Neural Partial Differential Equations for Chaotic Systems

Gelbrecht, Maximilian; Boers, Niklas; Kurths, Jürgen

doi:10.1088/1367-2630/abeb90

Datensatz

DATENSATZ AKTIONENEXPORT

Zur Ablage hinzufügen

Bitte beachten Sie, dass eine neuere Version dieses Datensatzes verfügbar ist:
https://publications.pik-potsdam.de/pubman/item/item_25408_4

DetailsÜbersicht

Freigegeben

Zeitschriftenartikel

Neural Partial Differential Equations for Chaotic Systems

Urheber*innen

/persons/resource/gelbrecht

Gelbrecht, Maximilian
Potsdam Institute for Climate Impact Research;

Boers, Niklas
External Organizations;

/persons/resource/Juergen.Kurths

Kurths, Jürgen
Potsdam Institute for Climate Impact Research;

Externe Ressourcen

Es sind keine externen Ressourcen hinterlegt

Volltexte (frei zugänglich)

Gelbrecht+et+al_2021_New_J._Phys._10.1088_1367-2630_abeb90.pdf
(Postprint), 8MB

Ergänzendes Material (frei zugänglich)

Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar

Zitation

Gelbrecht, M., Boers, N., Kurths, J. (2021 online): Neural Partial Differential Equations for Chaotic Systems. - New Journal of Physics.
https://doi.org/10.1088/1367-2630/abeb90

Zitierlink: https://publications.pik-potsdam.de/pubman/item/item_25408

Zusammenfassung

When predicting complex systems one typically relies on differential equation which can often be incomplete, missing unknown infl uences 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.