A Hybrid CNN-LSTM Model for Predicting Solar Cycle 25
DOI:
https://doi.org/10.47611/jsrhs.v12i1.3996Keywords:
solar cycle, sunspot prediction, machine learning, convolutional neural network, long short-term memoryAbstract
The solar cycle is linked to the number of sunspots and follows the fluctuations of the Sun’s magnetic field. It can have powerful global impacts on the Earth. Thus, predicting the timing and amplitude of the peak of the incoming solar cycle 25 is of great importance. This study uses a hybrid deep learning convolutional neural network (CNN) - long short-term memory (LSTM) model and the observed 13-month smoothed sunspot numbers to predict Solar Cycle 25. Here it is shown for the first time that the MinMax normalization method substantially reduces the error of the CNN-LSTM model’s solar cycle predictions compared to the Standard Deviation normalization method. The results also suggest that it is best to use four historical solar cycles to predict the future solar cycle. The predicted Solar Cycle 25 has a 13-month smoothed peak amplitude similar to that of Solar Cycle 24. The predicted Solar Cycle 25 peak spans a relatively long period of time between approximately August 2023 and July 2024.
Downloads
References or Bibliography
Benson, B., Pan, W. D., Prasad, A., Gary, G. A., & Hu, Q. (2020). Forecasting solar cycle 25 using deep neural
networks. Solar Physics, 295(5), 1-15. https://doi.org/10.1007/s11207-020-01634-y
Brooks, N. Tensorflow Time series LSTM Tutorial. https://www.kaggle.com/code/nicapotato/keras-timeseries-multi-step-multi-output, retrieved July 2022.
Hathaway, D. H. (2015). The solar cycle. Living reviews in solar physics, 12(1), 1-87. https://doi.org/10.1007/lrsp-2015-4
Hochreiter, S., Schmidhuber, J. (1997). Long short-term memory. Neural Comput. 9(8), 1735.
https://doi.org/10.1162/neco.1997.9.8.1735
Jyothi, S. A. (2021). Solar superstorms: planning for an internet apocalypse. In Proceedings of the 2021
ACM SIGCOMM 2021 Conference (pp. 692-704). https://doi.org/10.1145/3452296.3472916
LeCun, Y., & Bengio, Y. (1995). Convolutional networks for images, speech, and time series. The handbook of
brain theory and neural networks, 3361(10), 1995. http://www.iro.umontreal.ca/~lisa/pointeurs/handbook-convo.pdf
McIntosh, S. W., Chapman, S., Leamon, R. J., Egeland, R., & Watkins, N. W. (2020). Overlapping magnetic
activity cycles and the sunspot number: forecasting sunspot cycle 25 amplitude. Solar Physics, 295(12), 1-14.
https://doi.org/10.1007/s11207-020-01723-y
Moore, T. E. (2020). The cosmic timeline of heliophysics: A declaration of significance. Perspectives of Earth and
Space Scientists, 1(1), https://doi.org/10.1029/2020CN000137
National Research Council. (2013). Solar and Space Physics: A Science for a Technological Society. Washington,
DC: The National Academies Press. https://doi.org/10.17226/13060
Prasad, A., Roy, S., Sarkar, A., Panja, S. C., & Patra, S. N. (2022). Prediction of solar cycle 25 using deep learning
based long short-term memory forecasting technique. Advances in Space Research, 69(1), 798-813.
Published
How to Cite
Issue
Section
Copyright (c) 2023 Alice Hu; Antonio Rodriguez
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright holder(s) granted JSR a perpetual, non-exclusive license to distriute & display this article.
