skip to main content

Title: Electronic spectra from TDDFT and machine learning in chemical space

Due to its favorable computational efficiency, time-dependent (TD) density functional theory (DFT) enables the prediction of electronic spectra in a high-throughput manner across chemical space. Its predictions, however, can be quite inaccurate. We resolve this issue with machine learning models trained on deviations of reference second-order approximate coupled-cluster (CC2) singles and doubles spectra from TDDFT counterparts, or even from DFT gap. We applied this approach to low-lying singlet-singlet vertical electronic spectra of over 20 000 synthetically feasible small organic molecules with up to eight CONF atoms. The prediction errors decay monotonously as a function of training set size. For a training set of 10 000 molecules, CC2 excitation energies can be reproduced to within ±0.1 eV for the remaining molecules. Analysis of our spectral database via chromophore counting suggests that even higher accuracies can be achieved. Based on the evidence collected, we discuss open challenges associated with data-driven modeling of high-lying spectra and transition intensities.
Authors:
 [1] ; ;  [2] ;  [1] ;  [3]
  1. Institute of Physical Chemistry and National Center for Computational Design and Discovery of Novel Materials, Department of Chemistry, University of Basel, Klingelbergstrasse 80, CH-4056 Basel (Switzerland)
  2. Department of Chemistry and Biochemistry, California State University, 1250 Bellflower Boulevard, Long Beach, California 90840 (United States)
  3. (United States)
Publication Date:
OSTI Identifier:
22493563
Resource Type:
Journal Article
Resource Relation:
Journal Name: Journal of Chemical Physics; Journal Volume: 143; Journal Issue: 8; Other Information: (c) 2015 AIP Publishing LLC; Country of input: International Atomic Energy Agency (IAEA)
Country of Publication:
United States
Language:
English
Subject:
37 INORGANIC, ORGANIC, PHYSICAL AND ANALYTICAL CHEMISTRY; ACCURACY; ATOMS; COMPUTERIZED SIMULATION; DENSITY FUNCTIONAL METHOD; EFFICIENCY; ELECTRON SPECTRA; ERRORS; EV RANGE; EXCITATION; MOLECULES; SPACE; TIME DEPENDENCE