Article (Scientific journals)
Capturing intensive and extensive DFT/TDDFT molecular properties with machine learning
Pronobis, Wiktor; Sch utt, Kristof; Tkatchenko, Alexandre et al.
2018In European Physical Journal B -- Condensed Matter, 91, p. 6
Peer Reviewed verified by ORBi
 

Files


Full Text
131-DFT-TDDFT-machine-learning-EPJB-2018.pdf
Publisher postprint (819.15 kB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Abstract :
[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.
Disciplines :
Physics
Author, co-author :
Pronobis, Wiktor ;  Technische Universit at Berlin, 10587 Berlin, Germany
Sch utt, Kristof 
Tkatchenko, Alexandre ;  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.
External co-authors :
yes
Language :
English
Title :
Capturing intensive and extensive DFT/TDDFT molecular properties with machine learning
Publication date :
06 August 2018
Journal title :
European Physical Journal B -- Condensed Matter
ISSN :
1434-6036
Publisher :
Springer, New York, Germany
Volume :
91
Pages :
6
Peer reviewed :
Peer Reviewed verified by ORBi
Focus Area :
Physics and Materials Science
Available on ORBilu :
since 01 January 2019

Statistics


Number of views
129 (1 by Unilu)
Number of downloads
135 (1 by Unilu)

Scopus citations®
 
49
Scopus citations®
without self-citations
43
OpenCitations
 
44
WoS citations
 
43

Bibliography


Similar publications



Contact ORBilu