Solar Physics

, 294:50 | Cite as

Forecasting Sunspot Time Series Using Deep Learning Methods

  • Zeydin Pala
  • Ramazan AticiEmail author


To predict Solar Cycle 25, we used the values of sunspot number (SSN), which have been measured regularly from 1749 to the present. In this study, we converted the SSN dataset, which consists of SSNs between 1749 – 2018, into a time series, and made the ten-year forecast with the help of deep-learning (DL) algorithms. Our results show that algorithms such as long-short-term memory (LSTM) and neural network autoregression (NNAR), which are DL algorithms, perform better than many algorithms such as ARIMA, Naive, Seasonal Naive, Mean and Drift, which are expressed as classical algorithms in a large time-series estimation process. Using the R programming language, it was also predicted that the maximum amplitude of Solar Cycle (SC) 25 will be reached between 2022 and 2023.


Sunspot number Statistics Solar cycle 


Disclosure of Potential Conflicts of Interest

The authors declare that they have no conflicts of interest.


  1. Adhikari, R., Agrawal, R.K.: 2013, arXiv.
  2. Aguirre, L.A., Letellier, C., Maquet, J.: 2008, Solar Phys. 249, 103. DOI. ADSCrossRefGoogle Scholar
  3. Atici, R.: 2018, Astrophys. Space Sci. 363, 231. DOI. ADSCrossRefGoogle Scholar
  4. Attia, A.-F., Ismail, H.A., Basurah, H.M.: 2013, Astrophys. Space Sci. 344, 5. DOI. ADSCrossRefGoogle Scholar
  5. Chattopadhyay, G., Chattopadhyay, S.: 2012, Eur. Phys. J. Plus 127, 43. DOI. CrossRefGoogle Scholar
  6. Dikpati, M., De Toma, G., Gilman, P.A.: 2006, Geophys. Res. Lett. 33, L05102. DOI. ADSCrossRefGoogle Scholar
  7. Gkana, A., Zachilas, L.: 2015, J. Eng. Sci. Technol. Rev. 8, 79. CrossRefGoogle Scholar
  8. Hiremath, K.: 2008, Astrophys. Space Sci. 314, 45. DOI. ADSCrossRefGoogle Scholar
  9. Javaraiah, J.: 2008, Solar Phys. 252, 419. DOI. ADSCrossRefGoogle Scholar
  10. Kane, R.: 2007, Solar Phys. 246, 487. DOI. ADSCrossRefGoogle Scholar
  11. Kilcik, A., Anderson, C., Rozelot, J., Ye, H., Sugihara, G., Ozguc, A.: 2009, Astrophys. J. 693, 1173. DOI. ADSCrossRefGoogle Scholar
  12. Kim, K.B., Kim, J.H., Chang, H.Y.: 2018, J. Astron. Space Sci. 35, 151. ADSGoogle Scholar
  13. Layden, A., Fox, P., Howard, J., Sarajedini, A., Schatten, K., Sofia, S.: 1991, Solar Phys. 132, 1. DOI. ADSCrossRefGoogle Scholar
  14. Lewis, N.D.: 2016, Deep Time Series Forecasting with Python: An Intuitive Introduction to Deep Learning for Applied Time Series Modeling, Create Space Independent Publishing Platform, New York. Google Scholar
  15. Li, K., Feng, W., Li, F.: 2015, J. Atmos. Solar-Terr. Phys. 135, 72. DOI. ADSCrossRefGoogle Scholar
  16. Maleki, A., Nasseri, S., Aminabad, M.S., Hadi, M.: 2018, KSCE J. Civ. Eng. 22, 3233. DOI. CrossRefGoogle Scholar
