Articles | Volume 14, issue 12
https://doi.org/10.5194/gmd-14-7425-2021
© 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/gmd-14-7425-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Robustness of neural network emulations of radiative transfer parameterizations in a state-of-the-art general circulation model
Alexei Belochitski
CORRESPONDING AUTHOR
IMSG, Rockville, MD 20852, USA
NOAA/NWS/NCEP/EMC, College Park, MD 20740, USA
Vladimir Krasnopolsky
NOAA/NWS/NCEP/EMC, College Park, MD 20740, USA
Viewed
Total article views: 3,523 (including HTML, PDF, and XML)
HTML | XML | Total | BibTeX | EndNote | |
---|---|---|---|---|---|
1,425 | 2,018 | 80 | 3,523 | 49 | 50 |
- HTML: 1,425
- PDF: 2,018
- XML: 80
- Total: 3,523
- BibTeX: 49
- EndNote: 50
Cumulative views and downloads
(calculated since 31 May 2021)
Total article views: 2,767 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 06 Dec 2021)
HTML | XML | Total | BibTeX | EndNote | |
---|---|---|---|---|---|
1,021 | 1,686 | 60 | 2,767 | 43 | 44 |
- HTML: 1,021
- PDF: 1,686
- XML: 60
- Total: 2,767
- BibTeX: 43
- EndNote: 44
Total article views: 756 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 31 May 2021)
HTML | XML | Total | BibTeX | EndNote | |
---|---|---|---|---|---|
404 | 332 | 20 | 756 | 6 | 6 |
- HTML: 404
- PDF: 332
- XML: 20
- Total: 756
- BibTeX: 6
- EndNote: 6
Viewed (geographical distribution)
Total article views: 3,523 (including HTML, PDF, and XML)
Thereof 3,330 with geography defined
and 193 with unknown origin.
Total article views: 2,767 (including HTML, PDF, and XML)
Thereof 2,668 with geography defined
and 99 with unknown origin.
Total article views: 756 (including HTML, PDF, and XML)
Thereof 662 with geography defined
and 94 with unknown origin.
Country | # | Views | % |
---|---|---|---|
United States of America | 1 | 1540 | 43 |
China | 2 | 402 | 11 |
Ireland | 3 | 298 | 8 |
Germany | 4 | 151 | 4 |
India | 5 | 107 | 3 |
Country | # | Views | % |
---|---|---|---|
United States of America | 1 | 1228 | 44 |
China | 2 | 339 | 12 |
Ireland | 3 | 267 | 9 |
Germany | 4 | 116 | 4 |
India | 5 | 99 | 3 |
Country | # | Views | % |
---|---|---|---|
United States of America | 1 | 312 | 41 |
China | 2 | 63 | 8 |
Germany | 3 | 35 | 4 |
Ireland | 4 | 31 | 4 |
Netherlands | 5 | 31 | 4 |
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1
- 1540
1
1540
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1
- 1228
1
1228
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1
- 312
1
312
Cited
16 citations as recorded by crossref.
- A Physics‐Incorporated Deep Learning Framework for Parameterization of Atmospheric Radiative Transfer Y. Yao et al. 10.1029/2022MS003445
- Improved Weather Forecasting Using Neural Network Emulation for Radiation Parameterization H. Song & S. Roh 10.1029/2021MS002609
- Applying Machine Learning in Numerical Weather and Climate Modeling Systems V. Krasnopolsky 10.3390/cli12060078
- MieAI: a neural network for calculating optical properties of internally mixed aerosol in atmospheric models P. Kumar et al. 10.1038/s41612-024-00652-y
- WRF–ML v1.0: a bridge between WRF v4.3 and machine learning parameterizations and its application to atmospheric radiative transfer X. Zhong et al. 10.5194/gmd-16-199-2023
- Efficient and stable coupling of the SuperdropNet deep-learning-based cloud microphysics (v0.1.0) with the ICON climate and weather model (v2.6.5) C. Arnold et al. 10.5194/gmd-17-4017-2024
- Forecasting the June Ridge Line of the Western Pacific Subtropical High with a Machine Learning Method C. Sun et al. 10.3390/atmos13050660
- Impact of Horizontal Resolution on the Robustness of Radiation Emulators in a Numerical Weather Prediction Model H. Song & S. Roh 10.3390/rs15102637
- NeuralMie (v1.0): an aerosol optics emulator A. Geiss & P. Ma 10.5194/gmd-18-1809-2025
- Usefulness of Automatic Hyperparameter Optimization in Developing Radiation Emulator in a Numerical Weather Prediction Model P. Kim & H. Song 10.3390/atmos13050721
- Neural emulator based on physical fields for accelerating the simulation of surface chlorophyll in an Earth System Model B. Wu et al. 10.1016/j.ocemod.2024.102491
- Benefits of Stochastic Weight Averaging in Developing Neural Network Radiation Scheme for Numerical Weather Prediction H. Song et al. 10.1029/2021MS002921
- Neural‐Network Parameterization of Subgrid Momentum Transport in the Atmosphere J. Yuval & P. O’Gorman 10.1029/2023MS003606
- A radiative transfer deep learning model coupled into WRF with a generic fortran torch adaptor B. Mu et al. 10.3389/feart.2023.1149566
- Robustness of neural network emulations of radiative transfer parameterizations in a state-of-the-art general circulation model A. Belochitski & V. Krasnopolsky 10.5194/gmd-14-7425-2021
- Effects of Cloud Microphysics on the Universal Performance of Neural Network Radiation Scheme H. Song & P. Kim 10.1029/2022GL098601
11 citations as recorded by crossref.
