Extreme Event Prediction with Multi-agent Reinforcement Learning-based Parametrization of Atmospheric and Oceanic Turbulence

no code implementations • 1 Dec 2023 • Rambod Mojgani, Daniel Waelchli, Yifei Guan, Petros Koumoutsakos, Pedram Hassanzadeh

Reinforcement learning is emerging as a potent alternative for developing such closures as it requires only low-order statistics and leads to stable closures.

Multi-agent Reinforcement Learning

Learning Closed-form Equations for Subgrid-scale Closures from High-fidelity Data: Promises and Challenges

1 code implementation • 8 Jun 2023 • Karan Jakhar, Yifei Guan, Rambod Mojgani, Ashesh Chattopadhyay, Pedram Hassanzadeh

These closures depend on nonlinear combinations of gradients of filtered variables, with constants that are independent of the fluid/flow properties and only depend on filter type/size.

Explaining the physics of transfer learning a data-driven subgrid-scale closure to a different turbulent flow

1 code implementation • 7 Jun 2022 • Adam Subel, Yifei Guan, Ashesh Chattopadhyay, Pedram Hassanzadeh

For effective TL, we need to know 1) what are the best layers to re-train?

Out-of-Distribution Generalization Transfer Learning