Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Generalization properties of feed-forward neural networks trained on Lorenz systems
Stockholm Univ, Dept Meteorol, Stockholm, Sweden;Stockholm Univ, Bolin Ctr Climate Res, Stockholm, Sweden.
Uppsala University, Disciplinary Domain of Science and Technology, Earth Sciences, Department of Earth Sciences, LUVAL. Stockholm Univ, Dept Meteorol, Stockholm, Sweden;Stockholm Univ, Bolin Ctr Climate Res, Stockholm, Sweden.ORCID iD: 0000-0002-2032-5211
2019 (English)In: Nonlinear processes in geophysics, ISSN 1023-5809, E-ISSN 1607-7946, Vol. 26, no 4, p. 381-399Article in journal (Refereed) Published
Abstract [en]

Neural networks are able to approximate chaotic dynamical systems when provided with training data that cover all relevant regions of the system's phase space. However, many practical applications diverge from this idealized scenario. Here, we investigate the ability of feed-forward neural networks to (1) learn the behavior of dynamical systems from incomplete training data and (2) learn the influence of an external forcing on the dynamics Climate science is a real-world example where these questions may be relevant: it is concerned with a non-stationary chaotic system subject to external forcing and whose behavior is known only through comparatively short data series. Our analysis is performed on the Lorenz63 and Lorenz95 models. We show that for the Lorenz63 system, neural networks trained on data covering only part of the system's phase space struggle to make skillful short-term forecasts in the regions excluded from the training Additionally, when making long series of consecutive forecasts, the networks struggle to reproduce trajectories exploring regions beyond those seen in the training data, except for cases where only small parts are left out during training. We find this is due to the neural network learning a localized mapping for each region of phase space in the training data rather than a global mapping. This manifests itself in that parts of the networks learn only particular parts of the phase space. In contrast, for the Lorenz95 system the networks succeed in generalizing to new parts of the phase space not seen in the training data. We also find that the networks are able to learn the influence of an external forcing, but only when given relatively large ranges of the forcing in the training These results point to potential limitations of feed-forward neural networks in generalizing a system's behavior given limited initial information. Much attention must therefore be given to designing appropriate train-test splits for real-world applications.

Place, publisher, year, edition, pages
2019. Vol. 26, no 4, p. 381-399
National Category
Meteorology and Atmospheric Sciences Geosciences, Multidisciplinary
Identifiers
URN: urn:nbn:se:uu:diva-397963DOI: 10.5194/npg-26-381-2019ISI: 000495389400001OAI: oai:DiVA.org:uu-397963DiVA, id: diva2:1376038
Funder
Swedish Research Council, 2016-03724Available from: 2019-12-06 Created: 2019-12-06 Last updated: 2019-12-06Bibliographically approved

Open Access in DiVA

fulltext(8156 kB)23 downloads
File information
File name FULLTEXT01.pdfFile size 8156 kBChecksum SHA-512
f04dc07ebd1ff9ad328ca954ca72c7a59737d82bea4fbba56eeff4c9e642a695436bc2ecc094efc3f6f228ec9790f750ab7dc90c5364ff923c96ed60e7fb589b
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Messori, Gabriele
By organisation
LUVAL
In the same journal
Nonlinear processes in geophysics
Meteorology and Atmospheric SciencesGeosciences, Multidisciplinary

Search outside of DiVA

GoogleGoogle Scholar
Total: 23 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 278 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf