Capturing intensive and extensive DFT/TDDFT molecular properties with machine learning★
Machine Learning Group, Technische Universität Berlin,
2 Physics and Materials Science Research Unit, University of Luxembourg, Luxembourg 1511, Luxembourg
3 Max Planck Institute for Informatics, 66123 Saarbrücken, Germany
4 Department of Brain and Cognitive Engineering, Korea University, Seoul 136-713, South Korea
a e-mail: firstname.lastname@example.org
b e-mail: email@example.com
Received in final form: 1 June 2018
Published online: 6 August 2018
Machine learning has been successfully applied to the prediction of chemical properties of small organic molecules such as energies or polarizabilities. Compared to these properties, the electronic excitation energies pose a much more challenging learning problem. Here, we examine the applicability of two existing machine learning methodologies to the prediction of excitation energies from time-dependent density functional theory. To this end, we systematically study the performance of various 2- and 3-body descriptors as well as the deep neural network SchNet to predict extensive as well as intensive properties such as the transition energies from the ground state to the first and second excited state. As perhaps expected current state-of-the-art machine learning techniques are more suited to predict extensive as opposed to intensive quantities. We speculate on the need to develop global descriptors that can describe both extensive and intensive properties on equal footing.
© The Author(s) 2018. This article is published with open access at Springerlink.com
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.