Effective models and predictability of chaotic multiscale systems via machine learning
This work addresses the challenge of predicting chaotic multiscale systems, which is important for fields like climate science and fluid dynamics, but it appears incremental as it builds on existing reservoir computing methods.
The researchers tackled the problem of building data-driven effective models for chaotic multiscale systems using machine learning, specifically reservoir computing, and found that it generates models similar to multiscale asymptotic techniques and remains effective in predictability even with reduced scale separation, with predictability further improved by hybridizing the reservoir with an imperfect model.
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.