compare intelligent models to estimate monthly precipitation kakareza basian

precipitation is considered as one of the most important factures in water cycle. prediction of monthly precipitation is important for many purposes such as estimating torrent, drought, run-off, sediment, irrigation programming and also management of drainage basins.in this study we studied and evaluated gene expression programming to predict the precipitation of the kakareza river (in lorestan), and the results were compared with results of anfis and artificial neural network model. for this purpose, mean temperature, relative humidity, evaporation, wind speed rate at monthly scale during the period (2005-2015) as input and output parameters were selected as precipitation . the criteria of correlation coefficient, root mean square error and of mean absolute error were used to evaluate and performance compare of models. the results showed that gene expression programming model has the highest correlation coefficient (0.978), the lowest root mean square error (0.026 mm) and the lowest mean absolute error (0.017mm) became a priority in the validation phase. the results showed that the gene expression programming model to estimate high minimum and maximum values of precipitation .