Back propagation neural networks in river flow forecasting

Back Propagation Neural Networks have been widely and successfully used for forecasting in various fields, especially in stock market prices. In this study, they were used to forecast daily river flows in two basins, namely the Da Nhim and La Nga basins, in Vietnam. It was found that the Back Propagation Network Models provided satisfactory forecast discharges for both basins. Moreover, the discharges were also forecast from data of different stations within the La Nga Basin input directly and separatedly to the model. In this case, however, the model took longer time to run and the correspondent forecast discharges were not as accurate as when those obtained with mean value data.