Transfer learning for nonlinear dynamics and its application to fluid turbulence
This work addresses the challenge of data-efficient prediction in complex systems like fluid turbulence, offering a method that leverages small-scale universality, but it appears incremental as it builds on existing transfer learning concepts applied to a new domain.
The paper tackles the problem of predicting chaotic dynamics efficiently by introducing transfer learning for nonlinear dynamics, achieving an order of magnitude more accurate inference for Lorenz chaos and enabling inference of the energy dissipation rate in Navier-Stokes turbulence with a surprisingly small amount of data.
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.