File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1021/acs.jpca.7b07045
- Scopus: eid_2-s2.0-85030532911
- PMID: 28876064
- WOS: WOS:000412149600023
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Improving the Performance of Long-Range-Corrected Exchange-Correlation Functional with an Embedded Neural Network
Title | Improving the Performance of Long-Range-Corrected Exchange-Correlation Functional with an Embedded Neural Network |
---|---|
Authors | |
Issue Date | 2017 |
Publisher | American Chemical Society. The Journal's web site is located at http://pubs.acs.org/jpca |
Citation | The Journal of Physical Chemistry A, 2017, v. 121 n. 39, p. 7273-7281 How to Cite? |
Abstract | A machine-learning-based exchange-correlation functional is proposed for general-purpose density functional theory calculations. It is built upon the long-range-corrected Becke-Lee-Yang-Parr (LC-BLYP) functional, along with an embedded neural network which determines the value of the range-separation parameter μ for every individual system. The structure and the weights of the neural network are optimized with a reference data set containing 368 highly accurate thermochemical and kinetic energies. The newly developed functional (LC-BLYP-NN) achieves a balanced performance for a variety of energetic properties investigated. It largely improves the accuracy of atomization energies and heats of formation on which the original LC-BLYP with a fixed μ performs rather poorly. Meanwhile, it yields a similar or slightly compromised accuracy for ionization potentials, electron affinities, and reaction barriers, for which the original LC-BLYP works reasonably well. This work clearly highlights the potential usefulness of machine-learning techniques for improving density functional calculations. (Figure Presented). © 2017 American Chemical Society. |
Persistent Identifier | http://hdl.handle.net/10722/279304 |
ISSN | 2023 Impact Factor: 2.7 2023 SCImago Journal Rankings: 0.604 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liu, Q | - |
dc.contributor.author | Wang, JC | - |
dc.contributor.author | Du, PL | - |
dc.contributor.author | Hu, LH | - |
dc.contributor.author | Zheng, X | - |
dc.contributor.author | Chen, G | - |
dc.date.accessioned | 2019-10-25T13:53:08Z | - |
dc.date.available | 2019-10-25T13:53:08Z | - |
dc.date.issued | 2017 | - |
dc.identifier.citation | The Journal of Physical Chemistry A, 2017, v. 121 n. 39, p. 7273-7281 | - |
dc.identifier.issn | 1089-5639 | - |
dc.identifier.uri | http://hdl.handle.net/10722/279304 | - |
dc.description.abstract | A machine-learning-based exchange-correlation functional is proposed for general-purpose density functional theory calculations. It is built upon the long-range-corrected Becke-Lee-Yang-Parr (LC-BLYP) functional, along with an embedded neural network which determines the value of the range-separation parameter μ for every individual system. The structure and the weights of the neural network are optimized with a reference data set containing 368 highly accurate thermochemical and kinetic energies. The newly developed functional (LC-BLYP-NN) achieves a balanced performance for a variety of energetic properties investigated. It largely improves the accuracy of atomization energies and heats of formation on which the original LC-BLYP with a fixed μ performs rather poorly. Meanwhile, it yields a similar or slightly compromised accuracy for ionization potentials, electron affinities, and reaction barriers, for which the original LC-BLYP works reasonably well. This work clearly highlights the potential usefulness of machine-learning techniques for improving density functional calculations. (Figure Presented). © 2017 American Chemical Society. | - |
dc.language | eng | - |
dc.publisher | American Chemical Society. The Journal's web site is located at http://pubs.acs.org/jpca | - |
dc.relation.ispartof | The Journal of Physical Chemistry A | - |
dc.rights | This document is the Accepted Manuscript version of a Published Work that appeared in final form in [JournalTitle], copyright © American Chemical Society after peer review and technical editing by the publisher. To access the final edited and published work see [insert ACS Articles on Request author-directed link to Published Work, see http://pubs.acs.org/page/policy/articlesonrequest/index.html]. | - |
dc.title | Improving the Performance of Long-Range-Corrected Exchange-Correlation Functional with an Embedded Neural Network | - |
dc.type | Article | - |
dc.identifier.email | Chen, G: ghchen@hku.hk | - |
dc.identifier.authority | Chen, G=rp00671 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1021/acs.jpca.7b07045 | - |
dc.identifier.pmid | 28876064 | - |
dc.identifier.scopus | eid_2-s2.0-85030532911 | - |
dc.identifier.hkuros | 308245 | - |
dc.identifier.volume | 121 | - |
dc.identifier.issue | 39 | - |
dc.identifier.spage | 7273 | - |
dc.identifier.epage | 7281 | - |
dc.identifier.isi | WOS:000412149600023 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 1089-5639 | - |