Molecular Dynamics with Neural Network Potentials

dc.contributor.authorGastegger, Michael
dc.contributor.authorMarquetand, Philipp
dc.date.accessioned2020-06-19T07:41:15Z
dc.date.available2020-06-19T07:41:15Z
dc.date.issued2020-06-04
dc.description.abstractMolecular dynamics simulations are an important tool for describing the evolution of a chemical system with time. However, these simulations are inherently held back either by the prohibitive cost of accurate electronic structure theory computations or the limited accuracy of classical empirical force fields. Machine learning techniques can help to overcome these limitations by providing access to potential energies, forces, and other molecular properties modeled directly after an accurate electronic structure reference at only a fraction of the original computational cost. The present text discusses several practical aspects of conducting machine learning driven molecular dynamics simulations. First, we study the efficient selection of reference data points on the basis of an active learning inspired adaptive sampling scheme. This is followed by the analysis of a machine learning based model for simulating molecular dipole moments in the framework of predicting infrared spectra via molecular dynamics simulations. Finally, we show that machine learning models can offer valuable aid in understanding chemical systems beyond a simple prediction of quantities.en
dc.description.sponsorshipEC/H2020/792572/EU/Machine Learning for Catalytic Carbon Dioxide Activation/MachineCaten
dc.identifier.eissn1616-6361
dc.identifier.isbn978-3-030-40245-7
dc.identifier.isbn978-3-030-40244-0
dc.identifier.issn0075-8450
dc.identifier.urihttps://depositonce.tu-berlin.de/handle/11303/11445
dc.identifier.urihttp://dx.doi.org/10.14279/depositonce-10326
dc.language.isoenen
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subject.ddc541 Physikalische Chemiede
dc.subject.ddc006 Spezielle Computerverfahrende
dc.subject.othermachine learningen
dc.subject.othermolecular dynamicsen
dc.subject.otherneural network potentialsen
dc.subject.otheractive learningen
dc.titleMolecular Dynamics with Neural Network Potentialsen
dc.typeBook Parten
dc.type.versionacceptedVersionen
dcterms.bibliographicCitation.booktitleMachine Learning Meets Quantum Physicsen
dcterms.bibliographicCitation.doi10.1007/978-3-030-40245-7_12en
dcterms.bibliographicCitation.editorSchütt, Kristof T.
dcterms.bibliographicCitation.editorChmiela, Stefan
dcterms.bibliographicCitation.editorvon Lilienfeld, Anatole
dcterms.bibliographicCitation.editorTkatchenko, Alexandre
dcterms.bibliographicCitation.editorTsuda, Koji
dcterms.bibliographicCitation.editorMüller, Klaus-Robert
dcterms.bibliographicCitation.originalpublishernameSpringeren
dcterms.bibliographicCitation.originalpublisherplaceChamen
dcterms.bibliographicCitation.pageend252
dcterms.bibliographicCitation.pagestart233
tub.accessrights.dnbdomain*
tub.affiliationFak. 4 Elektrotechnik und Informatik::Inst. Softwaretechnik und Theoretische Informatik::FG Maschinelles Lernende
tub.affiliation.facultyFak. 4 Elektrotechnik und Informatikde
tub.affiliation.groupFG Maschinelles Lernende
tub.affiliation.instituteInst. Softwaretechnik und Theoretische Informatikde
tub.publisher.universityorinstitutionTechnische Universität Berlinen
tub.series.issuenumber968en
tub.series.nameLecture Notes in Physicsen

Files

Original bundle
Now showing 1 - 1 of 1
Loading…
Thumbnail Image
Name:
gastegger_marquetand_2020.pdf
Size:
3.91 MB
Format:
Adobe Portable Document Format
Description:
Accepted manuscript
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.9 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections