heavy rain warning, and it was selected as the criteria for a heavy rain warning in this study. The rainfall events of Typhoon Mitag in 2019, Typhoons Maysak and Haishen in 2020, and Typhoon Khanun in 2023 were applied as rainfall events to review the criteria for heavy rainfall warnings, as a result of Hit Rate accuracy verification, this study reflects the actual warning well with 72% in Gangneung Plain and 98% in Wonju. The criteria for heavy rain warnings in this study are the same as the crisis warning stages (Attention, Caution, Alert, and Danger), which are considered to be possible for preemptive rain disaster response. The results of this study are expected to complement the uniform decision-making system for responding to heavy rain disasters in the future and can be used as a basis for heavy rain warnings that consider disaster risk by region.