Reference : Capturing intensive and extensive DFT/TDDFT molecular properties with machine learning
Scientific journals : Article
Physical, chemical, mathematical & earth Sciences : Physics
Physics and Materials Science
Capturing intensive and extensive DFT/TDDFT molecular properties with machine learning
Pronobis, Wiktor* [Technische Universit at Berlin, 10587 Berlin, Germany]
Sch utt, Kristof* []
Tkatchenko, Alexandre mailto [University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Physics and Materials Science Research Unit >]
M uller, Klaus-Robert []
* These authors have contributed equally to this work.
European Physical Journal B -- Condensed Matter
Yes (verified by ORBilu)
New York
[en] 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 rst 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.

File(s) associated to this reference

Fulltext file(s):

Open access
131-DFT-TDDFT-machine-learning-EPJB-2018.pdfPublisher postprint799.95 kBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.