Prediction techniques have the challenge of guaranteeing large horizons for chaotic time series. For instance, this paper shows that the majority of techniques can predict one step ahead with relatively low rootmeansquare error (RMSE) and Symmetric Mean Absolute Percentage Error (SMAPE). However, some techniques based on neural networks can predict more steps with similar RMSE and SMAPE values. In this manner, this work provides a summary of prediction techniques, including the type of chaotic time series, predicted steps ahead, and the prediction error. Among those techniques, the echo state network (ESN), long shortterm memory, artificial neural network and convolutional neural network are compared with similar conditions to predict up to ten steps ahead of Lorenzchaotic time series. The comparison among these prediction techniques include RMSE and SMAPE values, training and testing times, and required memory in each case. Finally, considering RMSE and SMAPE, with relatively few neurons in the reservoir, the performance comparison shows that an ESN is a good technique to predict five to fifteen steps ahead using thirty neurons and taking the lowest time for the tracking and testing cases.
Chaotic time series, Chaotic time series, Neural network, Echo state network, Long shortterm memory, RMSE, Prediction technique
Primary Language  English 

Subjects  Mathematics, Interdisciplinary Applications 
Journal Section  Research Articles 
Authors 

Early Pub Date  July 30, 2022 
Publication Date  July 30, 2022 
Published in Issue  Year 2022, Volume 4, Issue 2 