Comparative Review of Machine Learning Models for Sunspot Number Prediction

Authors

  • Meenu Mohil Associate Professor, Department of Physics, Acharya Narendra Dev College, University of Delhi, Delhi, India
  • Preeti Marwaha Associate Professor, Department of Computer Science, Acharya Narendra Dev College, University of Delhi, Delhi, India
  • Manju Bhardwaj Associate Professor, Department of Computer Science, Maitreyi College, University of Delhi, Delhi, India

DOI:

https://doi.org/10.14738/tmlai.1401.19923

Keywords:

Sunspot numbers, Machine Learning, RNN, LSTM, GRU, Neural Networks

Abstract

Accurate prediction of sunspot numbers is essential for understanding solar activity and mitigating the adverse effects of space weather on technological infrastructure. With the limitations of traditional statistical methods, recent years have witnessed a surge in the application of machine learning (ML) models, particularly deep learning architectures, to sunspot time series forecasting. This review presents a comprehensive comparative analysis of major ML models utilised in the prediction of sunspot numbers, focusing on recurrent neural networks (RNN), long short-term memory (LSTM) networks, gated recurrent unit (GRU) models, and hybrid neural network approaches. The article synthesises findings from state-of-the-art literature, summarising the methodological advances, dataset preparation strategies, and evaluation metrics commonly employed in this field. A critical assessment of model performance, based on accuracy, robustness, and operational feasibility, highlights the superior capabilities of LSTM and GRU architectures for long-term and multi-step forecasting tasks. By systematically evaluating methodological advancements and benchmarking results from recent studies, this article highlights the strengths, limitations, and emerging trends in solar forecasting approaches, aiming to guide future research toward robust, interpretable, and operationally feasible sunspot prediction.

References

Hathaway DH. The solar cycle. Living Rev Solar Phys. 2015;12(1):4. doi:10.1007/lrsp-2015-4

Usoskin IG. A history of solar activity over millennia. Living Rev Solar Phys. 2017;14(1):3.

Petrovay K. Solar cycle prediction. Living Rev Solar Phys. 2020;17(1):2.

Xiao Z. A review of machine learning methods applied in sunspot prediction. In: 2021 International Conference on Networking, Communications and Information Technology (NetCIT); 2021; Manchester, UK. p. 158–161. doi:10.1109/NetCIT54147.2021.00039

Paraskakis N, Hristopulos DT. Prediction of yearly mean sunspot number using machine learning methods. Stoch Environ Res Risk Assess. 2025;39:3405–3432. doi:10.1007/s00477-025-03024-x

Wang QJ, Li JC, Guo LQ. Solar cycle prediction using an extended short-term memory deep learning model. Res Astron Astrophys. 2021;21(1):012. Scholar Publishing

Yunita A, et al. Performance analysis of neural network architectures: RNN, LSTM, GRU, hybrids. MethodsX. 2025;12:102345. Available from: https://pubmed.ncbi.nlm.nih.gov/40777584/

Cui, Z., Ding, Z., Xu, J. et al. Probabilistic sunspot predictions with a gated recurrent unitsbased combined model guided by pinball loss. Sci Rep 14, 13601 (2024). https://doi.org/10.1038/s41598-024-63878-z

Moustafa SSR, Khodairy SS. Comparison of different predictive models and their effectiveness in sunspot number prediction. Phys Scr. 2023;98:045022. doi:10.1088/1402-4896/acc21a

Xu S, Liang B, Feng S, Cai Y, Dai W, Yang Y. Solar cycle prediction using a combinatorial deep learning model. Mon Not R Astron Soc. 2023;527(3):5675. doi:10.1093/mnras/stad3451

Kumar A, Kumar V. Forecast of Solar Cycle 25 based on hybrid CNN-bidirectional-GRU (CNN-BiGRU) model and novel Gradient Residual Correction (GRC) technique. Adv Space Res. 2024;73(8):4342

Mohil M, Singh S, Jha R. Hybrid LSTM-GRU model for predicting solar activity and geomagnetic indices. Astrophys Space Sci. 2025;370:118. doi:10.1007/s10509-025-04510-y

Li G, Ma X, Yang H. A hybrid model for forecasting sunspots time series based on variational mode decomposition and backpropagation neural network improved by firefly algorithm. Comput Intell Neurosci. 2018;2018:3713410.

Yang H, et al. Forecasting long-term sunspot numbers using LSTM-WGAN. Front Astron Space Sci. 2025;12:1541299

Dang Y, Chen Z, Li H, Shu H. A comparative study of non-deep learning, deep learning, and ensemble learning methods for sunspot number prediction. Appl Artif Intell. 2022;36(1). doi:10.1080/08839514.2022.2074129

Kumar A, Kumar V. Hybrid-ensemble deep-learning models to enhance the sunspot prediction and forecasting of Solar Cycle 26. Sol Phys. 2025;300:100. doi:10.1007/s11207-025-02510-3

Downloads

Published

2026-01-31

How to Cite

Mohil, M., Marwaha, P., & Bhardwaj, M. (2026). Comparative Review of Machine Learning Models for Sunspot Number Prediction. Transactions on Engineering and Computing Sciences, 14(01), 130–137. https://doi.org/10.14738/tmlai.1401.19923