A novel spatiotemporal prediction approach to fill air pollution data gaps using mobile sensors, machine learning and citizen science techniques
Abstract Particulate Matter (PM) air pollution poses significant threats to public health. We introduce a novel machine learning methodology to predict PM2.5 levels at 30 m long segments along the roads and at a temporal scale of 10 seconds. A hybrid dataset was curated from an intensive PM campaign...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | npj Climate and Atmospheric Science |
| Online Access: | https://doi.org/10.1038/s41612-024-00859-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846112666241728512 |
|---|---|
| author | Arunik Baruah Dimitrios Bousiotis Seny Damayanti Alessandro Bigi Grazia Ghermandi O. Ghaffarpasand Roy M. Harrison Francis D. Pope |
| author_facet | Arunik Baruah Dimitrios Bousiotis Seny Damayanti Alessandro Bigi Grazia Ghermandi O. Ghaffarpasand Roy M. Harrison Francis D. Pope |
| author_sort | Arunik Baruah |
| collection | DOAJ |
| description | Abstract Particulate Matter (PM) air pollution poses significant threats to public health. We introduce a novel machine learning methodology to predict PM2.5 levels at 30 m long segments along the roads and at a temporal scale of 10 seconds. A hybrid dataset was curated from an intensive PM campaign in Selly Oak, Birmingham, UK, utilizing citizen scientists and low-cost instruments strategically placed in static and mobile settings. Spatially resolved proxy variables, meteorological parameters, and PM properties were integrated, enabling a fine-grained analysis of PM2.5. Calibration involved three approaches: Standard Random Forest Regression, Sensor Transferability and Road Transferability Evaluations. This methodology significantly increased spatial resolution beyond what is possible with regulatory monitoring, thereby improving exposure assessments. The findings underscore the importance of machine learning approaches and citizen science in advancing our understanding of PM pollution, with a small number of participants significantly enhancing local air quality assessment for thousands of residents. |
| format | Article |
| id | doaj-art-e258f9b416f64ae58a7fe9ae40a1e71a |
| institution | Kabale University |
| issn | 2397-3722 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Climate and Atmospheric Science |
| spelling | doaj-art-e258f9b416f64ae58a7fe9ae40a1e71a2024-12-22T12:23:52ZengNature Portfolionpj Climate and Atmospheric Science2397-37222024-12-017111210.1038/s41612-024-00859-zA novel spatiotemporal prediction approach to fill air pollution data gaps using mobile sensors, machine learning and citizen science techniquesArunik Baruah0Dimitrios Bousiotis1Seny Damayanti2Alessandro Bigi3Grazia Ghermandi4O. Ghaffarpasand5Roy M. Harrison6Francis D. Pope7Dept. of Engineering ‘Enzo Ferrari’, University of Modena and Reggio EmiliaSchool of Geography, Earth and Environmental Sciences, University of BirminghamSchool of Geography, Earth and Environmental Sciences, University of BirminghamDept. of Engineering ‘Enzo Ferrari’, University of Modena and Reggio EmiliaDept. of Engineering ‘Enzo Ferrari’, University of Modena and Reggio EmiliaSchool of Geography, Earth and Environmental Sciences, University of BirminghamSchool of Geography, Earth and Environmental Sciences, University of BirminghamSchool of Geography, Earth and Environmental Sciences, University of BirminghamAbstract Particulate Matter (PM) air pollution poses significant threats to public health. We introduce a novel machine learning methodology to predict PM2.5 levels at 30 m long segments along the roads and at a temporal scale of 10 seconds. A hybrid dataset was curated from an intensive PM campaign in Selly Oak, Birmingham, UK, utilizing citizen scientists and low-cost instruments strategically placed in static and mobile settings. Spatially resolved proxy variables, meteorological parameters, and PM properties were integrated, enabling a fine-grained analysis of PM2.5. Calibration involved three approaches: Standard Random Forest Regression, Sensor Transferability and Road Transferability Evaluations. This methodology significantly increased spatial resolution beyond what is possible with regulatory monitoring, thereby improving exposure assessments. The findings underscore the importance of machine learning approaches and citizen science in advancing our understanding of PM pollution, with a small number of participants significantly enhancing local air quality assessment for thousands of residents.https://doi.org/10.1038/s41612-024-00859-z |
