Accelerating Electron Dynamics Simulations through Machine Learned Time Propagators

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Shah, Karan, Cangi, Attila
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916336687382528
author Shah, Karan
Cangi, Attila
author_facet Shah, Karan
Cangi, Attila
contents Time-dependent density functional theory (TDDFT) is a widely used method to investigate electron dynamics under various external perturbations such as laser fields. In this work, we present a novel approach to accelerate real time TDDFT based electron dynamics simulations using autoregressive neural operators as time-propagators for the electron density. By leveraging physics-informed constraints 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. This method has potential in enabling real-time, on-the-fly modeling of laser-irradiated molecules and materials with varying experimental parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2407_09628
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Accelerating Electron Dynamics Simulations through Machine Learned Time Propagators
Shah, Karan
Cangi, Attila
Materials Science
Machine Learning
Computational Physics
Time-dependent density functional theory (TDDFT) is a widely used method to investigate electron dynamics under various external perturbations such as laser fields. In this work, we present a novel approach to accelerate real time TDDFT based electron dynamics simulations using autoregressive neural operators as time-propagators for the electron density. By leveraging physics-informed constraints 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. This method has potential in enabling real-time, on-the-fly modeling of laser-irradiated molecules and materials with varying experimental parameters.
title Accelerating Electron Dynamics Simulations through Machine Learned Time Propagators
topic Materials Science
Machine Learning
Computational Physics
url https://arxiv.org/abs/2407.09628