Nonlinear Processes in Geophysics
Nonlinear Processes in Geophysics
NPG
Articles | Volume 28, issue 1
Articles | Volume 28, issue 1
https://doi.org/10.5194/npg-28-111-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/npg-28-111-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 28, issue 1
Research article
 | 
09 Feb 2021
Research article |  | 09 Feb 2021

Training a convolutional neural network to conserve mass in data assimilation

Yvonne Ruckstuhl, Tijana Janjić, and Stephan Rasp

Viewed

Total article views: 4,454 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
3,458 906 90 4,454 130 146
  • HTML: 3,458
  • PDF: 906
  • XML: 90
  • Total: 4,454
  • BibTeX: 130
  • EndNote: 146
Views and downloads (calculated since 25 Sep 2020)
Cumulative views and downloads (calculated since 25 Sep 2020)

Viewed (geographical distribution)

Total article views: 4,454 (including HTML, PDF, and XML) Thereof 4,117 with geography defined and 337 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Feb 2026
Download
Short summary
The assimilation of observations using standard algorithms can lead to a violation of physical laws (e.g. mass conservation), which is shown to have a detrimental impact on the system's forecast. We use a neural network (NN) to correct this mass violation, using training data generated from expensive algorithms that can constrain such physical properties. We found that, in an idealized set-up, the NN can match the performance of these expensive algorithms at negligible computational costs.
Read more
Share