English
 
Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Neural partial differential equations for chaotic systems

Gelbrecht, M., Boers, N., Kurths, J. (2021): Neural partial differential equations for chaotic systems. - New Journal of Physics, 23, 043005.
https://doi.org/10.1088/1367-2630/abeb90

Item is

Basic

show hide
Item Permalink: https://publications.pik-potsdam.de/pubman/item/item_25408 Version Permalink: https://publications.pik-potsdam.de/pubman/item/item_25408_2
Genre: Journal Article

Files

show Files
hide Files
:
25408oa.pdf (Publisher version), 6MB
Name:
25408oa.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Gelbrecht, Maximilian1, Author              
Boers, Niklas1, Author              
Kurths, Jürgen1, Author              
Affiliations:
1Potsdam Institute for Climate Impact Research, Potsdam, ou_persistent13              

Content

show
hide
Free keywords: -
 Abstract: 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.

Details

show
hide
Language(s):
 Dates: 2021-03-032021-03-032021-04-02
 Publication Status: Finally published
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: DOI: 10.1088/1367-2630/abeb90
PIKDOMAIN: RD4 - Complexity Science
Organisational keyword: RD4 - Complexity Science
MDB-ID: pending
Research topic keyword: Nonlinear Dynamics
Organisational keyword: FutureLab - Artificial Intelligence in the Anthropocene
Model / method: Machine Learning
Model / method: Nonlinear Data Analysis
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: New Journal of Physics
Source Genre: Journal, SCI, Scopus, p3, oa
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 23 Sequence Number: 043005 Start / End Page: - Identifier: CoNE: https://publications.pik-potsdam.de/cone/journals/resource/1911272
Publisher: IOP Publishing