Uncertainty of Discharge-SS Relationship Used for Turbid Flow Modeling

Chung, Se-woong; Lee, Jung-Hyun; Lee, Heung-Soo; Maeng, Seung-Jin

doi:10.3741/jkwra.2011.44.12.991

Cited by 2 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Soyang River Dam is the main water source for the metropolitan area. The inflow from Inbuk Stream and Naerin Stream are the main tributaries to the Soyang River Dam, and the flow rate at the confluence accounts for more than 90% of the total inflow of the Soyang River Dam [24]. The discharge of Soyang River Dam, which directly affects the water environment at the downstream, is carried out during water level control before the flood, water supply in drought season, and power generation in the dam.…”

Section: Study Areamentioning

confidence: 99%

Development and Evaluation of the Combined Machine Learning Models for the Prediction of Dam Inflow

Hong

Lee

Bae

et al. 2020

Water

View full text Add to dashboard Cite

Predicting dam inflow is necessary for effective water management. This study created machine learning algorithms to predict the amount of inflow into the Soyang River Dam in South Korea, using weather and dam inflow data for 40 years. A total of six algorithms were used, as follows: decision tree (DT), multilayer perceptron (MLP), random forest (RF), gradient boosting (GB), recurrent neural network–long short-term memory (RNN–LSTM), and convolutional neural network–LSTM (CNN–LSTM). Among these models, the multilayer perceptron model showed the best results in predicting dam inflow, with the Nash–Sutcliffe efficiency (NSE) value of 0.812, root mean squared errors (RMSE) of 77.218 m3/s, mean absolute error (MAE) of 29.034 m3/s, correlation coefficient (R) of 0.924, and determination coefficient (R2) of 0.817. However, when the amount of dam inflow is below 100 m3/s, the ensemble models (random forest and gradient boosting models) performed better than MLP for the prediction of dam inflow. Therefore, two combined machine learning (CombML) models (RF_MLP and GB_MLP) were developed for the prediction of the dam inflow using the ensemble methods (RF and GB) at precipitation below 16 mm, and the MLP at precipitation above 16 mm. The precipitation of 16 mm is the average daily precipitation at the inflow of 100 m3/s or more. The results show the accuracy verification results of NSE 0.857, RMSE 68.417 m3/s, MAE 18.063 m3/s, R 0.927, and R2 0.859 in RF_MLP, and NSE 0.829, RMSE 73.918 m3/s, MAE 18.093 m3/s, R 0.912, and R2 0.831 in GB_MLP, which infers that the combination of the models predicts the dam inflow the most accurately. CombML algorithms showed that it is possible to predict inflow through inflow learning, considering flow characteristics such as flow regimes, by combining several machine learning algorithms.

show abstract

Section: Study Areamentioning

confidence: 99%

Development and Evaluation of the Combined Machine Learning Models for the Prediction of Dam Inflow

Hong

Lee

Bae

et al. 2020

Water

View full text Add to dashboard Cite

show abstract

“…The water levels in this study were adjusted to remain within ±0.5 m of the 10-year average water level. In order to set up the boundary conditions for the CE-QUAL-W2 model, the total suspended solid concentration of the HSPF output was converted into turbidity using regression analysis of the discharge and the SS relationship (Chung et al 2011). The model results were compared with the field measured vertical profiles to calibrate and validate the vertical profiles of the TSS.…”

Section: Model Applicationmentioning

confidence: 99%

Effects of Climate Change on the Movement of Turbidity Flow in a Stratified Reservoir

Lee

Kim

Park

et al. 2015

Water Resour Manage

View full text Add to dashboard Cite

In this study, we investigated the effects of climate change on the movement of the turbidity flow in a stratified reservoir. Reservoir turbidity is primarily caused by the concentration of suspended solids in a watershed. Under the effects of climate change, which increases the frequency and intensity of extreme weather events in the Asian monsoon area, turbidity can be considered to be an essential water quality variable in a reservoir that supplies drinking water. We adopted a two-dimensional hydrodynamic water quality model coupled to a watershed model and used a future climate scenario applied to the Yongdam Reservoir in South Korea. To account for the uncertainty of climate change scenarios and the extent of the variation of both temperature and precipitation, three cases each from the 2050's and 2090's were selected for simulation. The simulations predicted that the significance of the summer stratification would produce a vertical circulation lower than 8 m in the warming reservoir of the 2090 scenario in comparison to 15 m in the 2050 scenario. The limited vertical circulation caused the density plume to spread within a depth of 8 m of the reservoir, isolating the upper water with high suspended solid concentrations from the hypolimnetic water. The results of this study provide the optimum horizontal and vertical location of the intake aqueducts to obtain drinking water with low turbidity during extremely heavy rainfall.

show abstract

Uncertainty of Discharge-SS Relationship Used for Turbid Flow Modeling

Cited by 2 publications

References 11 publications

Development and Evaluation of the Combined Machine Learning Models for the Prediction of Dam Inflow

Development and Evaluation of the Combined Machine Learning Models for the Prediction of Dam Inflow

Effects of Climate Change on the Movement of Turbidity Flow in a Stratified Reservoir

Contact Info

Product

Resources

About