Author(s): Chadin Chutachindakate; Tetsuya Sumi
Linked Author(s): Tetsuya Sumi
Keywords: Real time forecast; Artificial neural network; Suspended sedimentconcentration; Managawa river basin
Abstract: The sediment flow into the reservoir is a factor for decision support in real time reservoir operation therefore the serious area of sediment erosion of Managawa river basin, Japan is monitored by suspended sediment gauge. The hourly suspended sediment concentration at Okumotani station; the upstream of Managawa reservoir, was monitored and estimated by the artificial neural network (ANN) model that the input data were rainfall data and its products. This artificial neural network (ANN) was calibrated and validated by using recently suspended sediment data on heavy rainfall events from December 2006 to January 2008. Choosing an appropriate neural network structure and providing field data to that network for training purpose are address by using a constructive back propagation algorithm. Rainfall and its products; the computed discharge from rainfall runoff model and rainfall intensity, were applied as inputs to neural network. It is demonstrated that the artificial neural network (ANN) is capable of modeling the hourly suspended sediment concentration with good accuracy and the neural network model has efficiency more than the multiple linear regression (MLR) model and the sediment rating curve (SRC) model.
Year: 2009