Articles | Volume 15, issue 17
https://doi.org/10.5194/gmd-15-6677-2022
© 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-15-6677-2022
© 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
| 
05 Sep 2022
Development and technical paper |
| 05 Sep 2022
| 05 Sep 2022
Downscaling atmospheric chemistry simulations with physically consistent deep learning
Pacific Northwest National Laboratory, Richland, WA, USA
Sam J. Silva
Pacific Northwest National Laboratory, Richland, WA, USA
University of Southern California, Los Angeles, CA, USA
Joseph C. Hardin
Pacific Northwest National Laboratory, Richland, WA, USA
ClimateAi, Inc., San Francisco, CA, USA
Viewed
Total article views: 6,502 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 23 Mar 2022)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 4,442 | 1,937 | 123 | 6,502 | 117 | 200 |
- HTML: 4,442
- PDF: 1,937
- XML: 123
- Total: 6,502
- BibTeX: 117
- EndNote: 200
Total article views: 4,400 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 05 Sep 2022)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 3,136 | 1,174 | 90 | 4,400 | 103 | 190 |
- HTML: 3,136
- PDF: 1,174
- XML: 90
- Total: 4,400
- BibTeX: 103
- EndNote: 190
Total article views: 2,102 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 23 Mar 2022)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 1,306 | 763 | 33 | 2,102 | 14 | 10 |
- HTML: 1,306
- PDF: 763
- XML: 33
- Total: 2,102
- BibTeX: 14
- EndNote: 10
Viewed (geographical distribution)
Total article views: 6,502 (including HTML, PDF, and XML)
Thereof 6,224 with geography defined
and 278 with unknown origin.
Total article views: 4,400 (including HTML, PDF, and XML)
Thereof 4,237 with geography defined
and 163 with unknown origin.
Total article views: 2,102 (including HTML, PDF, and XML)
Thereof 1,987 with geography defined
and 115 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
20 citations as recorded by crossref.
- Emulating aerosol optics with randomly generated neural networks A. Geiss et al.
- Learn from Simulations, Adapt to Observations: Super-Resolution of Isoprene Emissions via Unpaired Domain Adaptation A. Giganti et al.
- A staged deep learning approach to spatial refinement in 3D temporal atmospheric transport M. Fernández-Godino et al.
- Regression analysis of air pollution and pediatric respiratory diseases based on interpretable machine learning Y. Ji et al.
- Key factors for quantitative precipitation nowcasting using ground weather radar data based on deep learning D. Han et al.
- Investigating reduced-dimensional variability in aircraft-observed aerosol–cloud parameters K. Butler et al.
- Enhancing Air Quality Simulations With Neural Downscaling Architectures M. Beauchamp et al.
- Pointwise and Complex Quality Metrics in Atmospheric Modeling: Methods and Approaches V. Rezvov et al.
- Enhancing spatiotemporal coverage of satellite-derived high-resolution NO2 data with a super-resolution model M. Zhang et al.
- Toward Explainable and Transferable Deep Downscaling of Atmospheric Pollutants G. Ashiotis et al.
- Arbitrary-Scale Downscaling of Tidal Current Data Using Implicit Continuous Representation D. Lee et al.
- A Nudge to the Truth: Atom Conservation as a Hard Constraint in Models of Atmospheric Composition Using a Species-Weighted Correction P. Sturm & S. Silva
- Daily high-resolution surface PM2.5 estimation over Europe by ML-based downscaling of the CAMS regional forecast S. Shetty et al.
- RainScaler: A Physics-Inspired Network for Precipitation Correction and Downscaling S. Zhao et al.
- Exposure disparities in global daily PM1 pollution C. Tao et al.
- Leveraging Land Cover Priors for Isoprene Emission Super-Resolution C. Ummerle et al.
- POINT-BY-POINT AND COMPLEX QUALITY METRICS IN ATMOSPHERE AND OCEAN RESEARCH: REVIEW OF METHODS AND APPROACHES V. Rezvov et al.
- Machine Learning Surrogate Models for Mechanistic Kinetics: Embedding Atom Balance and Positivity T. Kircher & M. Votsmeier
- Reconstructing long-term (1980–2022) daily ground particulate matter concentrations in India (LongPMInd) S. Wang et al.
- Recent progress, bottlenecks, and outlook of multiscale air quality modelling: a review Y. Dai et al.
20 citations as recorded by crossref.
- Emulating aerosol optics with randomly generated neural networks A. Geiss et al.
- Learn from Simulations, Adapt to Observations: Super-Resolution of Isoprene Emissions via Unpaired Domain Adaptation A. Giganti et al.
- A staged deep learning approach to spatial refinement in 3D temporal atmospheric transport M. Fernández-Godino et al.
- Regression analysis of air pollution and pediatric respiratory diseases based on interpretable machine learning Y. Ji et al.
- Key factors for quantitative precipitation nowcasting using ground weather radar data based on deep learning D. Han et al.
- Investigating reduced-dimensional variability in aircraft-observed aerosol–cloud parameters K. Butler et al.
- Enhancing Air Quality Simulations With Neural Downscaling Architectures M. Beauchamp et al.
- Pointwise and Complex Quality Metrics in Atmospheric Modeling: Methods and Approaches V. Rezvov et al.
- Enhancing spatiotemporal coverage of satellite-derived high-resolution NO2 data with a super-resolution model M. Zhang et al.
- Toward Explainable and Transferable Deep Downscaling of Atmospheric Pollutants G. Ashiotis et al.
- Arbitrary-Scale Downscaling of Tidal Current Data Using Implicit Continuous Representation D. Lee et al.
- A Nudge to the Truth: Atom Conservation as a Hard Constraint in Models of Atmospheric Composition Using a Species-Weighted Correction P. Sturm & S. Silva
- Daily high-resolution surface PM2.5 estimation over Europe by ML-based downscaling of the CAMS regional forecast S. Shetty et al.
- RainScaler: A Physics-Inspired Network for Precipitation Correction and Downscaling S. Zhao et al.
- Exposure disparities in global daily PM1 pollution C. Tao et al.
- Leveraging Land Cover Priors for Isoprene Emission Super-Resolution C. Ummerle et al.
- POINT-BY-POINT AND COMPLEX QUALITY METRICS IN ATMOSPHERE AND OCEAN RESEARCH: REVIEW OF METHODS AND APPROACHES V. Rezvov et al.
- Machine Learning Surrogate Models for Mechanistic Kinetics: Embedding Atom Balance and Positivity T. Kircher & M. Votsmeier
- Reconstructing long-term (1980–2022) daily ground particulate matter concentrations in India (LongPMInd) S. Wang et al.
- Recent progress, bottlenecks, and outlook of multiscale air quality modelling: a review Y. Dai et al.
Saved (final revised paper)
Latest update: 20 May 2026
Short summary
This work demonstrates the use of modern machine learning techniques to enhance the resolution of atmospheric chemistry simulations. We evaluate the schemes for an 8 x 10 increase in resolution and find that they perform substantially better than conventional methods. Methods are introduced to target machine learning methods towards this type of problem, most notably by ensuring they do not break known physical constraints.
This work demonstrates the use of modern machine learning techniques to enhance the resolution...
