Machine Learning Modeling of Charge-Density-Wave Recovery After Laser Melting

TL;DR

This paper develops a machine learning approach combined with Langevin dynamics to efficiently simulate the long-time recovery of charge-density-wave order in laser-pumped systems, overcoming computational challenges of fully nonadiabatic simulations.

Contribution

It introduces a hybrid method that separates the lattice force into a learnable quasi-adiabatic part and a bath component, enabling scalable simulations of nonequilibrium dynamics.

Findings

Efficient modeling of charge-density-wave recovery dynamics.

Machine learning accurately captures the quasi-adiabatic force component.

Langevin dynamics reproduces essential features of the nonequilibrium process.

Abstract

We investigate the nonequilibrium dynamics of a laser-pumped two-dimensional spinless Holstein model within a semiclassical framework, focusing on the melting and recovery of long-range charge-density-wave order. Accurately describing this process requires fully nonadiabatic electron-lattice dynamics, which is computationally demanding due to the need to resolve fast electronic motion over long time scales. By analyzing the structure of the lattice force during nonequilibrium evolution, we show that the force naturally separates into a smooth quasi-adiabatic component and a residual bath-like contribution associated with fast electronic fluctuations. The quasi-adiabatic component depends only on the instantaneous local lattice configuration and can be efficiently learned using machine-learning techniques, while a minimal Langevin description of the bath term captures the essential features of the recovery dynamics. Combining these elements enables efficient and scalable simulations of long-time nonequilibrium dynamics on large lattices, providing a practical route to access driven correlated systems beyond the reach of direct nonadiabatic approaches.