Machine-learning inference of fluid variables from data using reservoir computing

Abstract

We infer both microscopic and macroscopic behaviors of a three-dimensional chaotic fluid flow using reservoir computing. In our procedure of the inference, we assume no prior knowledge of a physical process of a fluid flow except that its behavior is complex but deterministic. We present two ways of inference of the complex behavior; the first called partial-inference requires continued knowledge of partial time-series data during the inference as well as past time-series data, while the second called full-inference requires only past time-series data as training data. For the first case, we are able to infer long-time motion of microscopic fluid variables. For the second case, we show that the reservoir dynamics constructed from only past data of energy functions can infer the future behavior of energy functions and reproduce the energy spectrum. It is also shown that we can infer a time-series data from only one measurement by using the delay coordinates. These implies that the obtained two reservoir systems constructed without the knowledge of microscopic data are equivalent to the dynamical systems describing macroscopic behavior of energy functions.

arXiv comment7 pages, 8 figures

References in corpus (10)

• Finding Density Functionals with Machine Learning
• Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
• Attractor Reconstruction by Machine Learning
• Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
• Searching for turbulence models by artificial neural network
• Matching matched filtering with deep networks in gravitational-wave astronomy
• Data-assisted reduced-order modeling of extreme events in complex dynamical systems
• Using a reservoir computer to learn chaotic attractors, with applications to chaos synchronisation and cryptography
• Detection of Generalized Synchronization using Echo State Networks
• Deep neural networks for direct, featureless learning through observation: the case of 2d spin models

Cited by in corpus (18)

• Anticipating synchronization with machine learning
• Synchronization to big-data: nudging the Navier-Stokes equations for data assimilation of turbulent flows
• Adaptable Hamiltonian neural networks
• Transfer learning for nonlinear dynamics and its application to fluid turbulence
• Finding nonlinear system equations and complex network structures from data: a sparse optimization approach
• Dynamical system analysis of a data-driven model constructed by reservoir computing
• Extreme events prediction from nonlocal partial information in a spatiotemporally chaotic microcavity laser
• Effective models and predictability of chaotic multiscale systems via machine learning
• Machine-learning construction of a model for a macroscopic fluid variable using the delay-coordinate of a scalar observable
• Long-term prediction of El Niño-Southern Oscillation using reservoir computing with data-driven realtime filter
• Computing with vortices: Bridging fluid dynamics and its information-processing capability
• Constructing differential equations using only a scalar time-series about continuous time chaotic dynamics
• Model-free prediction of spatiotemporal dynamical systems with recurrent neural networks: Role of network spectral radius
• Long-term prediction of chaotic systems with recurrent neural networks
• Stability of exoplanetary systems retrieved from scalar time series
• Physical reservoir computing using finitely-sampled quantum systems
• Reservoir observer enhanced with residual calibration and attention mechanism
• Data-driven prediction of reversal of large-scale circulation in turbulent convection