Forecasting Sunspot Numbers with Recurrent Neural Networks (RNN) Using ´Sunspot Neural Forecaster´ System

This paper presents the investigations of forecasting performance of different type of Recurrent Neural Networks (RNN) in forecasting the sunspot numbers. Recurrent Neural Network will be used in this investigation by using different learning algorithms, sunspot data models and RNN transfer functions. Simulations are done using Matlab 7 where customized Graphic User Interface (GUI) called `Sunspot Neural Forecaster´ have been developed for analysis. A complete analysis for different learning algorithms, sunspot data models and RNN transfer functions are examined in terms of Mean Square Error(MSE) and correlation analysis. Finally, the best optimized RNN parameters will be used to forecast the sunspot numbers.