• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.246-246
• /
• 2023

Multi-purpose dams are operated accounting for both physical and socioeconomic factors. This study aims to evaluate the utility of a deep learning algorithm-based model for three multi-purpose dam operation (Seomjin River dam, Juam dam, and Juam Control dam) in Seomjin River. In this study, the Gated Recurrent Unit (GRU) algorithm is applied to predict hourly water level of the dam reservoirs over 2002-2021. The hyper-parameters are optimized by the Bayesian optimization algorithm to enhance the prediction skill of the GRU model. The GRU models are set by the following cases: single dam input - single dam output (S-S), multi-dam input - single dam output (M-S), and multi-dam input - multi-dam output (M-M). Results show that the S-S cases with the local dam information have the highest accuracy above 0.8 of NSE. Results from the M-S and M-M model cases confirm that upstream dam information can bring important information for downstream dam operation prediction. The S-S models are simulated with altered outflows (-40% to +40%) to generate the simulated water level of the dam reservoir as alternative dam operational scenarios. The alternative S-S model simulations show physically inconsistent results, indicating that our deep learning algorithm-based model is not explainable for multi-purpose dam operation patterns. To better understand this limitation, we further analyze the relationship between observed water level and outflow of each dam. Results show that complexity in outflow-water level relationship causes the limited predictability of the GRU algorithm-based model. This study highlights the importance of socioeconomic factors from hidden multi-purpose dam operation processes on not only physical processes-based modeling but also aritificial intelligence modeling.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.133-139
• /
• 2023

This paper proposes a two-stage Water Shield Automation System (WSAS) to predict the possibility of river overflow and vehicle flooding due to sudden rainfall. The WSAS uses a two-stage Deep Neural Network (DNN) model. First, a river overflow prediction module is designed with LSTM to decide whether the river is flooded by predicting the river's water level rise. Second, a vehicle flooding prediction module predicts flooding of underground parking lots by detecting flooded tires with YOLOv5 from CCTV images. Finally, the WSAS automatically installs the water barrier whenever the river overflow and vehicle flooding events happen in the underground parking lots. The only constraint to implementing is that collecting training data for flooded vehicle tires is challenging. This paper exploits the Image C&S data augmentation technique to synthesize flooded tire images. Experimental results validate the superiority of WSAS by showing that the river overflow prediction module can reduce RMSE by three times compared with the previous method, and the vehicle flooding detection module can increase mAP by 20% compared with the naive detection method, respectively.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.49 no.4
• /
• pp.13-22
• /
• 2007

The uncertainty in water quality model predictions is inevitably high due to natural stochasticity, model uncertainty, and parameter uncertainty. An integrated modeling system under uncertainty was described and demonstrated for use in watershed management and receiving-water quality prediction. A watershed model (HSPF), a receiving water quality model (WASP), and a wetland model (NPS-WET) were incorporated into an integrated modeling system (modified-BASINS) and applied to the Hwaseong Reservoir watershed. Reservoir water quality was predicted using the calibrated integrated modeling system, and the deterministic integrated modeling output was useful for estimating mean water quality given future watershed conditions and assessing the spatial distribution of pollutant loads. A Monte Carlo simulation was used to investigate the effect of various uncertainties on output prediction. Without pollution control measures in the watershed, the concentrations of total nitrogen (T-N) and total phosphorous (T-P) in the Hwaseong Reservoir, considering uncertainty, would be less than about 4.8 and 0.26 mg 4.8 and 0.26 mg $L^{-1}$, respectively, with 95% confidence. The effects of two watershed management practices, a wastewater treatment plant (WWTP) and a constructed wetland (WETLAND), were evaluated. The combined scenario (WWTP + WETLAND) was the most effective at improving reservoir water quality, bringing concentrations of T-N and T-P in the Hwaseong Reservoir to less than 3.54 and 0.15 mg ${L^{-1}$, 26.7 and 42.9% improvements, respectively, with 95% confidence. Overall, the Monte Carlo simulation in the integrated modeling system was practical for estimating uncertainty and reliable in water quality prediction. The approach described here may allow decisions to be made based on probability and level of risk, and its application is recommended.

• Journal of Forest and Environmental Science
• /
• v.30 no.1
• /
• pp.76-84
• /
• 2014

This study was performed to monitor the effects of water level change on changes of landscape, vegetation community, and species diversity of riparian forest. Hantan river dam, study area, has been constructed in the area of Chansoo-myeon, Pocheon-si and Yeoncheon-eup, Yeoncheon-gun, Gyeonggi-do, which is a dam for flood control only in flooding season. Landscape changes were notable after the construction of coffer dam, and the changes were caused by water level increase in areas of riparian forests which consisted of mainly withered willow as a dominant species in the flooding season. It changed vegetation communities of riparian forest from Phragmites japonica and Salix koreensis to Phragmites japonica. Species diversity index was lowest in 2010 when the coffer dam was constructed and showed an increasing trend later. Thus, this study is well in agreement with a previous report that plants of the genus Salix wither by muddy water during flooding and also suggests, controlling water level of river and prediction of water level change's effects should be considered when any facilities are planned.

