Chaotic Analysis of Seismic Time Series and Short-Term Prediction with RBF Neural Networks

By incorporating chaotic algorithm with the RBF neural network, a chaotic analysis approach was applied to a time series composed of seismic events occurred in Guangxi nearly three decades based on the theory of phase-space reconstruction. The dynamics of the earthquakes exhibit chaotic behavior. After the chaotic analysis, short term forecasting using an RBF Neural Network has been performed, and information about the nature of the underlying system has been gathered and aided the construction of the RBF neural network. The simulation results show that the method of chaotic time series has a better the non-linear fitting and higher prediction accuracy. Preliminary results indicate that this is a promising approach.