Show simple item record

A critical comparison of neural network potentials for molecular reaction dynamics with exact permutation symmetry

dc.contributor.authorLi, Jun
dc.contributor.authorSong, Kaisheng
dc.contributor.authorBehler, Jörg
dc.date.accessioned2019-10-01T10:46:22Z
dc.date.available2019-10-01T10:46:22Z
dc.date.issued2019de
dc.relation.ISSN1463-9084de
dc.identifier.urihttp://resolver.sub.uni-goettingen.de/purl?gs-1/16458
dc.description.abstractThe availability of accurate full-dimensional potential energy surfaces (PESs) is a mandatory condition for efficient computer simulations of molecular systems. Much effort has been devoted to developing reliable PESs with physically sound properties, such as the invariance of the energy with respect to the permutation of chemically identical atoms. In this work, we compare the performance of four neural network (NN)-based approaches with a rigorous permutation symmetry for fitting five typical reaction systems: OH + CO, H + H2S, H + NH3, H + CH4 and OH + CH4. The methods can be grouped into two categories, invariant polynomial based NNs and high-dimensional NN potentials (HD-NNPs). For the invariant polynomial based NNs, three types of polynomials, permutation invariant polynomials (PIPs), non-redundant PIPs (NRPIPs) and fundamental invariants (FIs), are used in the input layer of the NN. In HD-NNPs, the total energy is the sum of atomic contributions, each of which is given by an individual atomic NN with input vectors consisting of sets of atom-centered symmetry functions. Our results show that all methods exhibit a similar level of accuracy for the energies with respect to ab initio data obtained at the explicitly correlated coupled cluster level of theory (CCSD(T)-F12a). The HD-NNP method allows study of systems with larger numbers of atoms, making it more generally applicable than invariant polynomial based approaches, which in turn are computationally more efficient for smaller systems. To illustrate the applicability of the obtained potentials, quasi-classical trajectory calculations have been performed for the OH + CH4 → H2O + CH3 reaction to reveal its complicated mode specificity.de
dc.language.isoengde
dc.rightsopenAccess
dc.rights.urihttps://creativecommons.org/licenses/by-nc/3.0/
dc.subject.ddc540
dc.titleA critical comparison of neural network potentials for molecular reaction dynamics with exact permutation symmetryde
dc.typejournalArticlede
dc.identifier.doi10.1039/C8CP06919K
dc.type.versionpublishedVersionde
dc.relation.pISSN1463-9076
dc.relation.eISSN1463-9084
dc.bibliographicCitation.volume21de
dc.bibliographicCitation.issue19de
dc.bibliographicCitation.firstPage9672de
dc.bibliographicCitation.lastPage9682de
dc.type.subtypejournalArticle
dc.identifier.pmid30672927
dc.description.statuspeerReviewedde
dc.bibliographicCitation.journalPhysical Chemistry Chemical Physicsde


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

These documents are avalilable under the license:
openAccess