Forecasting Solar Cycle 25 using Deep Neural Networks

TL;DR

This paper employs advanced deep neural networks, specifically WaveNet and LSTM, to forecast Solar Cycle 25's sunspot activity, demonstrating improved trend capturing and dependency learning over other models.

Contribution

The study introduces a novel combination of WaveNet and LSTM neural networks for solar cycle forecasting, outperforming other models in capturing long-term dependencies.

Findings

Forecasts Solar Cycle 25 with a maximum sunspot number around 106.

Predicts maximum total sunspot area around 1771.

Indicates Solar Cycle 25 will be slightly weaker than Cycle 24.

Abstract

With recent advances in the field of machine learning, the use of deep neural networks for time series forecasting has become more prevalent. The quasi-periodic nature of the solar cycle makes it a good candidate for applying time series forecasting methods. We employ a combination of WaveNet and LSTM neural networks to forecast the sunspot number using the years 1749 to 2019 and total sunspot area using the years 1874 to 2019 time series data for the upcoming Solar Cycle 25. Three other models involving the use of LSTMs and 1D ConvNets are also compared with our best model. Our analysis shows that the WaveNet and LSTM model is able to better capture the overall trend and learn the inherent long and short term dependencies in time series data. Using this method we forecast 11 years of monthly averaged data for Solar Cycle 25. Our forecasts show that the upcoming Solar Cycle 25 will have a maximum sunspot number around 106 $\pm$ 19.75 and maximum total sunspot area around 1771 $\pm$ 381.17. This indicates that the cycle would be slightly weaker than Solar Cycle 24.