• Journal of Korea Water Resources Association
• /
• v.56 no.4
• /
• pp.245-259
• /
• 2023

The agricultural reservoir is a critical water supply system in South Korea, providing approximately 60% of the agricultural water demand. However, the reservoir faces several issues that jeopardize its efficient operation and management. To address this issues, we propose a novel deep-learning-based water level recognition model that uses CCTV image data to accurately estimate water levels in agricultural reservoirs. The model consists of three main parts: (1) dataset construction, (2) image segmentation using the U-Net algorithm, and (3) CCTV-based water level recognition using either CNN or ResNet. The model has been applied to two reservoirs G-reservoir and M-reservoir with observed CCTV image and water level time series data. The results show that the performance of the image segmentation model is superior, while the performance of the water level recognition model varies from 50 to 80% depending on water level classification criteria (i.e., classification guideline) and complexity of image data (i.e., variability of the image pixels). The performance of the model can be improved if more numbers of data can be collected.

• Journal of the Korean Geosynthetics Society
• /
• v.18 no.4
• /
• pp.181-191
• /
• 2019

Most of the reservoirs in South Korea are fill dam, and overflow and piping phenomena have been detected as the main causes of failure of fill dam. In this study, an operating ◯◯ reservoir located in Gongju-si is modeled in centrifuge model test to study the behavior of reservoir during water level rise and overflow conditions. In order to simulate seepage and overflow in the real reservoir, the model was constructed in 1/50 scale, and deteriorated and reinforced conduits were installed. After modeling the reinforced and deteriorated conditions of the conduits, LVDTs, pore pressure gauges were installed and centrifuge model tests were carried out with water level rise and overflow conditions in order to analyze the reservoir behavior according to the reinforcement methods. The results of centrifuge model test in water level rise condition show that deteriorated conduit has adverse effects in the stability of the reservoir body, and the conduit which is reinforced by the inverse lining method has enhanced stability of the reservoir body. Moreover, installation of water spillway is seen to prevent the scour and erosion of the reservoir body. The study provides a basic data required for the reinforcement of conduit and water spillway in the reservoir.

• Journal of Korea Water Resources Association
• /
• v.40 no.1 s.174
• /
• pp.1-10
• /
• 2007

Reallocation procedure of multipurpose reservoir storage capacity between flood control and conservation is presented as an alternative to secure more water resources. Storage reallocation is an adaptive management mechanism for converting existing normal pool level of reservoirs to more beneficial uses without requirement for physical alteration. This study is intended to develop a reservoir storage reallocation methodology that allows increased water supply storage without minimizing adverse impacts on flood control. The methodology consists of flood control reservoir simulation for inflows with various return periods, flow routing from reservoir to a potential damage site, analyzing river carrying capacity, and reservoir yields estimation for reallocated storages. For the flood control model, a simulation model called Rigid ROM(Reservoir Operation Method) and HEC-5 are used. The approach is illustrated by applying it to two reservoirs system in Geum River basin. Especially with and without new project conditions are considered to analyze trade-offs between competing objectives.

• Ecology and Resilient Infrastructure
• /
• v.2 no.4
• /
• pp.274-283
• /
• 2015

The reservoir shores seem to be vulnerable to biological invasion. The purpose of this research was to find out the floristic composition of alien plants and their relationship between environmental factors on reservoir shorelines in Korea. We investigated flora of alien plants and environmental factors of geomorphology, hydrology, water quality and soil on the shoreline of a total of 35 reservoirs with different water level managements. There were 56 species of alien plants, which was 15% of the total plant species identified in the study of reservoirs. A total of 57% of these alien species were the species which were introduced shortly after opening the port from 1876 to 1921 in Korea. More than 80% of the alien plants on the reservoir shores originated from America and Europe. The current distribution of Ambrosia trifida and Paspalum distichum were restricted in the central part and the southern region of the Korean Peninsula, respectively. The water level fluctuation, flood frequency at the median water level, water pollution index, coverage of rock exposure and mean degree of shoreline slope were determined as important environmental factors that have an effect on the characteristics of shoreline alien flora. Our results suggest that the reservoir shore was in danger of being invaded by alien plants due to the water level management and other human disturbances. For effective conservation of the reservoir ecosystem, periodic monitoring systems are required for the early detection of alien species on the reservoir shore.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.57 no.4
• /
• pp.85-99
• /
• 2015

It is urgent to redevelop the superannuated reservoir levee through the levee raising for countermeasure to climate change and improvement of storage capacity of reservoir. However, low compaction degree of the raised reservoir levee owing to poor construction condition leads to degradation of the stability of the reservoir levee on seepage and earthquake. In this study, seepage and seismic behavior of raised reservoir levee with low compaction degree was evaluated through numerical simulation. From the simulated results, water level raising possibly induces crack and/or sinkhole on the surface of the poorly-compacted raised reservoir levee owing to the increase of the subsidences at the crown and the front side of that. In addition, relatively larger displacement and acceleration response at the front side of raised reservoir levee in seismic condition may degrade overall stability of reservoir levee. Therefore, reasonable construction management for the compaction of the raised reservoir levee is required for ensuring long-term stability on seepage and earthquake.

