Articles | Volume 15, issue 5
https://doi.org/10.5194/gmd-15-2221-2022
© Author(s) 2022. 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-15-2221-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Development and technical paper
| 
16 Mar 2022
Development and technical paper |
| 16 Mar 2022
| 16 Mar 2022
Towards physics-inspired data-driven weather forecasting: integrating data assimilation with a deep spatial-transformer-based U-NET in a case study with ERA5
Ashesh Chattopadhyay
Department of Mechanical Engineering, Rice University, Houston, TX, USA
Lawrence Berkeley National Laboratory, Berkeley, CA, USA
Mustafa Mustafa
Lawrence Berkeley National Laboratory, Berkeley, CA, USA
Department of Mechanical Engineering, Rice University, Houston, TX, USA
Department of Earth, Environmental and Planetary Sciences, Rice University, Houston, TX, USA
Eviatar Bach
Department of Atmospheric and Oceanic Science and Institute for Physical Science and Technology, University of Maryland, College Park, USA
Geosciences Department and Laboratoire de Météorologie Dynamique (CNRS and IPSL), École Normale Supérieure and PSL University, Paris, France
Karthik Kashinath
Lawrence Berkeley National Laboratory, Berkeley, CA, USA
Viewed
Total article views: 9,019 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 12 Apr 2021)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 6,031 | 2,806 | 182 | 9,019 | 176 | 206 |
- HTML: 6,031
- PDF: 2,806
- XML: 182
- Total: 9,019
- BibTeX: 176
- EndNote: 206
Total article views: 6,705 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 16 Mar 2022)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 4,873 | 1,686 | 146 | 6,705 | 146 | 182 |
- HTML: 4,873
- PDF: 1,686
- XML: 146
- Total: 6,705
- BibTeX: 146
- EndNote: 182
Total article views: 2,314 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 12 Apr 2021)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 1,158 | 1,120 | 36 | 2,314 | 30 | 24 |
- HTML: 1,158
- PDF: 1,120
- XML: 36
- Total: 2,314
- BibTeX: 30
- EndNote: 24
Viewed (geographical distribution)
Total article views: 9,019 (including HTML, PDF, and XML)
Thereof 8,574 with geography defined
and 445 with unknown origin.
Total article views: 6,705 (including HTML, PDF, and XML)
Thereof 6,401 with geography defined
and 304 with unknown origin.
Total article views: 2,314 (including HTML, PDF, and XML)
Thereof 2,173 with geography defined
and 141 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
33 citations as recorded by crossref.
- Deep Learning-Enhanced Ensemble-Based Data Assimilation for High-Dimensional Nonlinear Dynamical Systems A. Chattopadhyay et al. https://doi.org/10.2139/ssrn.4142015
- Learning spatiotemporal chaos using next-generation reservoir computing W. Barbosa & D. Gauthier https://doi.org/10.1063/5.0098707
- Statistical Deep Learning for Spatial and Spatiotemporal Data C. Wikle & A. Zammit-Mangion https://doi.org/10.1146/annurev-statistics-033021-112628
- Artificial Intelligence techniques in data assimilation: Emerging approaches, key challenges, and future prospects W. Wang et al. https://doi.org/10.1007/s11430-025-1807-8
- Deep learning-enhanced ensemble-based data assimilation for high-dimensional nonlinear dynamical systems A. Chattopadhyay et al. https://doi.org/10.1016/j.jcp.2023.111918
- Machine Learning for Climate Physics and Simulations C. Lai et al. https://doi.org/10.1146/annurev-conmatphys-043024-114758
- Long-term stability and generalization of observationally-constrained stochastic data-driven models for geophysical turbulence A. Chattopadhyay et al. https://doi.org/10.1017/eds.2022.30
- Key factors for quantitative precipitation nowcasting using ground weather radar data based on deep learning D. Han et al. https://doi.org/10.5194/gmd-16-5895-2023
- Generative Lagrangian data assimilation for ocean dynamics under extreme sparsity N. Asefi et al. https://doi.org/10.1088/3049-4753/ae0b70
