The daily inflow has one of apparent nonlinear and complicated phenomena. The nonlinearity and co... more The daily inflow has one of apparent nonlinear and complicated phenomena. The nonlinearity and complexity make it difficult to model the prediction of daily flow, but attractive to try the neural networks approach which contains inherently nonlinear scheme. The study focuses on developing the forecasting models of daily inflows to a large dam site using neural networks. In order to reduce the error caused by high or low outliers, the Back propagation algorithm which is one of neural network structures is modified by combining the regression algorithm. The study indicates that continuous forecasting of a reservoir inflow in real time is possible through the use of modified neural network models. The positive effect of the modification using regression scheme in BP algorithm is showed in the low and high inflows.
Critical Transitions in Water and Environmental Resources Management, 2004
The purpose of this study is to develop a real-time flood forecasting model in order to predict t... more The purpose of this study is to develop a real-time flood forecasting model in order to predict the flood runoff having nature of non-linearity and to verify applicability of neural network model for large river basin. Developed model in this study, NRDFM (Neural River Discharge-stage Forecasting Model) was applied to predict the flood discharge on Waekwan station in Nakdong river of Korea. As a result of flood forecasting on Waekwan, it can be concluded that NRDFM- II is the best predictive model for real-time operation. In addition, the forecasting results of NRDFM- I and NRDFM-III show sufficient probability for real-time forecasting. Consequently, it is expected that NRDFM will be available in real-time flood warning system.
The daily inflow has one of apparent nonlinear and complicated phenomena. The nonlinearity and co... more The daily inflow has one of apparent nonlinear and complicated phenomena. The nonlinearity and complexity make it difficult to model the prediction of daily flow, but attractive to try the neural networks approach which contains inherently nonlinear scheme. The study focuses on developing the forecasting models of daily inflows to a large dam site using neural networks. In order to reduce the error caused by high or low outliers, the Back propagation algorithm which is one of neural network structures is modified by combining the regression algorithm. The study indicates that continuous forecasting of a reservoir inflow in real time is possible through the use of modified neural network models. The positive effect of the modification using regression scheme in BP algorithm is showed in the low and high inflows.
Critical Transitions in Water and Environmental Resources Management, 2004
The purpose of this study is to develop a real-time flood forecasting model in order to predict t... more The purpose of this study is to develop a real-time flood forecasting model in order to predict the flood runoff having nature of non-linearity and to verify applicability of neural network model for large river basin. Developed model in this study, NRDFM (Neural River Discharge-stage Forecasting Model) was applied to predict the flood discharge on Waekwan station in Nakdong river of Korea. As a result of flood forecasting on Waekwan, it can be concluded that NRDFM- II is the best predictive model for real-time operation. In addition, the forecasting results of NRDFM- I and NRDFM-III show sufficient probability for real-time forecasting. Consequently, it is expected that NRDFM will be available in real-time flood warning system.
Uploads
Papers by Hyun-Suk SHIN