Articles | Volume 28, issue 1
https://doi.org/10.5194/npg-28-111-2021
https://doi.org/10.5194/npg-28-111-2021
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: 2,834 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
2,174 630 30 2,834 45 32
  • HTML: 2,174
  • PDF: 630
  • XML: 30
  • Total: 2,834
  • BibTeX: 45
  • EndNote: 32
Views and downloads (calculated since 25 Sep 2020)
Cumulative views and downloads (calculated since 25 Sep 2020)

Viewed (geographical distribution)

Total article views: 2,834 (including HTML, PDF, and XML) Thereof 2,574 with geography defined and 260 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 02 Mar 2024
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.