• Journal of Environmental Science International
• /
• v.17 no.7
• /
• pp.733-741
• /
• 2008

The object of this study is the safety insurance of the dam to provide for the extraordinary flood. The safety insurance of the reservoir was taken by the preparatory discharge using the temporary division tunnel used during the reservoir construction. In this study, the Sungju reservoir was simulated. The existing discharge facilities of the intake tower of the Sungju reservoir could nat have influence on the flood control. When the Sungju reservoir operated to begin preparatory discharge for 48 hrs by the temporary diversion tunnel that have discharge of an 20-years frequency, the water level was lowered about 20 cm. When the Sungju reservoir operated to begin the continuous discharge after the preparatory discharge, the water level was lowered over 1m but the downstream at risk was caused by the resulted. If it is possible to operate to begin the preparatory discharge of the reservoir for 24 hrs by the temporary diversion tunnel, that will improve the flood control faculty of the reservoir without other hydraulic structure and safety of the Sungju reservoir will be higher.

• Journal of Korea Water Resources Association
• /
• v.51 no.7
• /
• pp.555-564
• /
• 2018

The detention reservoir is a hydraulic structure that constructs a levee on the inland of river and sets up side weir in a section of the levee, and this facility stores a part of the flood volume in case of a flood event over a certain scale. In order to optimize the operation of detention reservoir, it is necessary to review the linkage with existing facilities in the river. In this study, the effect of water level reduction and the flow distribution was analyzed according to the location of the side weir in the detention reservoir considering the run-of-the-river gate. Two radial gates were installed in the experimental channel, and the water level in channel and the overflow of weir were measured by moving the location of the side weir upstream from the gate. As a results of experiment, it was confirmed that the water level reduction is more remarkable as the location of the side weir was closer to the gate, and the effect of flow distribution is not greatly changed. When two or more side weirs were operated, it is confirmed that the sufficient storage space was secured and the water level reduction effect with the location of the side weir is not large. In addition, the water level reduction rate according to the location of the side weir was estimated by empirical formula and it is provided as basic data that can be used in the planning of the detention reservoir.

• Journal of Korean Society of Rural Planning
• /
• v.9 no.4 s.21
• /
• pp.1-7
• /
• 2003

This study was conducted to seek the effective water management method of the irrigation reservoirs. Joongpyong reservoir was selected for the hydrologic monitoring, and investigated from May in 1999 to December in 2001. The water level and amount of outlet discharge were measured, the stage discharge equation as a rating curve was induced, and which were compared to the irrigation water requirements calculated by a daily simulation model. The water balance of Joongpyong reservoir was analyzed, mainly on the reservoir storage ratio during irrigation period. Comparing the observed storage and simulation data, the results of the simulation were well agreed with the measured data.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.59 no.3
• /
• pp.97-110
• /
• 2017

This study investigates the efficiencies of machine learning models, including artificial neural network (ANN), generalized regression neural network (GRNN), adaptive neuro-fuzzy inference system (ANFIS) and random forest (RF), for reservoir water level forecasting in the Chungju Dam, South Korea. The models' efficiencies are assessed based on model efficiency indices and graphical comparison. The forecasting results of the models are dependent on lead times and the combination of input variables. For lead time t = 1 day, ANFIS1 and ANN6 models yield superior forecasting results to RF6 and GRNN6 models. For lead time t = 5 days, ANN1 and RF6 models produce better forecasting results than ANFIS1 and GRNN3 models. For lead time t = 10 days, ANN3 and RF1 models perform better than ANFIS3 and GRNN3 models. It is found that ANN model yields the best performance for all lead times, in terms of model efficiency and graphical comparison. These results indicate that the optimal combination of input variables and forecasting models depending on lead times should be applied in reservoir water level forecasting, instead of the single combination of input variables and forecasting models for all lead times.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.433-442
• /
• 2018

The reservoir area is defined as the area surrounded by the planned flood level of the dam or the land under the planned flood level of the dam. In this study, supervised classification based on RF (Random Forest), which is a representative machine learning technique, was performed to detect cropland in the reservoir area. In order to classify the cropland in the reservoir area efficiently, the GLCM (Gray Level Co-occurrence Matrix), which is a representative technique to quantify texture information, NDWI (Normalized Difference Water Index) and NDVI (Normalized Difference Vegetation Index) were utilized as additional features during classification process. In particular, we analyzed the effect of texture information according to window size for generating GLCM, and suggested a methodology for detecting croplands in the reservoir area. In the experimental result, the classification result showed that cropland in the reservoir area could be detected by the multispectral, NDVI, NDWI and GLCM images of UAV, efficiently. Especially, the window size of GLCM was an important parameter to increase the classification accuracy.