Identifying drivers of surface ozone bias in global chemical reanalysis with explainable machine learning
<p>This study employs an explainable machine learning (ML) framework to examine the regional dependencies of surface ozone biases and their underlying drivers in global chemical reanalysis. Surface ozone observations from the Tropospheric Ozone Assessment Report (TOAR) network and chemical rea...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2025-08-01
|
| Series: | Atmospheric Chemistry and Physics |
| Online Access: | https://acp.copernicus.org/articles/25/8507/2025/acp-25-8507-2025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849338199432757248 |
|---|---|
| author | K. Miyazaki Y. Marchetti J. Montgomery S. Lu K. Bowman |
| author_facet | K. Miyazaki Y. Marchetti J. Montgomery S. Lu K. Bowman |
| author_sort | K. Miyazaki |
| collection | DOAJ |
| description | <p>This study employs an explainable machine learning (ML) framework to examine the regional dependencies of surface ozone biases and their underlying drivers in global chemical reanalysis. Surface ozone observations from the Tropospheric Ozone Assessment Report (TOAR) network and chemical reanalysis outputs from the multi-model multi-constituent chemical (MOMO-Chem) data assimilation (DA) system for the period 2005–2020 were utilized for ML training. A regression-tree-based randomized ensemble ML approach successfully reproduced the spatiotemporal patterns of ozone bias in the chemical reanalysis relative to TOAR observations across North America, Europe, and East Asia. The global distributions of ozone bias predicted by ML revealed systematic patterns influenced by meteorological conditions, geographic features, anthropogenic activities, and biogenic emissions. The primary drivers identified include temperature, surface pressure, carbon monoxide (CO), formaldehyde (<span class="inline-formula">CH<sub>2</sub>O</span>), and nitrogen oxide (<span class="inline-formula">NO<sub><i>x</i></sub></span>) reservoirs such as nitric acid (<span class="inline-formula">HNO<sub>3</sub></span>) and peroxyacetyl nitrate (<span class="inline-formula">PAN</span>). The ML framework provided a detailed quantification of the magnitude and variability of these drivers, delivering bias-corrected ozone estimates suitable for human health and environmental impact assessments. The findings provide valuable insights that can inform advancements in chemical transport modeling, DA, and observational system design, thereby improving surface ozone reanalysis. However, the complex interplay among numerous parameters highlights the need for rigorous validation of identified drivers against established scientific knowledge to attain a comprehensive understanding at the process level. Further advancements in ML interpretability are essential to achieve reliable, actionable outcomes and to lead to an improved reanalysis framework for more effectively mitigating air pollution and its impacts.</p> |
| format | Article |
| id | doaj-art-6a7cbea69f13419d9b80a24ddf79a2a7 |
| institution | Kabale University |
| issn | 1680-7316 1680-7324 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Atmospheric Chemistry and Physics |
| spelling | doaj-art-6a7cbea69f13419d9b80a24ddf79a2a72025-08-20T03:44:28ZengCopernicus PublicationsAtmospheric Chemistry and Physics1680-73161680-73242025-08-01258507853210.5194/acp-25-8507-2025Identifying drivers of surface ozone bias in global chemical reanalysis with explainable machine learningK. Miyazaki0Y. Marchetti1J. Montgomery2S. Lu3K. Bowman4Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, USAJet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, USAJet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, USAJet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, USAJet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, USA<p>This study employs an explainable machine learning (ML) framework to examine the regional dependencies of surface ozone biases and their underlying drivers in global chemical reanalysis. Surface ozone observations from the Tropospheric Ozone Assessment Report (TOAR) network and chemical reanalysis outputs from the multi-model multi-constituent chemical (MOMO-Chem) data assimilation (DA) system for the period 2005–2020 were utilized for ML training. A regression-tree-based randomized ensemble ML approach successfully reproduced the spatiotemporal patterns of ozone bias in the chemical reanalysis relative to TOAR observations across North America, Europe, and East Asia. The global distributions of ozone bias predicted by ML revealed systematic patterns influenced by meteorological conditions, geographic features, anthropogenic activities, and biogenic emissions. The primary drivers identified include temperature, surface pressure, carbon monoxide (CO), formaldehyde (<span class="inline-formula">CH<sub>2</sub>O</span>), and nitrogen oxide (<span class="inline-formula">NO<sub><i>x</i></sub></span>) reservoirs such as nitric acid (<span class="inline-formula">HNO<sub>3</sub></span>) and peroxyacetyl nitrate (<span class="inline-formula">PAN</span>). The ML framework provided a detailed quantification of the magnitude and variability of these drivers, delivering bias-corrected ozone estimates suitable for human health and environmental impact assessments. The findings provide valuable insights that can inform advancements in chemical transport modeling, DA, and observational system design, thereby improving surface ozone reanalysis. However, the complex interplay among numerous parameters highlights the need for rigorous validation of identified drivers against established scientific knowledge to attain a comprehensive understanding at the process level. Further advancements in ML interpretability are essential to achieve reliable, actionable outcomes and to lead to an improved reanalysis framework for more effectively mitigating air pollution and its impacts.</p>https://acp.copernicus.org/articles/25/8507/2025/acp-25-8507-2025.pdf |
| spellingShingle | K. Miyazaki Y. Marchetti J. Montgomery S. Lu K. Bowman Identifying drivers of surface ozone bias in global chemical reanalysis with explainable machine learning Atmospheric Chemistry and Physics |
| title | Identifying drivers of surface ozone bias in global chemical reanalysis with explainable machine learning |
| title_full | Identifying drivers of surface ozone bias in global chemical reanalysis with explainable machine learning |
| title_fullStr | Identifying drivers of surface ozone bias in global chemical reanalysis with explainable machine learning |
| title_full_unstemmed | Identifying drivers of surface ozone bias in global chemical reanalysis with explainable machine learning |
| title_short | Identifying drivers of surface ozone bias in global chemical reanalysis with explainable machine learning |
| title_sort | identifying drivers of surface ozone bias in global chemical reanalysis with explainable machine learning |
| url | https://acp.copernicus.org/articles/25/8507/2025/acp-25-8507-2025.pdf |
| work_keys_str_mv | AT kmiyazaki identifyingdriversofsurfaceozonebiasinglobalchemicalreanalysiswithexplainablemachinelearning AT ymarchetti identifyingdriversofsurfaceozonebiasinglobalchemicalreanalysiswithexplainablemachinelearning AT jmontgomery identifyingdriversofsurfaceozonebiasinglobalchemicalreanalysiswithexplainablemachinelearning AT slu identifyingdriversofsurfaceozonebiasinglobalchemicalreanalysiswithexplainablemachinelearning AT kbowman identifyingdriversofsurfaceozonebiasinglobalchemicalreanalysiswithexplainablemachinelearning |