Using electron density improves machine learning of molecular spectra
Electronic Density versus Geometry for Machine-Learned Molecular Absorption Spectra
Machine Learning
Summary
Predicting how molecules absorb light helps identify and understand them, but accurate calculations are slow. This paper compares two ways to teach computers to predict these absorption patterns: one using the molecule’s shape and the other using a detailed map of its electrons. The researchers show that using the electron map gives more accurate predictions, even if it takes extra calculation time upfront. This means machines can better estimate molecular behavior faster once trained.
What this means in practice
- •For computational chemistry teams: Generate faster and more accurate predictions of molecular absorption spectra using machine learning models based on electron density data.
- •For materials design engineers: Improve rapid screening of molecular compounds’ optical properties to assist in developing new photonic or electronic materials.
Authors
Siddharth Dhanpal, Peter Elliott, Paolo Emilio Trevisanutto, Alin M. Elena, Gilberto Teobaldi
Abstract
Molecular optical absorption spectroscopy provides a direct probe of electronic structure and is widely used for molecular identification, interpretation of photophysical behaviour, and planning of spectroscopy experiments. Calculating the absorption spectra using first-principle excited-state methods, however, is computationally demanding, at least compared to ground-state calculations, which limits their routine application across large molecular sets. Machine-learning (ML) surrogates can reduce this cost and allow rapid spectral prediction. However, their performance depends strongly on how molecular information is represented. Here, we compare using the ground-state electron density versus the molecular geometry as inputs to a ML model for predicting absorption spectra, for a training set of 6874 molecules selected from the QM7 dataset. For each of these molecules, the density was calculated using density functional theory (DFT) and the absorption spectrum was calculated using linear-response (LR) time-dependent DFT (TDDFT). Utilizing the ground-state density as the input to the ML model is motivated by the Hohenberg-Kohn and Runge-Gross theorems, and the fact that the ground-state density encodes information about bonding, charge localisation, and electronic delocalisation. Hence, it may be a more judicious starting point for the ML model compared to the geometry, as it effectively decouples the chemistry of the ground-state. The question we test is whether the benefits of using the density outweigh the (notprohibitive) penalty of requiring an additional single-point DFT calculation for the density. We find that the density-based convolutional neural network achieves a validation correlation of 0.9926, compared with 0.9795 for the best geometry-based graph model, reducing the residual decorrelation, by approximately 64%.