Solar cycle prediction using a combinatorial deep learning model

Abstract

The long-term prediction of the solar cycle is of great significance for aerospace, communication, and space missions. For a long time, many studies have used relatively primitive deep learning methods to predict the solar cycle, and most of them do not perform well in the long-term prediction. In this paper, we proposed XG-SN ensemble model. The model used extreme gradient boosting (XGBoost) ensemble learning method, combined with sample convolution and interaction net (SCINet), and neural basis expansion analysis for the interpretable time series (N-BEATS) to make predictions for known solar cycles. 13 months of smoothed monthly total sunspot numbers were selected as the data set. The model performance was e v aluated by mean absolute error (MAE), root-mean-square error (RMSE), and mean absolute time lag (MATL) between the predicted and actual values. The first two e v aluation metrics measured the prediction deviation from the numerical dimension, and the last one measured the prediction deviation from the temporal dimension. The results show that the model achieves the MAE, RMSE, and MATL values of 13.19, 17.13, and 0.08, respectively, in Solar Cycle 13 to 24. Our model is able to better predict in most cycles, ensuring accurate prediction of peaks with little time lag.