| spellingShingle | Arunik Baruah Dimitrios Bousiotis Seny Damayanti Alessandro Bigi Grazia Ghermandi O. Ghaffarpasand Roy M. Harrison Francis D. Pope A novel spatiotemporal prediction approach to fill air pollution data gaps using mobile sensors, machine learning and citizen science techniques npj Climate and Atmospheric Science |
| title | A novel spatiotemporal prediction approach to fill air pollution data gaps using mobile sensors, machine learning and citizen science techniques |
| title_full | A novel spatiotemporal prediction approach to fill air pollution data gaps using mobile sensors, machine learning and citizen science techniques |
| title_fullStr | A novel spatiotemporal prediction approach to fill air pollution data gaps using mobile sensors, machine learning and citizen science techniques |
| title_full_unstemmed | A novel spatiotemporal prediction approach to fill air pollution data gaps using mobile sensors, machine learning and citizen science techniques |
| title_short | A novel spatiotemporal prediction approach to fill air pollution data gaps using mobile sensors, machine learning and citizen science techniques |
| title_sort | novel spatiotemporal prediction approach to fill air pollution data gaps using mobile sensors machine learning and citizen science techniques |
| url | https://doi.org/10.1038/s41612-024-00859-z |
| work_keys_str_mv | AT arunikbaruah anovelspatiotemporalpredictionapproachtofillairpollutiondatagapsusingmobilesensorsmachinelearningandcitizensciencetechniques AT dimitriosbousiotis anovelspatiotemporalpredictionapproachtofillairpollutiondatagapsusingmobilesensorsmachinelearningandcitizensciencetechniques AT senydamayanti anovelspatiotemporalpredictionapproachtofillairpollutiondatagapsusingmobilesensorsmachinelearningandcitizensciencetechniques AT alessandrobigi anovelspatiotemporalpredictionapproachtofillairpollutiondatagapsusingmobilesensorsmachinelearningandcitizensciencetechniques AT graziaghermandi anovelspatiotemporalpredictionapproachtofillairpollutiondatagapsusingmobilesensorsmachinelearningandcitizensciencetechniques AT oghaffarpasand anovelspatiotemporalpredictionapproachtofillairpollutiondatagapsusingmobilesensorsmachinelearningandcitizensciencetechniques AT roymharrison anovelspatiotemporalpredictionapproachtofillairpollutiondatagapsusingmobilesensorsmachinelearningandcitizensciencetechniques AT francisdpope anovelspatiotemporalpredictionapproachtofillairpollutiondatagapsusingmobilesensorsmachinelearningandcitizensciencetechniques AT arunikbaruah novelspatiotemporalpredictionapproachtofillairpollutiondatagapsusingmobilesensorsmachinelearningandcitizensciencetechniques AT dimitriosbousiotis novelspatiotemporalpredictionapproachtofillairpollutiondatagapsusingmobilesensorsmachinelearningandcitizensciencetechniques AT senydamayanti novelspatiotemporalpredictionapproachtofillairpollutiondatagapsusingmobilesensorsmachinelearningandcitizensciencetechniques AT alessandrobigi novelspatiotemporalpredictionapproachtofillairpollutiondatagapsusingmobilesensorsmachinelearningandcitizensciencetechniques AT graziaghermandi novelspatiotemporalpredictionapproachtofillairpollutiondatagapsusingmobilesensorsmachinelearningandcitizensciencetechniques AT oghaffarpasand novelspatiotemporalpredictionapproachtofillairpollutiondatagapsusingmobilesensorsmachinelearningandcitizensciencetechniques AT roymharrison novelspatiotemporalpredictionapproachtofillairpollutiondatagapsusingmobilesensorsmachinelearningandcitizensciencetechniques AT francisdpope novelspatiotemporalpredictionapproachtofillairpollutiondatagapsusingmobilesensorsmachinelearningandcitizensciencetechniques |