• Journal of Korea Water Resources Association
• /
• v.53 no.12
• /
• pp.1159-1172
• /
• 2020

This study applied deep convolution neural network based on U-Net and SegNet using long period weather radar data to very short-term rainfall prediction. And the results were compared and evaluated with the translation model. For training and validation of deep neural network, Mt. Gwanak and Mt. Gwangdeoksan radar data were collected from 2010 to 2016 and converted to a gray-scale image file in an HDF5 format with a 1km spatial resolution. The deep neural network model was trained to predict precipitation after 10 minutes by using the four consecutive radar image data, and the recursive method of repeating forecasts was applied to carry out lead time 60 minutes with the pretrained deep neural network model. To evaluate the performance of deep neural network prediction model, 24 rain cases in 2017 were forecast for rainfall up to 60 minutes in advance. As a result of evaluating the predicted performance by calculating the mean absolute error (MAE) and critical success index (CSI) at the threshold of 0.1, 1, and 5 mm/hr, the deep neural network model showed better performance in the case of rainfall threshold of 0.1, 1 mm/hr in terms of MAE, and showed better performance than the translation model for lead time 50 minutes in terms of CSI. In particular, although the deep neural network prediction model performed generally better than the translation model for weak rainfall of 5 mm/hr or less, the deep neural network prediction model had limitations in predicting distinct precipitation characteristics of high intensity as a result of the evaluation of threshold of 5 mm/hr. The longer lead time, the spatial smoothness increase with lead time thereby reducing the accuracy of rainfall prediction The translation model turned out to be superior in predicting the exceedance of higher intensity thresholds (> 5 mm/hr) because it preserves distinct precipitation characteristics, but the rainfall position tends to shift incorrectly. This study are expected to be helpful for the improvement of radar rainfall prediction model using deep neural networks in the future. In addition, the massive weather radar data established in this study will be provided through open repositories for future use in subsequent studies.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.1
• /
• pp.13-34
• /
• 2022

Soil moisture data have been collected at 11 agrometeorological stations operated by The Korea Meteorological Administration (KMA). This study aimed to verify the accuracy of soil moisture data of KMA and develop a correction formula to be applied to improve their quality. The soil of the observation field was sampled to analyze its physical properties that affect soil water content. Soil texture was classified to be sandy loam and loamy sand at most sites. The bulk density of the soil samples was about 1.5 g/cm³ on average. The content of silt and clay was also closely related to bulk density and water holding capacity. The EnviroSCAN model, which was used as a reference sensor, was calibrated using the self-manufactured "reference soil moisture observation system". Comparison between the calibrated reference sensor and the field sensor of KMA was conducted at least three times at each of the 11 sites. Overall, the trend of fluctuations over time in the measured values of the two sensors appeared similar. Still, there were sites where the latter had relatively lower soil moisture values than the former. A linear correction formula was derived for each site and depth using the range and average of the observed data for the given period. This correction formula resulted in an improvement in agreement between sensor values at the Suwon site. In addition, the detailed approach was developed to estimate the correction value for the period in which a correction formula was not calculated. In summary, the correction of soil moisture data at a regular time interval, e.g., twice a year, would be recommended for all observation sites to improve the quality of soil moisture observation data.

• Korean Journal of Ecology and Environment
• /
• v.55 no.4
• /
• pp.274-284
• /
• 2022

Through sample-size-based rarefaction analyses, we tried to suggest the appropriate degree of sample concentration and sub-sample extraction, as a way to estimate more accurate zooplankton species diversity when assessing biodiversity. When we collected zooplankton from three reservoirs with different environmental characteristics, the estimated species richness (S) and Shannon's H' values showed different changing patterns according to the amount of sub-sample extracted from the whole sample by reservoir. However, consequently, their zooplankton diversity indices were estimated the highest values when analyzed by extracting the largest amount of sub-sample. As a result of rarefaction analysis about sample coverage, in the case of deep eutrophic reservoir (Juam) with high zooplankton species and individual numbers, it was analyzed that 99.8% of the whole samples were represented by only 1 mL of sub-sample based on 100 mL of concentrated samples. On the other hand, in Soyang reservoir, which showed very small species and individual numbers, a relatively low representation at 97% when 10 mL of sub-sample was extracted from the same amount of concentrated sample. As such, the representation of sub-sample for the whole zooplankton sample varies depending on the individual density in the sample collected from the field. If the degree of concentration of samples and the amount of sub-sample extraction are adjusted according to the collected individual density, it is believed that errors that occur when comparing the number of species and diversity indices among different water bodies can be minimized.

