1. osnaDocs
  2. Fachbereich 08 - Humanwissenschaften
  3. FB08 - Hochschulschriften

A trajectory-based loss function to learn missing terms in bifurcating dynamical systems

Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
https://doi.org/10.48693/230
Open Access logo originally created by the Public Library of Science (PLoS)
Langanzeige der Metadaten
DC ElementWertSprache
dc.creatorVortmeyer-Kley, Rahel-
dc.creatorNieters, Pascal-
dc.creatorPipa, Gordon-
dc.date.accessioned2023-01-27T08:29:02Z-
dc.date.available2023-01-27T08:29:02Z-
dc.date.issued2021-10-14-
dc.identifier.citationVortmeyer-Kley, R., Nieters, P. & Pipa, G: A trajectory-based loss function to learn missing terms in bifurcating dynamical systems. Sci Rep 11, 20394 (2021).ger
dc.identifier.urihttps://doi.org/10.48693/230-
dc.identifier.urihttps://osnadocs.ub.uni-osnabrueck.de/handle/ds-202301278055-
dc.description.abstractMissing terms in dynamical systems are a challenging problem for modeling. Recent developments in the combination of machine learning and dynamical system theory open possibilities for a solution. We show how physics-informed differential equations and machine learning—combined in the Universal Differential Equation (UDE) framework by Rackauckas et al.—can be modified to discover missing terms in systems that undergo sudden fundamental changes in their dynamical behavior called bifurcations. With this we enable the application of the UDE approach to a wider class of problems which are common in many real world applications. The choice of the loss function, which compares the training data trajectory in state space and the current estimated solution trajectory of the UDE to optimize the solution, plays a crucial role within this approach. The Mean Square Error as loss function contains the risk of a reconstruction which completely misses the dynamical behavior of the training data. By contrast, our suggested trajectory-based loss function which optimizes two largely independent components, the length and angle of state space vectors of the training data, performs reliable well in examples of systems from neuroscience, chemistry and biology showing Saddle-Node, Pitchfork, Hopf and Period-doubling bifurcations.eng
dc.relationhttps://doi.org/10.1038/s41598-021-99609-xger
dc.rightsAttribution 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectComputational scienceeng
dc.subjectNonlinear phenomenaeng
dc.subject.ddc004 - Informatikger
dc.titleA trajectory-based loss function to learn missing terms in bifurcating dynamical systemseng
dc.typeEinzelbeitrag in einer wissenschaftlichen Zeitschrift [Article]ger
orcid.creatorhttps://orcid.org/0000-0002-3416-2652-
dc.identifier.doi10.1038/s41598-021-99609-x-
Enthalten in den Sammlungen:FB08 - Hochschulschriften
Open-Access-Publikationsfonds

Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat 
SciReports_Vortmeyer-Kley_etal_2021.pdfArticle2,68 MBAdobe PDF
SciReports_Vortmeyer-Kley_etal_2021.pdf
Miniaturbild
Öffnen/Anzeigen
Zur Kurzanzeige


Diese Ressource wurde unter folgender Copyright-Bestimmung veröffentlicht: Lizenz von Creative Commons Creative Commons