Estimating Nitrogen Dioxide Levels Using Open Data and Machine Learning: A Comparative Modeling Study
Nitrogen dioxide (NO<sub>2</sub>) is a critical pollutant with widespread effects on both air quality and environmental health, recognized as a key concern within the United Nations’ Sustainable Development Goals (SDGs). This study investigates NO<sub>2</sub> levels...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2025-07-01
|
| Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-annals.copernicus.org/articles/X-G-2025/893/2025/isprs-annals-X-G-2025-893-2025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839629728792707072 |
|---|---|
| author | D. Varam R. Mitra F. Kamran D. A. Abuhani H. Sulieman I. Zualkernan |
| author_facet | D. Varam R. Mitra F. Kamran D. A. Abuhani H. Sulieman I. Zualkernan |
| author_sort | D. Varam |
| collection | DOAJ |
| description | Nitrogen dioxide (NO<sub>2</sub>) is a critical pollutant with widespread effects on both air quality and environmental health, recognized as a key concern within the United Nations’ Sustainable Development Goals (SDGs). This study investigates NO<sub>2</sub> levels in Italy, analyzing spatial and seasonal variations to better understand pollutant distribution. Using open-source data, we employed machine learning models to estimate NO<sub>2</sub> concentrations, achieving strong predictive accuracy based on the mean absolute percentage error and the root mean-squared error. The results reveal that model performance improves significantly when data is segmented based on seasonal and urban development factors. Specifically, predictions for urban, rural, and mixed cities demonstrated that urban areas exhibited higher NO<sub>2</sub> concentrations, while rural regions showed comparatively lower levels. The analysis underscores the importance of tailoring models to regional and temporal contexts, affirming that open-source data, combined with machine learning techniques, can effectively estimate NO<sub>2</sub> pollution levels across diverse environments. |
| format | Article |
| id | doaj-art-30f8f2dcc8b14df28c4ed1d6a3b7abc2 |
| institution | Matheson Library |
| issn | 2194-9042 2194-9050 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj-art-30f8f2dcc8b14df28c4ed1d6a3b7abc22025-07-14T19:15:07ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502025-07-01X-G-202589390010.5194/isprs-annals-X-G-2025-893-2025Estimating Nitrogen Dioxide Levels Using Open Data and Machine Learning: A Comparative Modeling StudyD. Varam0R. Mitra1F. Kamran2D. A. Abuhani3H. Sulieman4I. Zualkernan5Dept. of Computer Science & Engineering, American University of Sharjah, Sharjah, UAEDept. of Computer Science & Engineering, American University of Sharjah, Sharjah, UAEDept. of Mathematics & Statistics, American University of Sharjah, Sharjah, UAEDept. of Computer Science & Engineering, American University of Sharjah, Sharjah, UAEDept. of Mathematics & Statistics, American University of Sharjah, Sharjah, UAEDept. of Computer Science & Engineering, American University of Sharjah, Sharjah, UAENitrogen dioxide (NO<sub>2</sub>) is a critical pollutant with widespread effects on both air quality and environmental health, recognized as a key concern within the United Nations’ Sustainable Development Goals (SDGs). This study investigates NO<sub>2</sub> levels in Italy, analyzing spatial and seasonal variations to better understand pollutant distribution. Using open-source data, we employed machine learning models to estimate NO<sub>2</sub> concentrations, achieving strong predictive accuracy based on the mean absolute percentage error and the root mean-squared error. The results reveal that model performance improves significantly when data is segmented based on seasonal and urban development factors. Specifically, predictions for urban, rural, and mixed cities demonstrated that urban areas exhibited higher NO<sub>2</sub> concentrations, while rural regions showed comparatively lower levels. The analysis underscores the importance of tailoring models to regional and temporal contexts, affirming that open-source data, combined with machine learning techniques, can effectively estimate NO<sub>2</sub> pollution levels across diverse environments.https://isprs-annals.copernicus.org/articles/X-G-2025/893/2025/isprs-annals-X-G-2025-893-2025.pdf |
| spellingShingle | D. Varam R. Mitra F. Kamran D. A. Abuhani H. Sulieman I. Zualkernan Estimating Nitrogen Dioxide Levels Using Open Data and Machine Learning: A Comparative Modeling Study ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | Estimating Nitrogen Dioxide Levels Using Open Data and Machine Learning: A Comparative Modeling Study |
| title_full | Estimating Nitrogen Dioxide Levels Using Open Data and Machine Learning: A Comparative Modeling Study |
| title_fullStr | Estimating Nitrogen Dioxide Levels Using Open Data and Machine Learning: A Comparative Modeling Study |
| title_full_unstemmed | Estimating Nitrogen Dioxide Levels Using Open Data and Machine Learning: A Comparative Modeling Study |
| title_short | Estimating Nitrogen Dioxide Levels Using Open Data and Machine Learning: A Comparative Modeling Study |
| title_sort | estimating nitrogen dioxide levels using open data and machine learning a comparative modeling study |
| url | https://isprs-annals.copernicus.org/articles/X-G-2025/893/2025/isprs-annals-X-G-2025-893-2025.pdf |
| work_keys_str_mv | AT dvaram estimatingnitrogendioxidelevelsusingopendataandmachinelearningacomparativemodelingstudy AT rmitra estimatingnitrogendioxidelevelsusingopendataandmachinelearningacomparativemodelingstudy AT fkamran estimatingnitrogendioxidelevelsusingopendataandmachinelearningacomparativemodelingstudy AT daabuhani estimatingnitrogendioxidelevelsusingopendataandmachinelearningacomparativemodelingstudy AT hsulieman estimatingnitrogendioxidelevelsusingopendataandmachinelearningacomparativemodelingstudy AT izualkernan estimatingnitrogendioxidelevelsusingopendataandmachinelearningacomparativemodelingstudy |