Prediction of Daily Flow to the Great Zab River Using Artificial Neural Network Models

The daily flow of rivers is one of the most important components of the hydrological cycle and plays an important role in the planning and management of various water resources projects, as the process of predicting such flow is very necessary in the operation of reservoirs, planning to prevent flooding and estimating water abundance or scarcity. This study aims to use two types of neural network models to predict the daily flow to the Great Zab river basin in the Northern Iraq region for the period (2012- 2021). Two types of Artificial Neural Networks (ANNs) are investigated and evaluated for flow forecasting of river. The first one is the Feed Forward Back Propagation (FFBP), and the second is the Multi-Layer Perceptron Neural Network (MLP). Data has been analyzed by comparing the simulation outputs delivered by models with two performance indices named as (a) correlation coefficient and root mean square errors, which can be denoted by (R^2) and (RMSE) respectively. The results showed that the neural network MLP structured (3-14-7-1), able to predict the daily flows in Eski-kelek station on correlation coefficient and root mean squared-errors (0.91, 51.7), respectively.