dc.contributor.author
Gelbrecht, Maximilian
dc.contributor.author
Boers, Niklas
dc.contributor.author
Kurths, Jürgen
dc.date.accessioned
2021-06-21T14:47:10Z
dc.date.available
2021-06-21T14:47:10Z
dc.identifier.uri
https://refubium.fu-berlin.de/handle/fub188/31103
dc.identifier.uri
http://dx.doi.org/10.17169/refubium-30839
dc.description.abstract
When predicting complex systems one typically relies on differential equation which can often be incomplete, missing unknown influences or higher order effects. By augmenting the equations with artificial neural networks we can compensate these deficiencies. We show that this can be used to predict paradigmatic, high-dimensional chaotic partial differential equations even when only short and incomplete datasets are available. The forecast horizon for these high dimensional systems is about an order of magnitude larger than the length of the training data.
en
dc.format.extent
10 Seiten
dc.rights.uri
https://creativecommons.org/licenses/by/4.0/
dc.subject
complex systems
en
dc.subject
nonlinear dynamics
en
dc.subject
machine learning
en
dc.subject
hybrid model
en
dc.subject
partial differential equations
en
dc.subject.ddc
500 Naturwissenschaften und Mathematik::530 Physik::530 Physik
dc.title
Neural partial differential equations for chaotic systems
dc.type
Wissenschaftlicher Artikel
dcterms.bibliographicCitation.articlenumber
043005
dcterms.bibliographicCitation.doi
10.1088/1367-2630/abeb90
dcterms.bibliographicCitation.journaltitle
New Journal of Physics
dcterms.bibliographicCitation.number
4
dcterms.bibliographicCitation.volume
23
dcterms.bibliographicCitation.url
https://doi.org/10.1088/1367-2630/abeb90
refubium.affiliation
Mathematik und Informatik
refubium.affiliation.other
Institut für Mathematik
![Dieser Normdateneintrag wurde von einer Benutzerin oder einem Benutzer als gültig bestätigt.](/cache_202e45ad85b55efaeb29160f63cd3f3b/themes/FuCD/images/authority_control/invisible.gif)
refubium.resourceType.isindependentpub
no
dcterms.accessRights.openaire
open access
dcterms.isPartOf.eissn
1367-2630
refubium.resourceType.provider
WoS-Alert