Excitation energies and UV-Vis absorption spectra from INDO/s+ML

TL;DR

This paper introduces machine learning models that significantly improve the accuracy of semi-empirical INDO/s excitation energy predictions and UV-Vis spectra, achieving near TDDFT accuracy with minimal additional computational cost.

Contribution

The study presents a novel ML correction approach for INDO/s, enhancing its accuracy for excitation energies and spectra without substantial computational overhead.

Findings

ML corrections reduce INDO/s error from 1.1 eV to 0.2 eV

UV-Vis spectra match well with TDDFT predictions

Method maintains low computational cost

Abstract

The semi-empirical INDO/s method is popular for studies of excitation energies and absorption of molecules due to its low computational requirement, making it possible to make predictions for large systems. However, its accuracy is generally low, particularly, when compared with the typical accuracy of other methods such as time-dependent density functional theory (TDDFT). Here, we present machine learning (ML) models that correct the INDO/s results with negligible increases in the amount of computing resources needed. While INDO/s excitations energies have an average error of about 1.1 eV relative to TDDFT energies, the added ML corrections reduce the error to 0.2 eV. Furthermore, this combination of INDO/s and ML produces UV-Vis absorption spectra that are in good agreement with the TDDFT predictions.