- Equation‐Free Surrogate Modeling of Geophysical Flows at the Intersection of Machine Learning and Data Assimilation S. Pawar & O. San https://doi.org/10.1029/2022MS003170
- A Novel Transformer Network With Shifted Window Cross-Attention for Spatiotemporal Weather Forecasting A. Bojesomo et al. https://doi.org/10.1109/JSTARS.2023.3323729
- Long-Time Accuracy of Ensemble Kalman Filters for Chaotic Dynamical Systems and Machine-Learned Dynamical Systems D. Sanz-Alonso & N. Waniorek https://doi.org/10.1137/24M1719232
- Ensemble data assimilation to diagnose AI-based weather prediction models: a case with ClimaX version 0.3.1 S. Kotsuki et al. https://doi.org/10.5194/gmd-18-7215-2025
- On the generalization ability of probabilistic neural networks for hyperspectral remote sensing of absorption properties across optically complex waters M. Werther et al. https://doi.org/10.1016/j.rse.2025.114820
- Stabilizing machine learning prediction of dynamics: Novel noise-inspired regularization tested with reservoir computing A. Wikner et al. https://doi.org/10.1016/j.neunet.2023.10.054
- Machine learning for the physics of climate A. Bracco et al. https://doi.org/10.1038/s42254-024-00776-3
- Blending machine learning and sequential data assimilation over latent spaces for surrogate modeling of Boussinesq systems S. Akbari et al. https://doi.org/10.1016/j.physd.2023.133711
- Precipitation nowcasting using transformer-based generative models and transfer learning for improved disaster preparedness M. Piran et al. https://doi.org/10.1016/j.jag.2024.103962
- 资料同化中的人工智能技术：新兴方法、关键挑战与未来展望 悟. 王 et al. https://doi.org/10.1360/N072025-0199
- Analog ensemble data assimilation in a quasigeostrophic coupled model I. Grooms et al. https://doi.org/10.1002/qj.4446
- Assessing the Feasibility of an NWP Satellite Data Assimilation System Entirely Based on AI Techniques E. Maddy et al. https://doi.org/10.1109/JSTARS.2024.3397078
- Accelerating regional weather forecasting by super-resolution and data-driven methods A. Mikhaylov et al. https://doi.org/10.1515/jiip-2023-0078
- Accurate initial field estimation for weather forecasting with a variational constrained neural network W. Wang et al. https://doi.org/10.1038/s41612-024-00776-1
- Bayesian Change Point Estimation and Evaluation of Machine Learning Models for Multi‐Scale SPI Prediction for Assam‐Meghalaya Region in North‐Eastern India S. Pavan Kumar et al. https://doi.org/10.1002/joc.70061
- Spatio‐Temporal Super‐Resolution Data Assimilation (SRDA) Utilizing Deep Neural Networks With Domain Generalization Y. Yasuda & R. Onishi https://doi.org/10.1029/2023MS003658
- Advancing neural network-based data assimilation for large-scale spatiotemporal systems with sparse observations S. Cai et al. https://doi.org/10.1063/5.0228384
- Analysis and evaluation of ensemble methods in weather classification M. Wang https://doi.org/10.1007/s11760-025-04322-1
- A Space-Time Partial Differential Equation Based Physics-Guided Neural Network for Sea Surface Temperature Prediction T. Yuan et al. https://doi.org/10.3390/rs15143498
- A Multi‐Model Ensemble Kalman Filter for Data Assimilation and Forecasting E. Bach & M. Ghil https://doi.org/10.1029/2022MS003123
- Data driven pathway analysis and forecast of global warming and sea level rise J. Song et al. https://doi.org/10.1038/s41598-023-30789-4
- Industrial Heat Source-Related PM2.5 Concentration Estimates and Analysis Using New Three-Stage Model in the Beijing–Tianjin–Hebei Region Y. Zeng et al. https://doi.org/10.3390/atmos15010131
- Can AI weather models predict out-of-distribution gray swan tropical cyclones? Y. Sun et al. https://doi.org/10.1073/pnas.2420914122
- The convergence of machine learning and data assimilation in Earth system science R. Arcucci et al. https://doi.org/10.1038/s44387-026-00107-0
33 citations as recorded by crossref.
