Nonlinear Processes in Geophysics
Nonlinear Processes in Geophysics
NPG
Articles | Volume 31, issue 3
Articles | Volume 31, issue 3
https://doi.org/10.5194/npg-31-409-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/npg-31-409-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 31, issue 3
Research article
 | Highlight paper
 | 
19 Sep 2024
Research article | Highlight paper |  | 19 Sep 2024

Representation learning with unconditional denoising diffusion models for dynamical systems

Tobias Sebastian Finn, Lucas Disson, Alban Farchi, Marc Bocquet, and Charlotte Durand

Viewed

Total article views: 9,757 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
7,573 1,471 713 9,757 309 395
  • HTML: 7,573
  • PDF: 1,471
  • XML: 713
  • Total: 9,757
  • BibTeX: 309
  • EndNote: 395
Views and downloads (calculated since 20 Oct 2023)
Cumulative views and downloads (calculated since 20 Oct 2023)

Viewed (geographical distribution)

Total article views: 9,757 (including HTML, PDF, and XML) Thereof 9,368 with geography defined and 389 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Saved (final revised paper)

Latest update: 27 Aug 2026
Download
Editorial statement
This paper tests the ability of Artificial Intelligence methods, and more specifically Deep Learning, to eliminate the Gaussian noise that disturbs the data of a dynamic system. The authors demonstrate this using a highly chaotic model as a hard test case.
Read more
Short summary
We train neural networks as denoising diffusion models for state generation in the Lorenz 1963 system and demonstrate that they learn an internal representation of the system. We make use of this learned representation and the pre-trained model in two downstream tasks: surrogate modelling and ensemble generation. For both tasks, the diffusion model can outperform other more common approaches. Thus, we see a potential of representation learning with diffusion models for dynamical systems.
Read more
Share