Learning Spatiotemporal Chaos Using Next-Generation Reservoir Computing

Abstract

Forecasting the behavior of high-dimensional dynamical systems using machine learning requires efficient methods to learn the underlying physical model. We demonstrate spatiotemporal chaos prediction using a machine learning architecture that, when combined with a next-generation reservoir computer, displays state-of-the-art performance with a computational time $10^3-10^4$ times faster for training process and training data set $\sim 10^2$ times smaller than other machine learning algorithms. We also take advantage of the translational symmetry of the model to further reduce the computational cost and training data, each by a factor of $\sim$10.

11 pages, 10 figures

References in corpus (9)

• Next Generation Reservoir Computing
• On Explaining the Surprising Success of Reservoir Computing Forecaster of Chaos? The Universal Machine Learning Dynamical System with Contrasts to VAR and DMD
• Lattice gauge equivariant convolutional neural networks
• Machine-learning hidden symmetries
• Breaking Symmetries of the Reservoir Equations in Echo State Networks
• Towards physically consistent data-driven weather forecasting: Integrating data assimilation with equivariance-preserving deep spatial transformers
• Using Data Assimilation to Train a Hybrid Forecast System that Combines Machine-Learning and Knowledge-Based Components
• Finding nonlinear system equations and complex network structures from data: a sparse optimization approach
• Symmetry-Aware Reservoir Computing

Cited by in corpus (9)

• Learning unseen coexisting attractors
• Controlling Chaos Using Edge Computing Hardware
• Controlling Chaotic Maps using Next-Generation Reservoir Computing
• Quantum Next Generation Reservoir Computing: An Efficient Quantum Algorithm for Forecasting Quantum Dynamics
• How more data can hurt: Instability and regularization in next-generation reservoir computing
• Tailored minimal reservoir computing: on the bidirectional connection between nonlinearities in the reservoir and in data
• Improving the prediction of spatio-temporal chaos by combining parallel reservoir computing with dimensionality reduction
• Model-free Forecasting of Rogue Waves using Reservoir Computing
• Data-Driven Forecasting of Non-Equilibrium Solid-State Dynamics