Machine Learning for Quantum Dynamics: Deep Learning of Excitation Energy Transfer Properties

TL;DR

This paper introduces neural networks to efficiently predict excitation energy transfer properties in light-harvesting systems, significantly reducing computational costs while maintaining high accuracy, thus enabling high-throughput screening for excitonic device design.

Contribution

The study demonstrates that trained neural networks can accurately predict energy transfer dynamics, surpassing traditional approximate methods in efficiency and precision.

Findings

Neural networks reduce computational costs by several orders of magnitude.

Predicted transfer times and efficiencies match or exceed traditional methods.

Approach enables high-throughput screening of excitonic systems.

Abstract

Understanding the relationship between the structure of light-harvesting systems and their excitation energy transfer properties is of fundamental importance in many applications including the development of next generation photovoltaics. Natural light harvesting in photosynthesis shows remarkable excitation energy transfer properties, which suggests that pigment-protein complexes could serve as blueprints for the design of nature inspired devices. Mechanistic insights into energy transport dynamics can be gained by leveraging numerically involved propagation schemes such as the hierarchical equations of motion (HEOM). Solving these equations, however, is computationally costly due to the adverse scaling with the number of pigments. Therefore virtual high-throughput screening, which has become a powerful tool in material discovery, is less readily applicable for the search of novel excitonic devices. We propose the use of artificial neural networks to bypass the computational limitations of established techniques for exploring the structure-dynamics relation in excitonic systems. Once trained, our neural networks reduce computational costs by several orders of magnitudes. Our predicted transfer times and transfer efficiencies exhibit similar or even higher accuracies than frequently used approximate methods such as secular Redfield theory