Transfer learning for nonlinear dynamics and its application to fluid turbulence
Masanobu Inubushi, Susumu Goto
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.
Topics & Concepts
TurbulenceStatistical physicsNonlinear systemReynolds numberUniversality (dynamical systems)ChaoticK-epsilon turbulence modelK-omega turbulence modelReynolds decompositionComputer scienceDissipationPhysicsMechanicsArtificial intelligenceThermodynamicsQuantum mechanicsNeural Networks and Reservoir ComputingModel Reduction and Neural NetworksNeural Networks and Applications