Predicting Sunspot Numbers Based on Inverse Number and Intelligent Fixed Point.

This article proposes a new model for predicting sunspot activity based on the inverse number and intelligent fixed point. Firstly, in the training phase, the optimal parameters of the model are selected by the inverse-number formula and intelligent fixed-point algorithm. Secondly, in the validation phase, the model is verified by the data. Finally, the model is applied to the prediction of monthly mean sunspot number (MSN). The model's predictions are compared with those of autoregressive models (AR) and the National Oceanic and Atmospheric Administration (NOAA) predictions. The results show that the prediction accuracy of the proposed method is higher than that of previous methods. The method is then used to predict the 13-month smoothed monthly total sunspot number (MSSN13), and a higher prediction accuracy is obtained. The model proposed in this article is theoretically complete and robust. [ABSTRACT FROM AUTHOR]