Estimation of precipitation using the combined method of Support Vector Machine- Simulated Annealing algorithm (case study: Gorgan synoptic station)

Precipitation is one of the basic components of the water cycle and it is considered as one of the most important input components of the hydrological cycle. In the current research, the accuracy of the Simulated Annealing algorithm based on Support Vector Machine (SVM-SA) was evaluated in the simulation of precipitation changes. In order to verify the results, the precipitation data of the Gorgan synoptic station during the 40-years from 1971 to 2010 were used . Based on the results, using 5 non-precipitation meteorological parameters including cloud cover, maximum temperature, water vapor pressure, maximum relative humidity, and dew point, the values of RMSE, SE and R2 in the training section are equal to 6.02 mm, 0.01 and 0.999, and in the testing section 18.72 mm, 0.03 and 0.925 mm, were calculated respectively. The results showed that the SVM-SA can be highly accurate in simulating precipitation changes in the study area.