Convolutional neural networks for long-time dissipative quantum dynamics

TL;DR

This paper introduces a convolutional neural network that efficiently predicts long-time dynamics of open quantum systems, significantly reducing computational costs while maintaining high accuracy across various regimes.

Contribution

The authors develop a convolutional neural network model capable of accurately simulating long-time quantum dynamics using short-time data, applicable to diverse initial conditions and regimes.

Findings

Model accurately predicts long-time dynamics across regimes.

Reduces computational resources needed for simulations.

Performs well on different initial conditions than training data.

Abstract

Exact numerical simulations of dynamics of open quantum systems often require immense computational resources. We demonstrate that a deep artificial neural network comprised of convolutional layers is a powerful tool for predicting long-time dynamics of an open quantum system provided the preceding short-time dynamics of the system is known. The neural network model developed in this work simulates long-time dynamics efficiently and very accurately across different dynamical regimes from weakly damped coherent motion to incoherent relaxation. The model was trained on a data set relevant to photosynthetic excitation energy transfer and can be deployed to study long-lasting quantum coherence phenomena observed in light-harvesting complexes. Furthermore, our model performs well for the initial conditions different than those used in the training. Our approach considerably reduces the required computational resources for long-time simulations and holds promise for becoming a valuable tool in the study of open quantum systems.