Model-Free Prediction of Large Spatiotemporally Chaotic Systems from Data: A Reservoir Computing Approach

Abstract

We demonstrate the effectiveness of using machine learning for model-free prediction of spatiotemporally chaotic systems of arbitrarily large spatial extent and attractor dimension purely from observations of the system's past evolution. We present a parallel scheme with an example implementation based on the reservoir computing paradigm and demonstrate the scalability of our scheme using the Kuramoto-Sivashinsky equation as an example of a spatiotemporally chaotic system.

Keywords

AttractorReservoir computingChaoticScalabilityComputer scienceScheme (mathematics)Chaotic systemsStatistical physicsDimension (graph theory)Distributed computingComputational sciencePhysicsArtificial neural networkArtificial intelligenceMathematicsRecurrent neural network

Affiliated Institutions

University of Maryland, College Park US

Related Publications

Neural network learning theoretical foundations

Martin Anthony , Peter L. Bartlett

This book describes theoretical advances in the study of artificial neural networks. It explores probabilistic models of supervised learning problems, and addresses the key stat...

2009 1356 citations

Deep Sparse Rectifier Neural Networks

Xavier Glorot , Antoine Bordes , Yoshua Bengio

While logistic sigmoid neurons are more biologically plausible than hyperbolic tangent neurons, the latter work better for training multi-layer neural networks. This paper shows...

2012 5408 citations

A channel access scheme for large dense packet radio networks

Timothy J. Shepard

Prior work in the field of packet radio networks has often assumed a simple success-if-exclusive model of successful reception. This simple model is insufficient to model interf...

1996 ACM SIGCOMM Computer Communication Re... 131 citations

A channel access scheme for large dense packet radio networks

Timothy J. Shepard

Prior work in the field of packet radio networks has often assumed a simple success-if-exclusive model of successful reception. This simple model is insufficient to model interf...

1996 290 citations

Consensus Filters for Sensor Networks and Distributed Sensor Fusion

R. Olfati-Saber , Jeff S. Shamma

Consensus algorithms for networked dynamic systems provide scalable algorithms for sensor fusion in sensor networks. This paper introduces a distributed filter that allows the n...

2006 977 citations

Publication Info

Year: 2018
Type: article
Volume: 120
Issue: 2
Pages: 024102-024102
Citations: 1194
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Model-Free Prediction of Large Spatiotemporally Chaotic Systems from Data: A Reservoir Computing Approach

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

1194

OpenAlex

Cite This

APA Style

                            
                                
                                    Jaideep Pathak, 
                                
                                    Brian R. Hunt, 
                                
                                    Michelle Girvan
                                
                                et al.
                            
                            (2018). 
                            Model-Free Prediction of Large Spatiotemporally Chaotic Systems from Data: A Reservoir Computing Approach. 
                            Physical Review Letters
                            , 120
                            (2)
                            , 024102-024102.
                            https://doi.org/10.1103/physrevlett.120.024102
                        

Identifiers

DOI: 10.1103/physrevlett.120.024102