Forecasting Yazd precipitation with Artificial Neural Networks

Precipitations consider as an important factor in hydrologic systems that it is necessary to study and calculate for runoff, drought, under ground water and sediment.Forecasting precipitation is most important in estimating of runoff, drought, catchments management, agriculture and etc. The aim of this article is forecasting precipitation with artificial neural networks in Yazd for a time period of 53 years. Artificial neural networks used as a nonlinear method for forecasting precipitation. The Results of this study after network testing with different hidden layer and training coefficient indicated that using of Artificial neural network with 4 hidden layer Perceptron, 0/1 training coefficient and 0/7 momentum has presentation comparatively a better model. So after testing again network and training with different hidden layer and training coefficient in combination with genetic algorithm indicated that combination of network with mentioned characters with genetic algorithm increase the error and increase speed of calculation and present a better model. It is necessary to be mentioned that data randomize and combination neural networks with algorithm genetic result in increase accuracy and model to be better.