Spatial Prediction of Monthly Precipitation in Sulaimani Governorate using Artificial Neural Network Models

ANN modeling is used here to predict missing monthly precipitation data in one station of the eight weather stations network Sulaimani Governorate. Eight models were developed, for each as prediction. The accuracy prediction obtain excellent with correlation coefficients between predicted and measured values ranged from (90% 97.2%). are found after many trials those highest coefficient selected. All have a hyperbolic tangent identity activation functions hidden output layers respectively, learning rate (0.4) momentum term (0.9), but different set sub-division into training, testing holdout sub-sets, number nodes layer. It that it not necessary nearest under has effect; this may be attributed high differences elevation stations. can also variance effect on obtained.