Articles | Volume 13, issue 5
https://doi.org/10.5194/gmd-13-2185-2020
© Author(s) 2020. 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-13-2185-2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Coupled online learning as a way to tackle instabilities and biases in neural network parameterizations: general algorithms and Lorenz 96 case study (v1.0)
Department of Informatics, Technical University of Munich, Munich, Germany
Viewed
Total article views: 4,982 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 07 Jan 2020)
HTML | XML | Total | BibTeX | EndNote | |
---|---|---|---|---|---|
3,286 | 1,627 | 69 | 4,982 | 104 | 90 |
- HTML: 3,286
- PDF: 1,627
- XML: 69
- Total: 4,982
- BibTeX: 104
- EndNote: 90
Total article views: 4,019 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 08 May 2020)
HTML | XML | Total | BibTeX | EndNote | |
---|---|---|---|---|---|
2,970 | 984 | 65 | 4,019 | 89 | 84 |
- HTML: 2,970
- PDF: 984
- XML: 65
- Total: 4,019
- BibTeX: 89
- EndNote: 84
Total article views: 963 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 07 Jan 2020)
HTML | XML | Total | BibTeX | EndNote | |
---|---|---|---|---|---|
316 | 643 | 4 | 963 | 15 | 6 |
- HTML: 316
- PDF: 643
- XML: 4
- Total: 963
- BibTeX: 15
- EndNote: 6
Viewed (geographical distribution)
Total article views: 4,982 (including HTML, PDF, and XML)
Thereof 4,555 with geography defined
and 427 with unknown origin.
Total article views: 4,019 (including HTML, PDF, and XML)
Thereof 3,688 with geography defined
and 331 with unknown origin.
Total article views: 963 (including HTML, PDF, and XML)
Thereof 867 with geography defined
and 96 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
46 citations as recorded by crossref.
- 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
- Development of a large-eddy simulation subgrid model based on artificial neural networks: a case study of turbulent channel flow R. Stoffer et al. 10.5194/gmd-14-3769-2021
- Spatio‐Temporal Super‐Resolution Data Assimilation (SRDA) Utilizing Deep Neural Networks With Domain Generalization Y. Yasuda & R. Onishi 10.1029/2023MS003658
- Correcting Weather and Climate Models by Machine Learning Nudged Historical Simulations O. Watt‐Meyer et al. 10.1029/2021GL092555
- How to Calibrate a Dynamical System With Neural Network Based Physics? B. Balogh et al. 10.1029/2022GL097872
- Deep Emulators for Differentiation, Forecasting, and Parametrization in Earth Science Simulators M. Nonnenmacher & D. Greenberg 10.1029/2021MS002554
- Stochastic rectification of fast oscillations on slow manifold closures M. Chekroun et al. 10.1073/pnas.2113650118
- Tutorial applications for Verification, Validation and Uncertainty Quantification using VECMA toolkit D. Suleimenova et al. 10.1016/j.jocs.2021.101402
- An Online‐Learned Neural Network Chemical Solver for Stable Long‐Term Global Simulations of Atmospheric Chemistry M. Kelp et al. 10.1029/2021MS002926
- Stable climate simulations using a realistic general circulation model with neural network parameterizations for atmospheric moist physics and radiation processes X. Wang et al. 10.5194/gmd-15-3923-2022
- Periodic orbits in chaotic systems simulated at low precision M. Klöwer et al. 10.1038/s41598-023-37004-4
- Using probabilistic machine learning to better model temporal patterns in parameterizations: a case study with the Lorenz 96 model R. Parthipan et al. 10.5194/gmd-16-4501-2023
- A Toy Model to Investigate Stability of AI‐Based Dynamical Systems B. Balogh et al. 10.1029/2020GL092133
- Machine learning parameterization of the multi-scale Kain–Fritsch (MSKF) convection scheme and stable simulation coupled in the Weather Research and Forecasting (WRF) model using WRF–ML v1.0 X. Zhong et al. 10.5194/gmd-17-3667-2024
- Stable machine-learning parameterization of subgrid processes for climate modeling at a range of resolutions J. Yuval & P. O’Gorman 10.1038/s41467-020-17142-3
- Deep reinforcement learning for turbulence modeling in large eddy simulations M. Kurz et al. 10.1016/j.ijheatfluidflow.2022.109094