  17. Nielsen, M.L., Kjeldsen, H.: 2011, Solar Phys. 270, 385. DOI. ADSCrossRefGoogle Scholar
  18. Okoh, D., Seemala, G., Rabiu, A., Uwamahoro, J., Habarulema, J., Aggarwal, M.: 2018, Space Weather 16, 1424. DOI. ADSCrossRefGoogle Scholar
  19. Penn, M.J., Livingston, W.: 2011, In: Choudhary, D.P., Strassmeier, K.G. (eds.) The Physics of Sun and Star Spots, IAU Symp. 273, 126. Google Scholar
  20. Pesnell, W.D.: 2008, Solar Phys. 252, 209. DOI. ADSCrossRefGoogle Scholar
  21. Petrovay, K.: 2010, Living Rev. Solar Phys. 7, 6. DOI. ADSCrossRefGoogle Scholar
  22. Pishkalo, M.: 2008, Kinemat. Phys. Celest. Bodies 24, 242. DOI. ADSCrossRefGoogle Scholar
  23. Pishkalo, M.: 2014, Solar Phys. 289, 1815. DOI. ADSCrossRefGoogle Scholar
  24. Quassim, M.S., Attia, A.-F., Elminir, H.K.: 2007, Solar Phys. 243, 253. DOI. ADSCrossRefGoogle Scholar
  25. Raissi, M., Karniadakis, G.E.: 2018, J. Comput. Phys. 357, 125. DOI. ADSMathSciNetCrossRefGoogle Scholar
  26. Rigozo, N., Echer, M.S., Evangelista, H., Nordemann, D., Echer, E.: 2011, J. Atmos. Solar-Terr. Phys. 73, 1294. DOI. ADSCrossRefGoogle Scholar
  27. Sabarinath, A., Anilkumar, A.: 2018, J. Earth Syst. Sci. 127, 84. DOI. ADSCrossRefGoogle Scholar
  28. Sagir, S., Atici, R., Ozcan, O.: 2018, Pramāna 91, 54. DOI. ADSCrossRefGoogle Scholar
  29. Sagir, S., Yesil, A.: 2018, Wirel. Pers. Commun. 102, 31. DOI. CrossRefGoogle Scholar
  30. Sagir, S., Karatay, S., Atici, R., Yesil, A., Ozcan, O.: 2015, Adv. Space Res. 55, 106. DOI. ADSCrossRefGoogle Scholar
  31. Sarp, V., Kilcik, A., Yurchyshyn, V., Rozelot, J., Ozguc, A.: 2018, Mon. Not. Roy. Astron. Soc. 481, 2981. DOI. ADSCrossRefGoogle Scholar
  32. Sena, D., Nagwani, N.K.: 2016, J. Eng. Appl. Sci. 11, 13123. Google Scholar
  33. Shaikh, Y.H., Khan, A., Iqbal, M., Behere, S., Bagare, S.: 2008, Fractals 16, 259. DOI. MathSciNetCrossRefGoogle Scholar
  34. Shumway, R.H., Stoffer, D.S.: 2011, Time Series Analysis and Its Applications: With R Examples, Springer, Berlin, 47. CrossRefGoogle Scholar
  35. Siami-Namini, S., Namin, A.S.: 2018, arXiv.
  36. Sirignano, J., Spiliopoulos, K.: 2018, J. Comput. Phys. 375, 1339. DOI. ADSMathSciNetCrossRefGoogle Scholar
  37. Thompson, R.: 1993, Solar Phys. 148, 383. DOI. ADSCrossRefGoogle Scholar
  38. Zazo, R., Lozano-Diez, A., Gonzalez-Dominguez, J., Toledano, D.T., Gonzalez-Rodriguez, J.: 2016, PLoS ONE 11, e0146917. DOI. CrossRefGoogle Scholar

Copyright information

© Springer Nature B.V. 2019

Authors and Affiliations

  1. 1.Department of Computer Engineering, Faculty of EngineeringMus Alparslan UniversityMuşTurkey
  2. 2.Faculty of EducationMus Alparslan UniversityMuşTurkey

Personalised recommendations