Stochastic approach for assessing the predictability of chaotic time series using reservoir computing

TL;DR

This paper introduces a stochastic method to generate training data and evaluate the predictability of chaotic systems, specifically analyzing the effectiveness and limitations of reservoir computing in this context.

Contribution

It proposes a novel stochastic approach for assessing chaotic time series predictability and critically evaluates reservoir computing's capabilities and limitations for chaotic system modeling.

Findings

Stochastic approach effectively characterizes chaotic data predictability.

Reservoir computing shows limitations in surrogate modeling of chaotic systems.

Analysis applied to Lorenz and Anishchenko-Astakhov systems.

Abstract

The applicability of machine learning for predicting chaotic dynamics relies heavily upon the data used in the training stage. Chaotic time series obtained by numerically solving ordinary differential equations embed a complicated noise of the applied numerical scheme. Such a dependence of the solution on the numeric scheme leads to an inadequate representation of the real chaotic system. A stochastic approach for generating training times series and characterising their predictability is suggested to address this problem. The approach is applied for analysing two chaotic systems with known properties, Lorenz system and Anishchenko-Astakhov generator. Additionally, the approach is extended to critically assess a reservoir computing model used for chaotic time series prediction. Limitations of reservoir computing for surrogate modelling of chaotic systems are highlighted.