File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1021/acs.jpclett.9b02838
- Scopus: eid_2-s2.0-85075053648
- PMID: 31690079
- WOS: WOS:000497261200043
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Toward the Exact Exchange–Correlation Potential: A Three-Dimensional Convolutional Neural Network Construct
Title | Toward the Exact Exchange–Correlation Potential: A Three-Dimensional Convolutional Neural Network Construct |
---|---|
Authors | |
Issue Date | 2019 |
Publisher | American Chemical Society. The Journal's web site is located at http://pubs.acs.org/loi/jpclcd |
Citation | The Journal of Physical Chemistry Letters, 2019, v. 10 n. 22, p. 7264-7269 How to Cite? |
Abstract | A deep neural network is constructed to yield in principle exact exchange–correlation potential. It requires merely the electron densities of small molecules and ions and yet can determine the exchange–correlation potentials of large molecules. We train and validate the neural network based on the data for H2 and HeH+ and subsequently determine the ground-state electron density of stretched HeH+, linear H3+, and H–He–He–H2+. Moreover, the deep neural network is proven to model the van der Waals interaction by being trained and validated on a data set containing He2. Comparisons to B3LYP are given to illustrate the accuracy and transferability of the neural network. |
Persistent Identifier | http://hdl.handle.net/10722/293529 |
ISSN | 2023 Impact Factor: 4.8 2023 SCImago Journal Rankings: 1.586 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhou, Y | - |
dc.contributor.author | Wu, J | - |
dc.contributor.author | Chen, S | - |
dc.contributor.author | Chen, G | - |
dc.date.accessioned | 2020-11-23T08:18:05Z | - |
dc.date.available | 2020-11-23T08:18:05Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | The Journal of Physical Chemistry Letters, 2019, v. 10 n. 22, p. 7264-7269 | - |
dc.identifier.issn | 1948-7185 | - |
dc.identifier.uri | http://hdl.handle.net/10722/293529 | - |
dc.description.abstract | A deep neural network is constructed to yield in principle exact exchange–correlation potential. It requires merely the electron densities of small molecules and ions and yet can determine the exchange–correlation potentials of large molecules. We train and validate the neural network based on the data for H2 and HeH+ and subsequently determine the ground-state electron density of stretched HeH+, linear H3+, and H–He–He–H2+. Moreover, the deep neural network is proven to model the van der Waals interaction by being trained and validated on a data set containing He2. Comparisons to B3LYP are given to illustrate the accuracy and transferability of the neural network. | - |
dc.language | eng | - |
dc.publisher | American Chemical Society. The Journal's web site is located at http://pubs.acs.org/loi/jpclcd | - |
dc.relation.ispartof | The Journal of Physical Chemistry Letters | - |
dc.rights | This document is the Accepted Manuscript version of a Published Work that appeared in final form in The Journal of Physical Chemistry Letters, copyright © American Chemical Society after peer review and technical editing by the publisher. To access the final edited and published work see https://doi.org/10.1021/acs.jpclett.9b02838 | - |
dc.title | Toward the Exact Exchange–Correlation Potential: A Three-Dimensional Convolutional Neural Network Construct | - |
dc.type | Article | - |
dc.identifier.email | Chen, S: sgchen@hku.hk | - |
dc.identifier.email | Chen, G: ghchen@hku.hk | - |
dc.identifier.authority | Chen, S=rp02785 | - |
dc.identifier.authority | Chen, G=rp00671 | - |
dc.description.nature | postprint | - |
dc.identifier.doi | 10.1021/acs.jpclett.9b02838 | - |
dc.identifier.pmid | 31690079 | - |
dc.identifier.scopus | eid_2-s2.0-85075053648 | - |
dc.identifier.hkuros | 318825 | - |
dc.identifier.volume | 10 | - |
dc.identifier.issue | 22 | - |
dc.identifier.spage | 7264 | - |
dc.identifier.epage | 7269 | - |
dc.identifier.isi | WOS:000497261200043 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 1948-7185 | - |