- Deep Learning-Enhanced Ensemble-Based Data Assimilation for High-Dimensional Nonlinear Dynamical Systems A. Chattopadhyay et al. https://doi.org/10.2139/ssrn.4142015
- Learning spatiotemporal chaos using next-generation reservoir computing W. Barbosa & D. Gauthier https://doi.org/10.1063/5.0098707
- Statistical Deep Learning for Spatial and Spatiotemporal Data C. Wikle & A. Zammit-Mangion https://doi.org/10.1146/annurev-statistics-033021-112628
- Artificial Intelligence techniques in data assimilation: Emerging approaches, key challenges, and future prospects W. Wang et al. https://doi.org/10.1007/s11430-025-1807-8
- Deep learning-enhanced ensemble-based data assimilation for high-dimensional nonlinear dynamical systems A. Chattopadhyay et al. https://doi.org/10.1016/j.jcp.2023.111918
- Machine Learning for Climate Physics and Simulations C. Lai et al. https://doi.org/10.1146/annurev-conmatphys-043024-114758
- Long-term stability and generalization of observationally-constrained stochastic data-driven models for geophysical turbulence A. Chattopadhyay et al. https://doi.org/10.1017/eds.2022.30
- Key factors for quantitative precipitation nowcasting using ground weather radar data based on deep learning D. Han et al. https://doi.org/10.5194/gmd-16-5895-2023
- Generative Lagrangian data assimilation for ocean dynamics under extreme sparsity N. Asefi et al. https://doi.org/10.1088/3049-4753/ae0b70
- Equation‐Free Surrogate Modeling of Geophysical Flows at the Intersection of Machine Learning and Data Assimilation S. Pawar & O. San https://doi.org/10.1029/2022MS003170
- A Novel Transformer Network With Shifted Window Cross-Attention for Spatiotemporal Weather Forecasting A. Bojesomo et al. https://doi.org/10.1109/JSTARS.2023.3323729
- Long-Time Accuracy of Ensemble Kalman Filters for Chaotic Dynamical Systems and Machine-Learned Dynamical Systems D. Sanz-Alonso & N. Waniorek https://doi.org/10.1137/24M1719232
- Ensemble data assimilation to diagnose AI-based weather prediction models: a case with ClimaX version 0.3.1 S. Kotsuki et al. https://doi.org/10.5194/gmd-18-7215-2025
- On the generalization ability of probabilistic neural networks for hyperspectral remote sensing of absorption properties across optically complex waters M. Werther et al. https://doi.org/10.1016/j.rse.2025.114820
- Stabilizing machine learning prediction of dynamics: Novel noise-inspired regularization tested with reservoir computing A. Wikner et al. https://doi.org/10.1016/j.neunet.2023.10.054
- Machine learning for the physics of climate A. Bracco et al. https://doi.org/10.1038/s42254-024-00776-3
- Blending machine learning and sequential data assimilation over latent spaces for surrogate modeling of Boussinesq systems S. Akbari et al. https://doi.org/10.1016/j.physd.2023.133711
- Precipitation nowcasting using transformer-based generative models and transfer learning for improved disaster preparedness M. Piran et al. https://doi.org/10.1016/j.jag.2024.103962
- 资料同化中的人工智能技术：新兴方法、关键挑战与未来展望 悟. 王 et al. https://doi.org/10.1360/N072025-0199
- Analog ensemble data assimilation in a quasigeostrophic coupled model I. Grooms et al. https://doi.org/10.1002/qj.4446
- Assessing the Feasibility of an NWP Satellite Data Assimilation System Entirely Based on AI Techniques E. Maddy et al. https://doi.org/10.1109/JSTARS.2024.3397078
- Accelerating regional weather forecasting by super-resolution and data-driven methods A. Mikhaylov et al. https://doi.org/10.1515/jiip-2023-0078
- Accurate initial field estimation for weather forecasting with a variational constrained neural network W. Wang et al. https://doi.org/10.1038/s41612-024-00776-1
- Bayesian Change Point Estimation and Evaluation of Machine Learning Models for Multi‐Scale SPI Prediction for Assam‐Meghalaya Region in North‐Eastern India S. Pavan Kumar et al. https://doi.org/10.1002/joc.70061
- Spatio‐Temporal Super‐Resolution Data Assimilation (SRDA) Utilizing Deep Neural Networks With Domain Generalization Y. Yasuda & R. Onishi https://doi.org/10.1029/2023MS003658
- Advancing neural network-based data assimilation for large-scale spatiotemporal systems with sparse observations S. Cai et al. https://doi.org/10.1063/5.0228384
- Analysis and evaluation of ensemble methods in weather classification M. Wang https://doi.org/10.1007/s11760-025-04322-1
- A Space-Time Partial Differential Equation Based Physics-Guided Neural Network for Sea Surface Temperature Prediction T. Yuan et al. https://doi.org/10.3390/rs15143498
- A Multi‐Model Ensemble Kalman Filter for Data Assimilation and Forecasting E. Bach & M. Ghil https://doi.org/10.1029/2022MS003123
- Data driven pathway analysis and forecast of global warming and sea level rise J. Song et al. https://doi.org/10.1038/s41598-023-30789-4
- Industrial Heat Source-Related PM2.5 Concentration Estimates and Analysis Using New Three-Stage Model in the Beijing–Tianjin–Hebei Region Y. Zeng et al. https://doi.org/10.3390/atmos15010131
- Can AI weather models predict out-of-distribution gray swan tropical cyclones? Y. Sun et al. https://doi.org/10.1073/pnas.2420914122
- The convergence of machine learning and data assimilation in Earth system science R. Arcucci et al. https://doi.org/10.1038/s44387-026-00107-0
Saved (final revised paper)
Latest update: 13 Jun 2026
Short summary
There is growing interest in data-driven weather forecasting, i.e., to predict the weather by using a deep neural network that learns from the evolution of past atmospheric patterns. Here, we propose three components to add to the current data-driven weather forecast models to improve their performance. These components involve a feature that incorporates physics into the neural network, a method to add data assimilation, and an algorithm to use several different time intervals in the forecast.
There is growing interest in data-driven weather forecasting, i.e., to predict the weather by...