- Deep-learning-driven simulations of boundary layer clouds over the Southern Great Plains T. Su & Y. Zhang 10.5194/gmd-17-6319-2024
- Advancing Artificial Neural Network Parameterization for Atmospheric Turbulence Using a Variational Multiscale Model M. Janssens & S. Hulshoff 10.1029/2021MS002490
- Advecting Superspecies: Efficiently Modeling Transport of Organic Aerosol With a Mass‐Conserving Dimensionality Reduction Method P. Sturm et al. 10.1029/2022MS003235
- Learning subgrid-scale models with neural ordinary differential equations S. Kang & E. Constantinescu 10.1016/j.compfluid.2023.105919
- Neural‐Network Parameterization of Subgrid Momentum Transport in the Atmosphere J. Yuval & P. O’Gorman 10.1029/2023MS003606
- Use of Neural Networks for Stable, Accurate and Physically Consistent Parameterization of Subgrid Atmospheric Processes With Good Performance at Reduced Precision J. Yuval et al. 10.1029/2020GL091363
- Developing intelligent Earth System Models: An AI framework for replacing sub-modules based on incremental learning and its application B. Mu et al. 10.1016/j.atmosres.2024.107306
- Physics-informed machine learning: case studies for weather and climate modelling K. Kashinath et al. 10.1098/rsta.2020.0093
- Pushing the frontiers in climate modelling and analysis with machine learning V. Eyring et al. 10.1038/s41558-024-02095-y
- Semi‐Automatic Tuning of Coupled Climate Models With Multiple Intrinsic Timescales: Lessons Learned From the Lorenz96 Model R. Lguensat et al. 10.1029/2022MS003367
- Compound Parameterization to Improve the Accuracy of Radiation Emulator in a Numerical Weather Prediction Model H. Song et al. 10.1029/2021GL095043
- Iterative integration of deep learning in hybrid Earth surface system modelling M. Chen et al. 10.1038/s43017-023-00452-7
- Deep learning subgrid-scale parametrisations for short-term forecasting of sea-ice dynamics with a Maxwell elasto-brittle rheology T. Finn et al. 10.5194/tc-17-2965-2023
- Updates on Model Hierarchies for Understanding and Simulating the Climate System: A Focus on Data‐Informed Methods and Climate Change Impacts L. Mansfield et al. 10.1029/2023MS003715
- 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
- Machine learning for numerical weather and climate modelling: a review C. de Burgh-Day & T. Leeuwenburg 10.5194/gmd-16-6433-2023
- Differentiable programming for Earth system modeling M. Gelbrecht et al. 10.5194/gmd-16-3123-2023
- A multifidelity deep operator network approach to closure for multiscale systems S. Ahmed & P. Stinis 10.1016/j.cma.2023.116161
- A Fast Time-Stepping Strategy for Dynamical Systems Equipped with a Surrogate Model S. Roberts et al. 10.1137/20M1386281
- Combining data assimilation and machine learning to infer unresolved scale parametrization J. Brajard et al. 10.1098/rsta.2020.0086
- Using neural networks to improve simulations in the gray zone R. Kriegmair et al. 10.5194/npg-29-171-2022
- TorchClim v1.0: a deep-learning plugin for climate model physics D. Fuchs et al. 10.5194/gmd-17-5459-2024
- Data assimilation empowered neural network parametrizations for subgrid processes in geophysical flows S. Pawar & O. San 10.1103/PhysRevFluids.6.050501
- Physics-informed learning of aerosol microphysics P. Harder et al. 10.1017/eds.2022.22
- Parameter sensitivity analysis of a sea ice melt pond parametrisation and its emulation using neural networks S. Driscoll et al. 10.1016/j.jocs.2024.102231
- Reduced data-driven turbulence closure for capturing long-term statistics R. Hoekstra et al. 10.1016/j.compfluid.2024.106469
- Data‐Driven Super‐Parameterization Using Deep Learning: Experimentation With Multiscale Lorenz 96 Systems and Transfer Learning A. Chattopadhyay et al. 10.1029/2020MS002084
- Online learning of both state and dynamics using ensemble Kalman filters M. Bocquet et al. 10.3934/fods.2020015
- Machine Learning Methods for Multiscale Physics and Urban Engineering Problems S. Sharma et al. 10.3390/e24081134
- Machine Learning in Weather Prediction and Climate Analyses—Applications and Perspectives B. Bochenek & Z. Ustrnul 10.3390/atmos13020180
42 citations as recorded by crossref.
