Neural network models for river flow forecasting

In this study, back propagation neural network I BPNN ) models were used to forecast daily river flow s in two basins, namely the Da Nhim and La Nga basins, in the Central Highlands of Vietnam for comparison with the Tank Model, It was found that the developed BPNN models provided satisfactory forecast discharges for both basins, Moreover, the discharges were also forecast from indiv idual data of different stations W ithin the La Nga Basin which were input directly and separately to the considered model. In this case, however, the model took a longer time to run and the corresponding forecast discharges were not as accurate as those obtained when mean areal values of rainfall and evaporation were used instead.