Title:
Neural partial differential equations for chaotic systems
Author(s):
Gelbrecht, Maximilian; Boers, Niklas; Kurths, Jürgen
Year of publication:
2021
Available Date:
2021-06-21T14:47:10Z
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.
Part of Identifier:
e-ISSN (online): 1367-2630
Keywords:
complex systems
nonlinear dynamics
prediction
machine learning
hybrid model
partial differential equations
DDC-Classification:
530 Physik
Publication Type:
Wissenschaftlicher Artikel
URL of the Original Publication:
DOI of the Original Publication:
Journaltitle:
New Journal of Physics
Department/institution:
Mathematik und Informatik
Institut für Mathematik