Two-dimensional (2D) spectroscopy encodes molecular properties and dynamics into expansive spectral datasets. Translating these data into meaningful chemical insights is challenging because of the many ways chemical properties can influence the spectra. To address the task of extracting chemical information from 2D spectra, we studied the capacity of simple feedforward neural networks (NNs) to map simulated 2D electronic spectra to underlying physical Hamiltonians. We examined hundreds of simulated 2D spectra corresponding to monomers and dimers with varied Franck-Condon active vibrations and monomer-monomer electronic couplings. We found that NNs can correctly characterize most Hamiltonian parameters considered in this study with an accuracy above 90%. Our results demonstrate that NNs can aid in interpreting 2D spectra, leading from spectroscopic features to underlying effective Hamiltonians. Ongoing work is aimed towards expanding the NNs’ capabilities for 2D spectra analysis including the interpretation of experimental spectra.

Mapping two-dimensional electronic spectra to molecular models using machine learning

Where thousands of chemistry professionals meet to share ideas and advance scientific and technical knowledge. Spring 2023 abstracts, posters, and presentations will launch at the end of March.

ACS Spring 2023

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.