Predicting Chaotic System Behavior using Machine Learning Techniques

TL;DR

This paper compares advanced machine learning methods, including NG-RC, RC, and LSTM, for predicting chaotic system behavior, highlighting NG-RC's superior efficiency and potential.

Contribution

It evaluates and compares the performance of NG-RC, RC, and LSTM in predicting chaotic systems, demonstrating NG-RC's advantages.

Findings

NG-RC is more computationally efficient.

NG-RC shows greater potential for chaotic prediction.

LSTM and RC are less efficient in this context.

Abstract

Recently, machine learning techniques, particularly deep learning, have demonstrated superior performance over traditional time series forecasting methods across various applications, including both single-variable and multi-variable predictions. This study aims to investigate the capability of i) Next Generation Reservoir Computing (NG-RC) ii) Reservoir Computing (RC) iii) Long short-term Memory (LSTM) for predicting chaotic system behavior, and to compare their performance in terms of accuracy, efficiency, and robustness. These methods are applied to predict time series obtained from four representative chaotic systems including Lorenz, R\"ossler, Chen, Qi systems. In conclusion, we found that NG-RC is more computationally efficient and offers greater potential for predicting chaotic system behavior.