Improved Un-Gauged Streamflow Prediction Using Three Artificial Neural Networks Methods for Leeser Zab

Artificial neural networks have flexible structures that allow multi-input and multi-output modeling's. This is particularly important in streamflow forecasting where inflows at multiple locations are considered. Three different artificial neural networks methods which are feed forward neural networks FFNN, layered recurrent neural network LRNN and radial basis function networks RBFNN were investigated in this research to predict the un gauged Leeser Zab data north Iraq at two locations. Comparisons were made between the performance of the three methods to cope the missing data at two gauging stations for this stream. In order to accomplish this task , historical inflow series is employed for training, validation and test with different proportions, many structures of ANNs were used by selecting different combinations of inputs and using different number of neurons at the hidden layer. Also a different selections for the outputs by using single and multiple outputs were tried. The ANN prediction models has been found to be workable tool for prediction Leeser Zab stream flow correctly but the layer recurrent neural network kind and radial basis function neural networks were most suitable to reflect the behavior of the Leeser Zab flow especially the RBFNN type since the predicted flow results using this method were quite cohesive to the exact data flows. It was concluded from the experiment that lower proportion of training, validation and test ratio gives better result with higher accuracy.