Transfer learning for nonlinear dynamics and its application to fluid turbulence

Abstract

We introduce transfer learning for nonlinear dynamics, which enables efficient predictions of chaotic dynamics by utilizing a small amount of data. For the Lorenz chaos, by optimizing the transfer rate, we accomplish more accurate inference than the conventional method by an order of magnitude. Moreover, a surprisingly small amount of learning is enough to infer the energy dissipation rate of the Navier-Stokes turbulence because we can, thanks to the small-scale universality of turbulence, transfer a large amount of the knowledge learned from turbulence data at lower Reynolds number.

8 pages, 7 figures

References in corpus (5)

• Recent Advances in Physical Reservoir Computing: A Review
• Turbulence Modeling in the Age of Data
• Searching for turbulence models by artificial neural network
• Synthetic turbulent inflow generator using machine learning
• Machine-learning inference of fluid variables from data using reservoir computing

Cited by in corpus (15)

• Explaining the physics of transfer learning a data-driven subgrid-scale closure to a different turbulent flow
• Chaos on compact manifolds: Differentiable synchronizations beyond the Takens theorem
• Data-driven nonlinear turbulent flow scaling with Buckingham Pi variables
• Global Extreme Heat Forecasting Using Neural Weather Models
• Physical deep learning based on optimal control of dynamical systems
• Compressing fluid flows with nonlinear machine learning: mode decomposition, latent modeling, and flow control
• Criticality in Reservoir Computer of Coupled Phase Oscillators
• Reservoir Computing with Generalized Readout based on Generalized Synchronization
• Image features of a splashing drop on a solid surface extracted using a feedforward neural network
• Generalizability of reservoir computing for flux-driven two-dimensional convection
• Synchronization of Low Reynolds Number Plane Couette Turbulence
• Characterizing Data Assimilation in Navier-Stokes Turbulence with Transverse Lyapunov Exponents
• Phase autoencoder for rapid data-driven synchronization of rhythmic spatiotemporal patterns
• (Thesis) Reservoir Computing With Dynamical Systems
• Data-driven prediction of reversal of large-scale circulation in turbulent convection