Prediction of Sunspot Series Using a Recurrent Neural Network

A prediction scheme for sunspot series using a Recurrent Neural Network is proposed in this paper. The recurrent neural network adopted in this scheme is the Bilinear recurrent neural network (BRNN). Since the BRNN is based on the bilinear polynomial, BRNN has been successfully used in modeling highly nonlinear systems with time-series characteristics. Dynamic-BRNN (D-BRNN) further improves the convergence of BRNN and the D-BRNN can be a natural choice in predicting sunspot series. In order to evaluate the performance of the proposed D-BRNN-based predictor, experiments are conducted on the Wolf sunspot series number data and the resulting prediction accuracy is compared with those of conventional MultiLayer Perceptron Type Neural Network (MLPNN)-based and BRNN-based predictors. The results show that the proposed D-BRNN-based predictor outperforms the MLPNN-based and BRNN-based predictors in terms of the Normalized Mean Squared Error (NMSE).