Articles | Volume 28, issue 1
Nonlin. Processes Geophys., 28, 111–119, 2021
https://doi.org/10.5194/npg-28-111-2021
Nonlin. Processes Geophys., 28, 111–119, 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 et al.

Model code and software

CNN to conserve mass in data assimilation Yvonne Ruckstuhl, Stephan Rasp, Michael Würsch, and Tijana Janjic https://doi.org/10.5281/zenodo.4354602

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.