- 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
- Development of a large-eddy simulation subgrid model based on artificial neural networks: a case study of turbulent channel flow R. Stoffer et al. 10.5194/gmd-14-3769-2021
- Spatio‐Temporal Super‐Resolution Data Assimilation (SRDA) Utilizing Deep Neural Networks With Domain Generalization Y. Yasuda & R. Onishi 10.1029/2023MS003658
- Correcting Weather and Climate Models by Machine Learning Nudged Historical Simulations O. Watt‐Meyer et al. 10.1029/2021GL092555
- How to Calibrate a Dynamical System With Neural Network Based Physics? B. Balogh et al. 10.1029/2022GL097872
- Deep Emulators for Differentiation, Forecasting, and Parametrization in Earth Science Simulators M. Nonnenmacher & D. Greenberg 10.1029/2021MS002554
- Stochastic rectification of fast oscillations on slow manifold closures M. Chekroun et al. 10.1073/pnas.2113650118
- Tutorial applications for Verification, Validation and Uncertainty Quantification using VECMA toolkit D. Suleimenova et al. 10.1016/j.jocs.2021.101402
- An Online‐Learned Neural Network Chemical Solver for Stable Long‐Term Global Simulations of Atmospheric Chemistry M. Kelp et al. 10.1029/2021MS002926
- Stable climate simulations using a realistic general circulation model with neural network parameterizations for atmospheric moist physics and radiation processes X. Wang et al. 10.5194/gmd-15-3923-2022
- Periodic orbits in chaotic systems simulated at low precision M. Klöwer et al. 10.1038/s41598-023-37004-4
- Using probabilistic machine learning to better model temporal patterns in parameterizations: a case study with the Lorenz 96 model R. Parthipan et al. 10.5194/gmd-16-4501-2023
- A Toy Model to Investigate Stability of AI‐Based Dynamical Systems B. Balogh et al. 10.1029/2020GL092133
- Machine learning parameterization of the multi-scale Kain–Fritsch (MSKF) convection scheme and stable simulation coupled in the Weather Research and Forecasting (WRF) model using WRF–ML v1.0 X. Zhong et al. 10.5194/gmd-17-3667-2024
- Stable machine-learning parameterization of subgrid processes for climate modeling at a range of resolutions J. Yuval & P. O’Gorman 10.1038/s41467-020-17142-3
- Deep reinforcement learning for turbulence modeling in large eddy simulations M. Kurz et al. 10.1016/j.ijheatfluidflow.2022.109094
- Deep-learning-driven simulations of boundary layer clouds over the Southern Great Plains T. Su & Y. Zhang 10.5194/gmd-17-6319-2024
- Advancing Artificial Neural Network Parameterization for Atmospheric Turbulence Using a Variational Multiscale Model M. Janssens & S. Hulshoff 10.1029/2021MS002490
- Advecting Superspecies: Efficiently Modeling Transport of Organic Aerosol With a Mass‐Conserving Dimensionality Reduction Method P. Sturm et al. 10.1029/2022MS003235
- Learning subgrid-scale models with neural ordinary differential equations S. Kang & E. Constantinescu 10.1016/j.compfluid.2023.105919
- Neural‐Network Parameterization of Subgrid Momentum Transport in the Atmosphere J. Yuval & P. O’Gorman 10.1029/2023MS003606
- Use of Neural Networks for Stable, Accurate and Physically Consistent Parameterization of Subgrid Atmospheric Processes With Good Performance at Reduced Precision J. Yuval et al. 10.1029/2020GL091363
- Developing intelligent Earth System Models: An AI framework for replacing sub-modules based on incremental learning and its application B. Mu et al. 10.1016/j.atmosres.2024.107306
- Physics-informed machine learning: case studies for weather and climate modelling K. Kashinath et al. 10.1098/rsta.2020.0093
