Learning hidden low dimensional dyanmics using a Generalized Onsager Principle and neural networks

This is the original pyTorch implemenation of OnsagerNet with three applications:

1. Learning deterministic Langevin dynamics
2. Learning chaotic and non-chaotic Lorenz63 system
3. Learning a reduced model for Rayleigh Bernard Convection (RBC) based only on trajectory data.

See the ReadMe.md in each subfolder and the reference paper for more information.

1. [PhyRevF] H. Yu, X. Tian, W. E and Q. Li, OnsagerNet: Learning Stable and Interpretable Dynamics using a Generalized Onsager Principle, arxiv:2009.02327, to appear on Physical Review Fluids, 2021.