Importance of ozone precursors information in modelling urban surface ozone variability using machine learning algorithm
Abstract Surface ozone (O $$_3$$ 3 ) is primarily formed through complex photo-chemical reactions in the atmosphere, which are non-linearly dependent on precursors. Even though, there have been many recent studies exploring the potential of machine learning (ML) in modeling surface ozone, the inclus...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-04-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-09619-6 |
| _version_ | 1819045465992200192 |
|---|---|
| author | Vigneshkumar Balamurugan Vinothkumar Balamurugan Jia Chen |
| author_facet | Vigneshkumar Balamurugan Vinothkumar Balamurugan Jia Chen |
| author_sort | Vigneshkumar Balamurugan |
| collection | DOAJ |
| description | Abstract Surface ozone (O $$_3$$ 3 ) is primarily formed through complex photo-chemical reactions in the atmosphere, which are non-linearly dependent on precursors. Even though, there have been many recent studies exploring the potential of machine learning (ML) in modeling surface ozone, the inclusion of limited available ozone precursors information has received little attention. The ML algorithm with in-situ NO information and meteorology explains 87% (R $$^{2}$$ 2 = 0.87) of the ozone variability over Munich, a German metropolitan area, which is 15% higher than a ML algorithm that considers only meteorology. The ML algorithm trained for the urban measurement station in Munich can also explain the ozone variability of the other three stations in the same city, with R $$^{2}$$ 2 = 0.88, 0.91, 0.63. While the same model robustly explains the ozone variability of two other German cities’ (Berlin and Hamburg) measurement stations, with R $$^{2}$$ 2 ranges from 0.72 to 0.84, giving confidence to use the ML algorithm trained for one location to other locations with sparse ozone measurements. The inclusion of satellite O $$_3$$ 3 precursors information has little effect on the ML model’s performance. |
| first_indexed | 2024-12-21T10:29:01Z |
| format | Article |
| id | doaj.art-200af620ccb742f2ad7f0df8ed6fd893 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-21T10:29:01Z |
| publishDate | 2022-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-200af620ccb742f2ad7f0df8ed6fd8932022-12-21T19:07:14ZengNature PortfolioScientific Reports2045-23222022-04-011211810.1038/s41598-022-09619-6Importance of ozone precursors information in modelling urban surface ozone variability using machine learning algorithmVigneshkumar Balamurugan0Vinothkumar Balamurugan1Jia Chen2Environmental Sensing and Modeling, Technical University of Munich (TUM)Mechanical Engineering, St. Joseph’s Institute of TechnologyEnvironmental Sensing and Modeling, Technical University of Munich (TUM)Abstract Surface ozone (O $$_3$$ 3 ) is primarily formed through complex photo-chemical reactions in the atmosphere, which are non-linearly dependent on precursors. Even though, there have been many recent studies exploring the potential of machine learning (ML) in modeling surface ozone, the inclusion of limited available ozone precursors information has received little attention. The ML algorithm with in-situ NO information and meteorology explains 87% (R $$^{2}$$ 2 = 0.87) of the ozone variability over Munich, a German metropolitan area, which is 15% higher than a ML algorithm that considers only meteorology. The ML algorithm trained for the urban measurement station in Munich can also explain the ozone variability of the other three stations in the same city, with R $$^{2}$$ 2 = 0.88, 0.91, 0.63. While the same model robustly explains the ozone variability of two other German cities’ (Berlin and Hamburg) measurement stations, with R $$^{2}$$ 2 ranges from 0.72 to 0.84, giving confidence to use the ML algorithm trained for one location to other locations with sparse ozone measurements. The inclusion of satellite O $$_3$$ 3 precursors information has little effect on the ML model’s performance.https://doi.org/10.1038/s41598-022-09619-6 |
| spellingShingle | Vigneshkumar Balamurugan Vinothkumar Balamurugan Jia Chen Importance of ozone precursors information in modelling urban surface ozone variability using machine learning algorithm Scientific Reports |
| title | Importance of ozone precursors information in modelling urban surface ozone variability using machine learning algorithm |
| title_full | Importance of ozone precursors information in modelling urban surface ozone variability using machine learning algorithm |
| title_fullStr | Importance of ozone precursors information in modelling urban surface ozone variability using machine learning algorithm |
| title_full_unstemmed | Importance of ozone precursors information in modelling urban surface ozone variability using machine learning algorithm |
| title_short | Importance of ozone precursors information in modelling urban surface ozone variability using machine learning algorithm |
| title_sort | importance of ozone precursors information in modelling urban surface ozone variability using machine learning algorithm |
| url | https://doi.org/10.1038/s41598-022-09619-6 |
| work_keys_str_mv | AT vigneshkumarbalamurugan importanceofozoneprecursorsinformationinmodellingurbansurfaceozonevariabilityusingmachinelearningalgorithm AT vinothkumarbalamurugan importanceofozoneprecursorsinformationinmodellingurbansurfaceozonevariabilityusingmachinelearningalgorithm AT jiachen importanceofozoneprecursorsinformationinmodellingurbansurfaceozonevariabilityusingmachinelearningalgorithm |