Predicting the Functional Dependence of the Sunspot Number in the Solar Activity Cycle Based on Elman Artificial Neural Network

The possibility of predicting the function of the time dependence of the sunspot number (SSN) in the solar activity cycle is analyzed based on the application of the Elman artificial neural network platform to the historical series of observational data. A method for normalizing the initial data for preliminary training of the ANN algorithm is proposed, in which a sequence of virtual idealized cycles is constructed using scaled duration coefficients and the amplitude of solar cycles. The correctness of the method is analyzed in a numerical experiment based on modeling the time series of sunspots. The intervals of changing the adaptable parameters in the ANN operation are estimated and a mathematical criterion for choosing a solution is proposed. The significant asymmetry of its ascending and descending branches is a characteristic property of the constructed functional dependence of the sunspot number cycle. A forecast of the time course for the current 25th cycle of solar activity is presented and its correctness is discussed in comparison with other forecast results and the available data of solar activity status monitoring.