Key points are not available for this paper at this time.
Physical, mathematical models and statistical distribution are applied to forecasting, whereas in natural resources, it is difficult to choose models that are closed to reality. Rainfall forecasting as an important dynamic process is ever favored by the researchers. Analyzing the behavior of these phenomena by intelligent systems is completely better than classical methods, because of high non-linear dynamic atmospheric phenomena. In this paper, a long term forecasting method is presented by a combination of intelligent methods with the use of the past month rainfall in karoon basin and global meteorological signals such as southern oscillation index (SOI), north athletics oscillation (NAO), sea level pressure (SLP), sea surface temperature (SST) and 41 years historical data. This method is obtained by the combination of artificial neural network, fuzzy logic and wavelet functions. In this model, several scenarios have been examined for the karoon basin of Iran, through the signals. SST and NAO signals show the best results, and then, the long-term forecasts are done for periods of six months, one year and two years. The results of the integrated model showed superior results when compared to the two-year forecasts to predict the six-month and annual periods. As a result of the root mean squared error, predicting the two-year and annual periods is 6.22 and 7.11, respectively. However, the predicted six months shows 13.15. Key words: Intelligent networks, long-term prediction, meteorological signals, artificial neural network, fuzzy logic, wavelet function.
Afshin et al. (Thu,) studied this question.