A LSTM based prediction model for nonlinear dynamical systems with chaotic itinerancy


The prediction for chaotic trajectory from the measured data of time history, without prior knowledge of underlying dynamical model, is a challenging task in the data-driven analysis, due to its sensitivity to initial conditions. In this paper, the Long Short-Term Memory Network (LSTM) with the merge layer is proposed to predict the future states of the coupled Morris-Lecar (M-L) system with the chaotic itinerancy responses. Here, the two LSTM models with single-branch and multi-branch are constructed respectively to carry out the predictions in the multivariate loading conditions. By comparison to the network model with single-branch, the multi-branch model with adding merge layer can provide a high utilization of weights to reduce training cost greatly and receive a low prediction error, which make the multi-layer LSTM promising to estimate a high-dimensional complex dynamical behavior like transient chaotic itinerancy.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12


  1. 1.

    Xu GUO, Feng SUN (2009) JIANG Jun, chaotic itinerancy phenomena and dynamic characteristicsin coupled neuron model. Chin Q Mech 30(04):511–516

    Google Scholar 

  2. 2.

    Hochreiter S, Schmidhuber J (1997) Long short-term mermory. Neural Comput 9(8):1735–1780

    Article  Google Scholar 

  3. 3.

    D’Acunto G (2016) A deep learning model to forecast financial time-series. University of Torino

  4. 4.

    Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw 5(2):157–166

    Article  Google Scholar 

  5. 5.

    Hinton G, Li D, Dong Y et al (2012) Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Process Mag 29(11):82–97

    Article  Google Scholar 

  6. 6.

    Gers FA, Schraudolph NN, Schmidhuber J (2002) Learning precise timing with LSTM recurrent networks. J Mach Learn Res 3(8):115–143

    MathSciNet  MATH  Google Scholar 

  7. 7.

    Dahl GE, Dong Y, Li D et al (2012) Context-dependent pre-trained deep neural networks for large vocabulary speech recognition. IEEE Trans Audio Speech Lang Process 20(1):30–42

    Article  Google Scholar 

  8. 8.

    Al-Mansouri E, Amos S (2016) Using artificial neural networks and sentiment analysis to predict upward movements in stock price. Worcester Polytechnic Institute

  9. 9.

    Han SK, Postnov DE (2003) Chaotic bursting as chaotic itiner ancy in coupled neural oscillators. Chaos 13:1105–1109

    MathSciNet  Article  Google Scholar 

  10. 10.

    Wolf A, Swift JP et al (1985) Determining Lyapunov Exponent from Time Series. Physica 16(2):284–317

    MathSciNet  Google Scholar 

  11. 11.

    Huang RS (2000) Chaos and its application. Wuhan University Press, Wuhan

    Google Scholar 

  12. 12.

    Fischer T, Krauss C (2018) Deep learning with long short-term memory networks for financial market predictions. Eur J Oper Res 270(2):654–669

    MathSciNet  Article  Google Scholar 

  13. 13.

    Goodfellow I, Bengio Y, Courville A (2016) Deep learning. The MIT Press, London

    Google Scholar 

  14. 14.

    Gulli A, Pal S (2017) Deep learning with Keras. Packt Publishing Ltd, Birmingham

    Google Scholar 

Download references


The work is supported by the National Natural Science Foundation of China under 11772243.

Author information



Corresponding author

Correspondence to Jun Jiang.

Appendix A

Appendix A

The network structure diagram built after adding the merge layer


Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Xue, Y., Jiang, J. & Hong, L. A LSTM based prediction model for nonlinear dynamical systems with chaotic itinerancy. Int. J. Dynam. Control (2020). https://doi.org/10.1007/s40435-020-00673-4

Download citation


  • Nonlinear dynamical systems
  • Chaotic itinerancy
  • Time series prediction
  • Multivariate loading conditions