Solar Activity Forecasting by Incorporating Prior Knowledge from Nonlinear Dynamics into Neural Networks

This paper presents an efficient approach for the prediction of sunspot-related time series commonly used for monitoring solar activity, namely the Yearly Sunspot Number and the R12 Index. The method consists in matching a "de-rectification" procedure of sunspot data with the use of nonlinear dynamics tools in order to design neural network based predictors with close-to-optimal performance. In fact, whereas the "de-rectification" process allows to obtain time series that can be modeled by neural structures much better than the original datasets, the incorporation of the prior knowledge extracted by using nonlinear dynamics into neural networks generates models able to fully capture the chaotic dynamics of solar activity. The proposed approach produces prediction results that outperform the most accurate methods existing in literature both for short and medium-term forecasting horizons.