Machine Learning Time Propagators for Time-Dependent Density Functional Theory Simulations

TL;DR

This paper introduces a machine learning method using autoregressive neural operators to accelerate real-time TDDFT simulations of electron dynamics, achieving higher accuracy and speed for modeling laser-irradiated molecules.

Contribution

It presents a novel ML-based time propagator for TDDFT that incorporates physics-informed constraints and high-resolution data, improving simulation efficiency.

Findings

Achieves superior accuracy over traditional solvers.

Provides faster computational performance.

Effectively models electron dynamics in laser-irradiated molecules.

Abstract

Time-dependent density functional theory (TDDFT) is a widely used method to investigate electron dynamics under external time-dependent perturbations such as laser fields. In this work, we present a machine learning approach to accelerate electron dynamics simulations based on real time TDDFT using autoregressive neural operators as time-propagators for the electron density. By leveraging physics-informed constraints and featurization, and high-resolution training data, our model achieves superior accuracy and computational speed compared to traditional numerical solvers. We demonstrate the effectiveness of our model on a class of one-dimensional diatomic molecules under the influence of a range of laser parameters. This method has potential in enabling on-the-fly modeling of laser-irradiated molecules and materials by utilizing fast machine learning predictions in a large space of varying experimental parameters of the laser.