Advertisement

A Study of Upper Tropospheric Circulations over the Northern Hemisphere Prediction Using Multivariate Features by ConvLSTM

  • Ekasit PhermphoonphiphatEmail author
  • Tomohiko Tomita
  • Masayuki Numao
  • Ken-ichi Fukui
Conference paper
Part of the Proceedings in Adaptation, Learning and Optimization book series (PALO, volume 12)

Abstract

Spatiotemporal prediction on climate data is aiming to predict future spatial data by learning from prior spatial sequence data. In this paper, we are interested in a prediction of upper tropospheric circulations over the Northern Hemisphere by predicting a geopotential height at 300 hPa (Z300) variable. We proposed a predictive model by constructing an architecture with convolutional layers and deconvolutional layers and applied to convolutional long short-term memory (ConvLSTM) network. The results show that our model obtained root mean square error (RMSE) of 77.36 m (0.84% comparing to average Z300 value) in short-term prediction. While, a convolutional neural network (CNN) and a linear regression (LR) model obtained RMSE of 109.35 (1.19%) and 153.61 (1.67%), respectively. The ConvLSTM maintains RMSE even in long-term prediction. Furthermore, the prediction features’ investigation result shows that temperature at 300 hPa (T300) and self prior Z300 features are important for Z300 prediction.

Keywords

Upper tropospheric circulations Spatial correlation ConvLSTM 

Notes

Acknowledgment

This work was supported in part by the Network Joint Research Center for Materials and Devices and by JSPS KAKENHI Grant Number 19K22876.

References

  1. 1.
    Chen, P., Niu, A., Liu, D., Jiang, W., Ma, B.: Time series forecasting of temperatures using SARIMA: an example from Nanjing. In: IOP Conference Series: Materials Science and Engineering (2018)Google Scholar
  2. 2.
    Giffard-Roisin, S., Yang, M., Charpiat, G., Ke\(^{\prime }\)gl, B., Monteleoni, C.: Fused deep learning for hurricane track forecast from reanalysis data. In: Proceedings of International Workshop on Climate Informatics, pp. 69–72 (2018)Google Scholar
  3. 3.
    Graves, A.: Generating sequences with recurrent neural networks. arXiv:1308.0850 (2013)
  4. 4.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  5. 5.
    Hong, S., Kim, S., Joh, M., Kwang Song, S.: GlobeNet: convolutional neural networks for typhoon eye tracking from remote sensing imagery. In: Proceedings of International Workshop on Climate Informatics, pp. 69–72 (2017)Google Scholar
  6. 6.
    Kim, S., Hong, S., Joh, M., Kwang Song, S.: DeepRain: ConvLSTM network for precipitation prediction using multichannel radar data. In: Proceedings of International Workshop on Climate Informatics, pp. 89–92 (2017)Google Scholar
  7. 7.
    Kim, S., Yoon, S., Lee, J., Kahou, S., Kim, H., Kashinath, K., Prabhat, M.: Deep-Hurricane-Tracker: tracking extreme climate events. In: Proceedings of International Workshop on Climate Informatics, pp. 16–18 (2018)Google Scholar
  8. 8.
    Kolstad, E.W., Breiteiga, T., Scaife, A.A.: The association between stratospheric weak polar vortex events and cold air outbreaks in the northern hemisphere. Q. J. R. Meteorol. Soc. 136, 886–893 (2010)CrossRefGoogle Scholar
  9. 9.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
  10. 10.
    Linkin, M.E., Nigam, S.: The North Pacific oscillation-West Pacific teleconnection pattern: mature-phase structure and winter impacts. J. Clim. 21, 1979–1997 (2008)CrossRefGoogle Scholar
  11. 11.
    Papacharalampous, G.A., Tyralis, H., Koutsoyiannis, D.: Predictability of monthly temperature and precipitation using automatic time series forecasting methods. Acta Geophysica 66(4), 807–831 (2018)CrossRefGoogle Scholar
  12. 12.
    Qing, C., Xiaoli, Z., Kun, Z.: Research on precipitation prediction based on time series model. In: Computer Distributed Control and Intelligent Environmental Monitoring, pp. 568–571 (2012)Google Scholar
  13. 13.
    Rao, J., Ren, R., Chen, H., Yu, Y., Zhou, Y.: The stratospheric sudden warming event in February 2018 and its prediction by a climate system model. J. Geophys. Res. Atmos. 123, 332–345 (2018)Google Scholar
  14. 14.
    Shi, X., Chen, Z., Wang, H., Yeung, D.Y.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. Neural Inf. Process. Syst. 1, 802–810 (2015)Google Scholar
  15. 15.
    Thompson, D.W.J., Wallace, J.M.: The arctic oscillation signature in the wintertime geopotential height and temperature fields. Geophys. Res. Lett. 25, 1297–1300 (1998)CrossRefGoogle Scholar
  16. 16.
    Tomassini, L., Gerber, E.P., Baldwin, M.P., Bunzel, F., Giorgetta, M.: The role of stratosphere-troposphere coupling in the occurrence of extreme winter cold spells over northern europe. J. Adv. Model. Earth Syst. 4, 1–14 (2012)CrossRefGoogle Scholar
  17. 17.
    Tomita, T., Yamaura, T.: A precursor of the monthly-mean large-scale atmospheric circulation anomalies over the North Pacific. SOLA 13, 85–89 (2017)CrossRefGoogle Scholar
  18. 18.
    Wang, Y., Gao, Z., Long, M., Wang, J., Yu, P.S.: PredRNN++: towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning. In: Proceedings of International Conference on Machine Learning, pp. 5123–5132 (2018)Google Scholar
  19. 19.
    Wang, Y., Long, M., Wang, J., Gao, Z., Yu, P.S.: PredRNN: recurrent neural networks for predictive learning using spatiotemporal LSTMs. In: Neural Information Processing Systems, pp. 879–888 (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Ekasit Phermphoonphiphat
    • 1
    Email author
  • Tomohiko Tomita
    • 2
  • Masayuki Numao
    • 3
  • Ken-ichi Fukui
    • 3
  1. 1.Graduate School of Information Science and TechnologyOsaka UniversitySuitaJapan
  2. 2.Faculty of Advanced Science and TechnologyKumamoto UniversityKumamotoJapan
  3. 3.The Institute of Scientific and Industrial ResearchOsaka UniversitySuitaJapan

Personalised recommendations