Machine Learning Time Propagators for Time-Dependent Density Functional Theory Simulations
This work addresses the computational bottleneck in TDDFT simulations for modeling laser-irradiated molecules and materials, enabling faster on-the-fly predictions across varying laser parameters.
The authors tackled the problem of accelerating electron dynamics simulations in time-dependent density functional theory (TDDFT) by developing a machine learning approach using autoregressive neural operators as time-propagators, achieving superior accuracy and computational speed compared to traditional numerical solvers.
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.