Effective models and predictability of chaotic multiscale systems via machine learning

TL;DR

This paper explores how reservoir computing can create effective models for chaotic multiscale systems, demonstrating its robustness across different scale separations and enhancing predictability through hybrid approaches.

Contribution

It shows that machine learning models can replicate multiscale asymptotic models and improve predictability by hybridizing with imperfect models, even with reduced scale separation.

Findings

Machine learning generates effective models similar to asymptotic techniques.

Predictability remains robust even with reduced scale separation.

Hybrid models improve forecast accuracy.

Abstract

We scrutinize the use of machine learning, based on reservoir computing, to build data-driven effective models of multiscale chaotic systems. We show that, for a wide scale separation, machine learning generates effective models akin to those obtained using multiscale asymptotic techniques and, remarkably, remains effective in predictability also when the scale separation is reduced. We also show that predictability can be improved by hybridizing the reservoir with an imperfect model.