• Journal of Environmental Impact Assessment
• /
• v.32 no.2
• /
• pp.134-145
• /
• 2023

Currently, the floodplains of major rivers are transforming into various types of waterfront spaces according to the increase in leisure activities and improved accessibility. In general, waterfront activities in river channels tend to be concentrated in summer, and the waterfront activities during this period directly affect water quality. Accordingly, it is necessary to accurately compare and evaluate the characteristics and water quality of waterfront activities during the period when waterfront activities are concentrated. In this study, the following research was conducted to compare and analyze the current status of waterfront activities of users of waterfront areas and the water quality of waterfront areas. First, three waterfront areas were selected for investigation using the information from the Ministry of Environment's water quality measurement network. Second, a survey was conducted on the satisfaction and types of waterfront activities targeting users of waterfront areas. Third, water quality grades were calculated based on monthly water quality measurement factors and compared. Fourth, statistical analysis (one-way analysis of variance) was conducted to see if there was a significant difference in water quality characteristics between periods of high waterfront activity and periods of low waterfront activity using water quality measurement data for the last 5 years. As a result of this analysis, the following conclusions were drawn in this study. First, the use of waterfront activities was investigated in the order of camping, water skiing, fishing, swimming, and rafting. Second, satisfaction factors for waterfront activities were investigated in the order of activity convenience, water quality, waterlandscape, transportation access convenience, and temperature. Third, it was found that satisfaction with water quality in waterfront areas was generally unsatisfactory regardless of the water quality grade presented by the competent authority. Fourth, as a result of comparing the water quality measurement network data of the Ministry of Environment by water quality grade, generally good grades were found, and in particular, there was a difference in grade frequency by season in the BOD category. Fifth, as a result of statistical analysis (one-way ANOVA) of water quality monitoring network data by season, there were statistically significant differences in COD, BOD, TP, and TOC except for DO. Considering the results of these studies, it is judged that it is necessary to prepare a comprehensive management system for water quality improvement in the waterfront zone and to improve water quality during periods of high waterfront activity, and to prepare a water quality forecasting system for waterfront areas in the future.

• Journal of Environmental Impact Assessment
• /
• v.32 no.6
• /
• pp.377-388
• /
• 2023

Carbon management is emerging as an important factor for global warming control, and land use change is considered one of the causes. To quantify the changes in carbon stocks due to development, this study attempted to calculate carbon storage by borrowing the formula of the InVEST Carbon Storage and Sequestration Model (InVEST Model). Before analyzing carbon stocks, a carbon pool was compiled based on previous studies in Korea. Then, we estimated the change in carbon stocks according to the development of Osong National Industrial Park (ONIP) and the application of alternatives. The analysis shows that 16,789.5 MgC will be emitted under Alternative 1 and 16,305.3 MgC under Alternative 2. These emissions account for 44.4% and 43.1% of the pre-project carbon stock, respectively, and shows that choosing Alternative 2 is advantageous for reducing carbon emissions. The difference is likely due to the difference in grassland area between Alternatives 1 and 2. Even if Alternative 2 is selected, efforts are needed to increase the carbon storage effect by managing the appropriate level of green cover in the grassland, creating multi-layered vegetation, and installing low-energy facilities. In addition, it is suggested to conserve wetlands that can be lost during the stream improvement process or to create artificial wetlands to increase carbon storage. The assessment of carbon storage using carbon pools by land cover can improve the objectivity of comparison and evaluation analysis results for land use plans in Environmental Impact Assessment and Strategic Environmental Impact Assessment. In addition, the carbon pool generated in this study is expected to be used as a basis for improving the accuracy of such analyses.

• 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 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.