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.
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.
the Creative Commons Attribution 4.0 License.
Research article
| 
09 Feb 2021
Research article |
| 09 Feb 2021
| 09 Feb 2021
Training a convolutional neural network to conserve mass in data assimilation
Yvonne Ruckstuhl
CORRESPONDING AUTHOR
Meteorological Institute Munich, Ludwig-Maximilians-Universität München, Munich, Germany
Tijana Janjić
Meteorological Institute Munich, Ludwig-Maximilians-Universität München, Munich, Germany
Stephan Rasp
ClimateAi, San Francisco, CA, USA
Viewed
Total article views: 3,185 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 25 Sep 2020)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 2,423 | 703 | 59 | 3,185 | 62 | 50 |
- HTML: 2,423
- PDF: 703
- XML: 59
- Total: 3,185
- BibTeX: 62
- EndNote: 50
Total article views: 2,134 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 09 Feb 2021)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 1,612 | 468 | 54 | 2,134 | 51 | 40 |
- HTML: 1,612
- PDF: 468
- XML: 54
- Total: 2,134
- BibTeX: 51
- EndNote: 40
Total article views: 1,051 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 25 Sep 2020)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 811 | 235 | 5 | 1,051 | 11 | 10 |
- HTML: 811
- PDF: 235
- XML: 5
- Total: 1,051
- BibTeX: 11
- EndNote: 10
Viewed (geographical distribution)
Total article views: 3,185 (including HTML, PDF, and XML)
Thereof 2,902 with geography defined
and 283 with unknown origin.
Total article views: 2,134 (including HTML, PDF, and XML)
Thereof 2,035 with geography defined
and 99 with unknown origin.
Total article views: 1,051 (including HTML, PDF, and XML)
Thereof 867 with geography defined
and 184 with unknown origin.
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
Cited
18 citations as recorded by crossref.
- Ensemble Kalman filter based data assimilation for tropical waves in the MJO skeleton model T. Gleiter et al. 10.1002/qj.4245
- Equation‐Free Surrogate Modeling of Geophysical Flows at the Intersection of Machine Learning and Data Assimilation S. Pawar & O. San 10.1029/2022MS003170
- Convergence of forecast distributions in a 100,000‐member idealised convective‐scale ensemble K. Tempest et al. 10.1002/qj.4410
- Combining Stochastic Parameterized Reduced‐Order Models With Machine Learning for Data Assimilation and Uncertainty Quantification With Partial Observations C. Mou et al. 10.1029/2022MS003597
- The effectiveness of machine learning methods in the nonlinear coupled data assimilation Z. Xuan et al. 10.1186/s40562-024-00347-5
- Towards neural Earth system modelling by integrating artificial intelligence in Earth system science C. Irrgang et al. 10.1038/s42256-021-00374-3
- Statistical variational data assimilation A. Benaceur & B. Verfürth 10.1016/j.cma.2024.117402
- Assessing the Physical Realism of Deep Learning Hydrologic Model Projections Under Climate Change S. Wi & S. Steinschneider 10.1029/2022WR032123
- Power line fault diagnosis based on convolutional neural networks L. Ning & D. Pei 10.1016/j.heliyon.2024.e29021
- Combining data assimilation and machine learning to estimate parameters of a convective‐scale model S. Legler & T. Janjić 10.1002/qj.4235
- Optimal sensor placement for ensemble-based data assimilation using gradient-weighted class activation mapping Z. Xu et al. 10.1016/j.jcp.2024.113224
- Super-Resolving Ocean Dynamics from Space with Computer Vision Algorithms B. Buongiorno Nardelli et al. 10.3390/rs14051159
- Integrating Recurrent Neural Networks With Data Assimilation for Scalable Data‐Driven State Estimation S. Penny et al. 10.1029/2021MS002843
- Weakly Constrained LETKF for Estimation of Hydrometeor Variables in Convective‐Scale Data Assimilation T. Janjić & Y. Zeng 10.1029/2021GL094962
- Advancements and Challenges in Deep Learning-Driven Marine Data Assimilation: A Comprehensive Review Y. Ma et al. 10.61186/crpase.9.4.2876
- Robot control system based on deep learning and RPA Y. Ren et al. 10.3233/JIFS-233056
- Modeling and control strategy of small unmanned helicopter rotation based on deep learning H. Xia 10.1016/j.sasc.2024.200146
- Using neural networks to improve simulations in the gray zone R. Kriegmair et al. 10.5194/npg-29-171-2022
18 citations as recorded by crossref.
- Ensemble Kalman filter based data assimilation for tropical waves in the MJO skeleton model T. Gleiter et al. 10.1002/qj.4245
- Equation‐Free Surrogate Modeling of Geophysical Flows at the Intersection of Machine Learning and Data Assimilation S. Pawar & O. San 10.1029/2022MS003170
- Convergence of forecast distributions in a 100,000‐member idealised convective‐scale ensemble K. Tempest et al. 10.1002/qj.4410
- Combining Stochastic Parameterized Reduced‐Order Models With Machine Learning for Data Assimilation and Uncertainty Quantification With Partial Observations C. Mou et al. 10.1029/2022MS003597
- The effectiveness of machine learning methods in the nonlinear coupled data assimilation Z. Xuan et al. 10.1186/s40562-024-00347-5
- Towards neural Earth system modelling by integrating artificial intelligence in Earth system science C. Irrgang et al. 10.1038/s42256-021-00374-3
- Statistical variational data assimilation A. Benaceur & B. Verfürth 10.1016/j.cma.2024.117402
- Assessing the Physical Realism of Deep Learning Hydrologic Model Projections Under Climate Change S. Wi & S. Steinschneider 10.1029/2022WR032123
- Power line fault diagnosis based on convolutional neural networks L. Ning & D. Pei 10.1016/j.heliyon.2024.e29021
- Combining data assimilation and machine learning to estimate parameters of a convective‐scale model S. Legler & T. Janjić 10.1002/qj.4235
- Optimal sensor placement for ensemble-based data assimilation using gradient-weighted class activation mapping Z. Xu et al. 10.1016/j.jcp.2024.113224
- Super-Resolving Ocean Dynamics from Space with Computer Vision Algorithms B. Buongiorno Nardelli et al. 10.3390/rs14051159
- Integrating Recurrent Neural Networks With Data Assimilation for Scalable Data‐Driven State Estimation S. Penny et al. 10.1029/2021MS002843
- Weakly Constrained LETKF for Estimation of Hydrometeor Variables in Convective‐Scale Data Assimilation T. Janjić & Y. Zeng 10.1029/2021GL094962
- Advancements and Challenges in Deep Learning-Driven Marine Data Assimilation: A Comprehensive Review Y. Ma et al. 10.61186/crpase.9.4.2876
- Robot control system based on deep learning and RPA Y. Ren et al. 10.3233/JIFS-233056
- Modeling and control strategy of small unmanned helicopter rotation based on deep learning H. Xia 10.1016/j.sasc.2024.200146
- Using neural networks to improve simulations in the gray zone R. Kriegmair et al. 10.5194/npg-29-171-2022
Latest update: 21 Nov 2024
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.
The assimilation of observations using standard algorithms can lead to a violation of physical...
