Abstract—Chaotic time-series is a dynamic nonlinear system
whose features can not be fully reflected by Linear
Regression Model or Static Neural Network. While
Nonlinear Autoregressive with eXogenous input includes
feedback of network output, therefore, it can better reflect
the system’s dynamic feature. Take annual active times of
sunspot as an example, after verifying the chaos of sunspot
time-series and calculating the series’ embedding dimension
and delay, we establish sunspot prediction model with
NARX network. The result shows that compared with BP
Network and ARIMA Model, NARX network can better
predict the chaos.