• Proceedings of the Korea Contents Association Conference
• /
• 2019.05a
• /
• pp.3-4
• /
• 2019

강의 수위 예측은 강 유역의 홍수 발생에 대한 방재 차원에서 아주 중요하다. 이 논문에서는 낙동강을 대상으로 수위를 예측하는 신경회로망 모델을 기반으로 홍수위에 도달하는 입력 조건을 학습에 의해 찾아내는 방법을 제시한다.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.36 no.2
• /
• pp.96-110
• /
• 1994

The purpose of this study is to develop soil salt prediction model for the estimation of irrigation water requirements for dry field crops in reclaimed tidelands. The simulation model based on water balance equation, salt balance equation, and salt storage equation was developed for daily prediction of sa]t concentration in root zone. The data obtained from field measurement during the growing period of tomato were used to evaluate the applicability of this model. The results of this study are summarized as follows: 1.The optimum irrigation point which maximizes the crop yield in reclaimed tidelands of silt loam soil while maintaining the salt concentration within the tolerance level, ws found to be pF 1.6, and total irrigation requirement after transplanting was 602mm(6.7 mm/day)for tomato. 2.When the irrigation point was pF 1.6, the deviation between predicted and measured salt concentration was less than 4 % at the significance level of 1 7% 3.Since the deviations between predicted and measured values data decrease as the amount of irrigation water increases, the proposed model appear to be more suitable for use in reclaimed tidelands. 4.The amount of irrigation water estimated by the simulation model was 7.2mm/day in the average for cultivating tomato at the optimum irrigation point of pF 1.6.The simulation model proposed in this study can be generalized by applying it to other crops. This, model, also, could be further improved and extended to estimate desalinization effects in reclaimed tidelands by including meteorological effect, capillary phenomenon, and infiltration.

• The Journal of the Korea Contents Association
• /
• v.9 no.6
• /
• pp.9-16
• /
• 2009

According to the construction of infrastructure for the water resource management services, the importance of the eco-friendly reservoir tank management is being spotlighted. In this paper, we proposed the eco-friendly reservoir tank management using prediction for improving the water quality and on-line managing efforts of reservoir tanks. The proposed method defined the context and environment of the reservoir tank and predicted the profited service according to the pump motion, the solar battery, the chemicals, the water level, the telephone line, and the modem using collaborative filtering. To evaluate the performance of the eco-friendly reservoir tank management system using prediction, we conducted sample T-tests so as to verify usefulness. This evaluation found that the difference of satisfaction by service was statistically meaningful, and showed high satisfaction. Accordingly, the satisfaction and the quality of services will be improved the efficient prediction by supporting the context information as well as the environment information.

• Nuclear Engineering and Technology
• /
• v.56 no.5
• /
• pp.1725-1732
• /
• 2024

In nuclear power plants, reactor coolant leakage can occur due to various reasons. Early detection of leaks is crucial for maintaining the safety of nuclear power plants. Currently, a detection system is being developed in Korea to identify reactor coolant system (RCS) leakage of less than 0.5 gpm. Typically, RCS leaks are detected by monitoring temperature, humidity, and radioactivity in the containment, and a water level in the sump. However, detecting small leaks proves challenging because the resulting changes in the containment humidity and temperature, and the sump water level are minimal. To address these issues and improve leak detection speed, it is necessary to quantify the leaks and develop an artificial intelligence-based leak detection system. In this study, we employed bidirectional long short-term memory, which are types of neural networks used in artificial intelligence, to predict the relative humidity in the leakage area for leak quantification. Additionally, an optimization technique was implemented to reduce learning time and enhance prediction performance. Through evaluation of the developed artificial intelligence model's prediction accuracy, we expect it to be valuable for future leak detection systems by accurately predicting the relative humidity in a leakage area.

• Journal of Ocean Engineering and Technology
• /
• v.5 no.1
• /
• pp.25-34
• /
• 1991

An accurate estimation of water level variation when thewaves propagate to the coastal regionis very important for the port and harbor development plan. This study describes the application of a hybrid element model to harbor oscillation problem due to the construction of shore structure and implementation of shore boundary. The site selected is Pusan Harbor area with the third development and the Artificial Island plan. The observed water level changes at the site are compared with the result of the numerical experiment. The model gives a very important prediction of water level changes for navigation and harbor design.

• Journal of Environmental Science International
• /
• v.31 no.12
• /
• pp.1027-1038
• /
• 2022

The intertidal zone has both land and marine characteristics and shows complex weather environments. These characteristics are suited for studying climate change, energy balance and ecosystems, and may play an important role in coastal and marine weather prediction and analysis. This study was conducted at Odo Island, approximately 300m from the mainland in Yeosu. We built a weather observation system capable of real-time monitoring on the mud flat in the intertidal zone and measured actual weather and marine data. Weather observation was conducted from April to June 2022. The results showed changes in air temperature and water temperature with changes in the tide level during spring. Correlation analysis revealed characteristic changes in air temperature and water temperature during the day and night, and with inundation and exposure.