- A Physics‐Incorporated Deep Learning Framework for Parameterization of Atmospheric Radiative Transfer Y. Yao et al. 10.1029/2022MS003445
- Improved Weather Forecasting Using Neural Network Emulation for Radiation Parameterization H. Song & S. Roh 10.1029/2021MS002609
- Applying Machine Learning in Numerical Weather and Climate Modeling Systems V. Krasnopolsky 10.3390/cli12060078
- MieAI: a neural network for calculating optical properties of internally mixed aerosol in atmospheric models P. Kumar et al. 10.1038/s41612-024-00652-y
- WRF–ML v1.0: a bridge between WRF v4.3 and machine learning parameterizations and its application to atmospheric radiative transfer X. Zhong et al. 10.5194/gmd-16-199-2023
- Efficient and stable coupling of the SuperdropNet deep-learning-based cloud microphysics (v0.1.0) with the ICON climate and weather model (v2.6.5) C. Arnold et al. 10.5194/gmd-17-4017-2024
- Forecasting the June Ridge Line of the Western Pacific Subtropical High with a Machine Learning Method C. Sun et al. 10.3390/atmos13050660
- Impact of Horizontal Resolution on the Robustness of Radiation Emulators in a Numerical Weather Prediction Model H. Song & S. Roh 10.3390/rs15102637
- NeuralMie (v1.0): an aerosol optics emulator A. Geiss & P. Ma 10.5194/gmd-18-1809-2025
- Usefulness of Automatic Hyperparameter Optimization in Developing Radiation Emulator in a Numerical Weather Prediction Model P. Kim & H. Song 10.3390/atmos13050721
- Neural emulator based on physical fields for accelerating the simulation of surface chlorophyll in an Earth System Model B. Wu et al. 10.1016/j.ocemod.2024.102491
5 citations as recorded by crossref.
- Benefits of Stochastic Weight Averaging in Developing Neural Network Radiation Scheme for Numerical Weather Prediction H. Song et al. 10.1029/2021MS002921
- Neural‐Network Parameterization of Subgrid Momentum Transport in the Atmosphere J. Yuval & P. O’Gorman 10.1029/2023MS003606
- A radiative transfer deep learning model coupled into WRF with a generic fortran torch adaptor B. Mu et al. 10.3389/feart.2023.1149566
- Robustness of neural network emulations of radiative transfer parameterizations in a state-of-the-art general circulation model A. Belochitski & V. Krasnopolsky 10.5194/gmd-14-7425-2021
- Effects of Cloud Microphysics on the Universal Performance of Neural Network Radiation Scheme H. Song & P. Kim 10.1029/2022GL098601
Latest update: 05 Apr 2025
Short summary
There is a lot interest in using machine learning (ML) techniques to improve environmental models by replacing physically based model components with ML-derived ones. The latter ordinarily demonstrate excellent results when tested in a stand-alone setting but can break their host model either outright when coupled to it or eventually when the model changes. We built an ML component that not only does not destabilize its host model but is also robust with respect to substantial changes in it.
There is a lot interest in using machine learning (ML) techniques to improve environmental...
Similar articles
From weather data to river runoff: using...
Börgel et al.
A Fortran–Python interface for...
Zhang et al.
A rapid-application emissions-to-impacts...
Mathison et al.