Article (Scientific journals)
Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions
Schütt, Kristof; Gastegger, Michael; Tkatchenko, Alexandre et al.
2019In Nature Communications, 10 (1), p. 5024
Peer Reviewed verified by ORBi
 

Files


Full Text
151-SchNorb-NatureComms-2019.pdf
Publisher postprint (917.35 kB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Abstract :
[en] Machine learning advances chemistry and materials science by enabling large-scale exploration of chemical space based on quantum chemical calculations. While these models supply fast and accurate predictions of atomistic chemical properties, they do not explicitly capture the electronic degrees of freedom of a molecule, which limits their applicability for reactive chemistry and chemical analysis. Here we present a deep learning framework for the prediction of the quantum mechanical wavefunction in a local basis of atomic orbitals from which all other ground-state properties can be derived. This approach retains full access to the electronic structure via the wavefunction at force-field-like efficiency and captures quantum mechanics in an analytically differentiable representation. On several examples, we demonstrate that this opens promising avenues to perform inverse design of molecular structures for targeting electronic property optimisation and a clear path towards increased synergy of machine learning and quantum chemistry.
Disciplines :
Physics
Author, co-author :
Schütt, Kristof
Gastegger, Michael
Tkatchenko, Alexandre ;  University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Physics and Materials Science Research Unit
Müller, Klaus-Robert
Maurer, Reinhard J.
External co-authors :
yes
Language :
English
Title :
Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions
Publication date :
15 November 2019
Journal title :
Nature Communications
ISSN :
2041-1723
Publisher :
Nature Publishing Group, London, United Kingdom
Volume :
10
Issue :
1
Pages :
5024
Peer reviewed :
Peer Reviewed verified by ORBi
Focus Area :
Physics and Materials Science
Computational Sciences
Available on ORBilu :
since 03 December 2019

Statistics


Number of views
214 (4 by Unilu)
Number of downloads
216 (5 by Unilu)

Scopus citations®
 
260
Scopus citations®
without self-citations
237
OpenCitations
 
218
WoS citations
 
252

Bibliography


Similar publications



Contact ORBilu