Long-term prediction of chaotic systems with recurrent neural networks
arXiv:2004.01258
Abstract
Reservoir computing systems, a class of recurrent neural networks, have recently been exploited for model-free, data-based prediction of the state evolution of a variety of chaotic dynamical systems. The prediction horizon demonstrated has been about half dozen Lyapunov time. Is it possible to significantly extend the prediction time beyond what has been achieved so far? We articulate a scheme incorporating time-dependent but sparse data inputs into reservoir computing and demonstrate that such rare "updates" of the actual state practically enable an arbitrarily long prediction horizon for a variety of chaotic systems. A physical understanding based on the theory of temporal synchronization is developed.
arXiv comment10 pages, 8 figures
References in corpus (7)
- The World of the Complex Ginzburg-Landau Equation
- Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
- Attractor Reconstruction by Machine Learning
- Reservoir computing with a single time-delay autonomous Boolean node
- Using reservoir computers to distinguish chaotic signals
- Machine-learning inference of fluid variables from data using reservoir computing
- Network synchronization with periodic coupling