Physics-Informed Latent Space Dynamics Identification for Time-Dependent NLTE Atomic Kinetics

TL;DR

This paper introduces a physics-informed machine learning framework called pLaSDI for modeling time-dependent NLTE atomic kinetics in plasmas, achieving high accuracy and significant speedups while maintaining physical stability.

Contribution

The novel pLaSDI framework explicitly models latent space dynamics for NLTE kinetics with physics-informed constraints, enabling fast, stable, and physically reliable extrapolation.

Findings

Achieves charge-state prediction errors below 2%.

Provides speedups of approximately 50,000 to 100,000 times.

Maintains stability and physical accuracy outside training data.

Abstract

Non-local thermodynamic equilibrium (NLTE) calculations remain a major computational bottleneck in radiation--hydrodynamics, while most existing machine-learning surrogates treat NLTE as a static input--output mapping rather than a kinetic evolution problem. Here, we present a physics-informed Latent Space Dynamics Identification (pLaSDI) framework specifically designed for NLTE atomic kinetics, which captures the time-dependent atomic kinetics of non-equilibrium plasmas through an explicit reduced governing equation. To ensure the physical reliability of the reduced model, we impose physics-informed loss terms that enforce macroscopic consistency, dynamical stability, and convergence to the correct steady state during long-time integration. Applied to tin NLTE population data generated along hydrodynamically modeled temperature--density trajectories relevant to extreme ultraviolet (EUV) lithography plasmas, the model accurately reproduces charge-state evolution and mean charge state with errors below 2\%, achieves speedups of approximately $5\times10^{4}$--$10^{5}$, and remains stable outside the training trajectories by converging toward physically admissible states and the correct steady-state solution under fixed plasma conditions. These results show that careful physics-informed design of the latent dynamics, rather than data fitting alone, is essential for constructing fast, stable, and physically reliable extrapolative surrogates for time-dependent NLTE kinetics.