Latent Space Dynamics Learning for Stiff Collisional-radiative Models

TL;DR

This paper introduces a data-driven approach using autoencoders and neural networks to reduce the complexity of stiff collisional-radiative models in plasma simulations, enabling faster and accurate predictions.

Contribution

The work presents a novel physics-assisted autoencoder and flow map neural network framework for low-dimensional modeling of high-dimensional CR systems in plasma physics.

Findings

Accurately predicts full CR dynamics

Efficiently estimates radiative power loss

Reduces computational costs in plasma simulations

Abstract

In this work, we propose a data-driven method to discover the latent space and learn the corresponding latent dynamics for a collisional-radiative (CR) model in radiative plasma simulations. The CR model, consisting of high-dimensional stiff ordinary differential equations (ODEs), must be solved at each grid point in the configuration space, leading to significant computational costs in plasma simulations. Our method employs a physics-assisted autoencoder to extract a low-dimensional latent representation of the original CR system. A flow map neural network is then used to learn the latent dynamics. Once trained, the reduced surrogate model predicts the entire latent dynamics given only the initial condition by iteratively applying the flow map. The radiative power loss is then reconstructed using a decoder. Numerical experiments demonstrate that the proposed architecture can accurately predict both the full-order CR dynamics and the radiative power loss rate.