Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-10466
For citation please use:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWestermayr, Julia-
dc.contributor.authorGastegger, Michael-
dc.contributor.authorMenger, Maximilian F. S. J.-
dc.contributor.authorMai, Sebastian-
dc.contributor.authorGonzález, Leticia-
dc.contributor.authorMarquetand, Philipp-
dc.date.accessioned2020-08-19T09:54:26Z-
dc.date.available2020-08-19T09:54:26Z-
dc.date.issued2019-08-05-
dc.identifier.issn2041-6520-
dc.identifier.urihttps://depositonce.tu-berlin.de/handle/11303/11579-
dc.identifier.urihttp://dx.doi.org/10.14279/depositonce-10466-
dc.description.abstractPhoto-induced processes are fundamental in nature but accurate simulations of their dynamics are seriously limited by the cost of the underlying quantum chemical calculations, hampering their application for long time scales. Here we introduce a method based on machine learning to overcome this bottleneck and enable accurate photodynamics on nanosecond time scales, which are otherwise out of reach with contemporary approaches. Instead of expensive quantum chemistry during molecular dynamics simulations, we use deep neural networks to learn the relationship between a molecular geometry and its high-dimensional electronic properties. As an example, the time evolution of the methylenimmonium cation for one nanosecond is used to demonstrate that machine learning algorithms can outperform standard excited-state molecular dynamics approaches in their computational efficiency while delivering the same accuracy.en
dc.description.sponsorshipEC/H2020/792572/EU/Machine Learning for Catalytic Carbon Dioxide Activation/MachineCaten
dc.language.isoenen
dc.rights.urihttps://creativecommons.org/licenses/by/3.0/en
dc.subject.ddc540 Chemie und zugeordnete Wissenschaftende
dc.subject.otherdeep neural networksen
dc.subject.othermachine learningen
dc.subject.othermolecular photodynamics simulationsen
dc.titleMachine learning enables long time scale molecular photodynamics simulationsen
dc.typeArticleen
tub.accessrights.dnbfreeen
tub.publisher.universityorinstitutionTechnische Universität Berlinen
dc.identifier.eissn2041-6539-
dc.type.versionpublishedVersionen
dcterms.bibliographicCitation.doi10.1039/C9SC01742Aen
dcterms.bibliographicCitation.journaltitleChemical Scienceen
dcterms.bibliographicCitation.originalpublisherplaceCambridgeen
dcterms.bibliographicCitation.volume10en
dcterms.bibliographicCitation.pageend8107en
dcterms.bibliographicCitation.pagestart8100en
dcterms.bibliographicCitation.originalpublishernameRoyal Society of Chemistry (RSC)en
tub.affiliationFak. 4 Elektrotechnik und Informatik » Inst. Softwaretechnik und Theoretische Informatik » FG Maschinelles Lernende
Appears in Collections:Technische Universität Berlin » Publications

Files in This Item:
c9sc01742a.pdf
Format: Adobe PDF | Size: 2.27 MB
DownloadShow Preview
Thumbnail

Item Export Bar

This item is licensed under a Creative Commons License Creative Commons