- Pushing the frontiers in climate modelling and analysis with machine learning V. Eyring et al. 10.1038/s41558-024-02095-y
- Semi‐Automatic Tuning of Coupled Climate Models With Multiple Intrinsic Timescales: Lessons Learned From the Lorenz96 Model R. Lguensat et al. 10.1029/2022MS003367
- Compound Parameterization to Improve the Accuracy of Radiation Emulator in a Numerical Weather Prediction Model H. Song et al. 10.1029/2021GL095043
- Iterative integration of deep learning in hybrid Earth surface system modelling M. Chen et al. 10.1038/s43017-023-00452-7
- Deep learning subgrid-scale parametrisations for short-term forecasting of sea-ice dynamics with a Maxwell elasto-brittle rheology T. Finn et al. 10.5194/tc-17-2965-2023
- Updates on Model Hierarchies for Understanding and Simulating the Climate System: A Focus on Data‐Informed Methods and Climate Change Impacts L. Mansfield et al. 10.1029/2023MS003715
- 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
- Machine learning for numerical weather and climate modelling: a review C. de Burgh-Day & T. Leeuwenburg 10.5194/gmd-16-6433-2023
- Differentiable programming for Earth system modeling M. Gelbrecht et al. 10.5194/gmd-16-3123-2023
- A multifidelity deep operator network approach to closure for multiscale systems S. Ahmed & P. Stinis 10.1016/j.cma.2023.116161
- A Fast Time-Stepping Strategy for Dynamical Systems Equipped with a Surrogate Model S. Roberts et al. 10.1137/20M1386281
- Combining data assimilation and machine learning to infer unresolved scale parametrization J. Brajard et al. 10.1098/rsta.2020.0086
- Using neural networks to improve simulations in the gray zone R. Kriegmair et al. 10.5194/npg-29-171-2022
- TorchClim v1.0: a deep-learning plugin for climate model physics D. Fuchs et al. 10.5194/gmd-17-5459-2024
- Data assimilation empowered neural network parametrizations for subgrid processes in geophysical flows S. Pawar & O. San 10.1103/PhysRevFluids.6.050501
- Physics-informed learning of aerosol microphysics P. Harder et al. 10.1017/eds.2022.22
- Parameter sensitivity analysis of a sea ice melt pond parametrisation and its emulation using neural networks S. Driscoll et al. 10.1016/j.jocs.2024.102231
- Reduced data-driven turbulence closure for capturing long-term statistics R. Hoekstra et al. 10.1016/j.compfluid.2024.106469
4 citations as recorded by crossref.
- Data‐Driven Super‐Parameterization Using Deep Learning: Experimentation With Multiscale Lorenz 96 Systems and Transfer Learning A. Chattopadhyay et al. 10.1029/2020MS002084
- Online learning of both state and dynamics using ensemble Kalman filters M. Bocquet et al. 10.3934/fods.2020015
- Machine Learning Methods for Multiscale Physics and Urban Engineering Problems S. Sharma et al. 10.3390/e24081134
- Machine Learning in Weather Prediction and Climate Analyses—Applications and Perspectives B. Bochenek & Z. Ustrnul 10.3390/atmos13020180
Latest update: 08 Dec 2024
Short summary
Subgrid parameterizations are largely responsible for uncertainties in climate models. Recently, several studies tried to improve the representation of subgrid processes by learning parameterization directly from high-resolution modeling data. In this paper, the current state of the art of this research direction is summarized, and an algorithm is proposed to combat major problems with existing approaches, namely instabilities and biases.
Subgrid parameterizations are largely responsible for uncertainties in climate models. Recently,...