Exploiting machine learning to efficiently predict multidimensional optical spectra in complex environments

TL;DR

This paper develops machine learning models to efficiently predict excited state energy gaps of chromophores in complex environments, enabling faster computation of multidimensional optical spectra crucial for understanding biological and energy processes.

Contribution

It introduces a machine learning approach leveraging chromophore locality to accelerate first-principles predictions of multidimensional optical spectra in complex environments.

Findings

ML models accurately predict excited state energy gaps

Strategies for constructing effective ML models are proposed

Significant acceleration in spectral calculations achieved

Abstract

The excited state dynamics of chromophores in complex environments determine a range of vital biological and energy capture processes. Time-resolved, multidimensional optical spectroscopies provide a key tool to investigate these processes. Although theory has the potential to decode these spectra in terms of the electronic and atomistic dynamics, the need for large numbers of excited state electronic structure calculations severely limits first principles predictions of multidimensional optical spectra for chromophores in the condensed phase. Here, we leverage the locality of chromophore excitations to develop machine learning models to predict the excited state energy gap of chromophores in complex environments for efficiently constructing linear and multidimensional optical spectra. By analyzing the performance of these models, which span a hierarchy of physical approximations, across a range of chromophore-environment interaction strengths, we provide strategies for the construction of ML models that greatly accelerate the calculation of multidimensional optical spectra from first principles.