Analysis on the Occurrence of Tropical Cyclone in the South Pacific Region Using Recurrent Neural Network with LSTM

  • Adarsh Karan Sharma
  • Vishal Prasad
  • Roneel Kumar
  • Anuraganand SharmaEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11301)


Weather prediction over the years has been a challenge for the meteorological centers in the South Pacific region. This paper presents Recurrent Neural Network (RNN) Architecture with Long Short Term Memory (LSTM) times-series weather data for prediction. From the gathered dataset, the Sea Surface Temperature (SST) is studied since it is known to be the foundation of the cyclone formation. This paper focuses on two scenarios. The first part is predicting upcoming SST using dataset from January 2013 to December 2017. The second part is taking out data of two different cyclones and predicting the SST for the next 14 days. Once the SST prediction is made, the predicted SST is compared with SST in the dataset for those 14 days. The main aim of this paper is to predict the SST using RNN and LSTM to anticipate the occurrence of tropical cyclones. The paper will focus on the reason for this study, a discussion of the model used, how the cyclones are formed, regarding the current threshold, the analysis of the dataset and lastly, the results from the experiment carried out.


Time series data Recurrent neural network Long short-term memory Artificial neural networks Deep learning Sea surface temperature Weather prediction 


  1. 1.
    Brownlee, J.: Time Series Prediction with LSTM Recurrent Neural Networks in Python with Keras. Accessed 01 May 2018
  2. 2.
    Raymond, D., Sessions, S., Carillo, C.: Thermodynamics of tropical cyclogenesis in the northwest Pacific. J. Geophys. Res. 116(1), 1–18 (2011)Google Scholar
  3. 3.
    Dare, R., McBride, J.: The threshold sea surface temperature condition for tropical cyclogenesis. J. Clim. 24(1), 4570–4576 (2011)CrossRefGoogle Scholar
  4. 4.
    Zaytar, M., Amrani, C.: Sequence to sequence weather forecasting with long short-term memory recurrent neural networks. Int. J. Comput. Appl. 143(11), 1–5 (2016)Google Scholar
  5. 5.
    Bell, I., Wilson, J.: Visualising the atmosphere in motion. In: Bureau of Meteorology Training Centre, Melbourne, pp. 1–4 (1995)Google Scholar
  6. 6.
    Patil, K., Deo, M., Ravichandran, M.: Prediction of sea surface temperature by combining numerical and neural techniques. J. Atmos. Ocean. Technol. 33(1), 1715–1726 (2016)CrossRefGoogle Scholar
  7. 7.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  8. 8.
    Hochreiter, S.: The vanishing gradient problem during learning recurrent neural nets and problem solutions. Int. J. Uncertain. Fuzziness Knowl.-Based Syst. 6(2), 1047–1116 (1998)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: 13th International Conference on Artificial Intelligence and Statistics, Italy, pp. 249–256 (2010)Google Scholar
  10. 10.
    Tory, K., Dare, R.: Sea surface temperature thresholds for tropical cyclone formation. Centre for Australian Weather and Climate Research, Melbourne, pp. 8171–8183 (2015)CrossRefGoogle Scholar
  11. 11.
    Arora, K., Dash, P.: Towards dependence of tropical cyclone intensity on sea surface temperature and its response in a warming world. Climate 4(30), 1–19 (2016)Google Scholar
  12. 12.
    Palmén, E.H.: On the formation and structure of tropical cyclones. Geophysica 3(1), 26–38 (1948)Google Scholar
  13. 13.
    Gray, W.M.: Global view of the origin of tropical disturbances and storms. Mon. Weather Rev. 96(10), 669–700 (1968)CrossRefGoogle Scholar
  14. 14.
    Montgomery, M.T.: Recent advances in tropical cyclogenesis. In: Mohanty, U.C., Gopalakrishnan, S.G. (eds.) Advanced Numerical Modeling and Data Assimilation Techniques for Tropical Cyclone Prediction, pp. 561–587. Springer, Dordrecht (2016). Scholar
  15. 15.
    ScienceDaile Homepage. Accessed 01 May 2018
  16. 16.
    Morrison, S.: Climate Change Opens the Door to More Intense Tropical Storms. Accessed 02 May 2018
  17. 17.
    Lian, X., Chan, J.: The effects of the full coriolis force on the structure and motion of a tropical cyclone. Part I: effects due to vertical motion. J. Atmos. Sci. 62(1), 3825–3830 (2005)CrossRefGoogle Scholar
  18. 18.
    Australian Government – Bureau of Meteorology. Accessed 15 Apr 2018
  19. 19.
    Michaels, P., Knappenberger, P., Davis, R.: Sea-surface temperatures and tropical cyclones in the Atlantic basin. Geophys. Res. Lett. 3(1), 1–4 (2006)Google Scholar
  20. 20.
    Landsea, C.: Climate Variability of Tropical Cyclones: Past, Present and Future. Accessed 10 May 2018
  21. 21.
    Ekwurzel, B.: Hurricane Watch Checklist: Four Factors that Strengthen Tropical Cyclones, Union of Concerned Scientists. Accessed 12 May 2018
  22. 22.
    Lipton, Z., Berkowitz, J., Elkan, C.: A Critical Review of Recurrent Neural Networks for Sequence Learning. arXiv preprint arXiv:1506.00019, pp. 1–38 (2015)
  23. 23.
    Zhang, Q., Wang, H., Dong, J., Zhong, G.: Prediction of sea surface temperature using long short-term memory. IEEE Geosci. Remote Sens. Lett. 14(10), 1745–1749 (2017)CrossRefGoogle Scholar
  24. 24.
    Gandhi, A., D’souza, S., Arjun, N.: Prediction of sea surface temperature using artificial neural network. Int. J. Remote. Sens. 39(12), 4214–4231 (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Adarsh Karan Sharma
    • 1
  • Vishal Prasad
    • 1
  • Roneel Kumar
    • 1
  • Anuraganand Sharma
    • 1
    Email author
  1. 1.The University of the South PacificSuvaFiji

Personalised recommendations