A Nonlinear Land Use Regression Approach for Modelling NO<sub>2</sub> Concentrations in Urban Areas—Using Data from Low-Cost Sensors and Diffusion Tubes
Land Use Regression (LUR) based on multiple linear regression model is one of the techniques used most frequently for modelling the spatial variability of air pollution and assessing exposure in urban areas. In this paper, a nonlinear generalised additive model is proposed for LUR and its performanc...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/11/7/736 |
| _version_ | 1797562671070969856 |
|---|---|
| author | Said Munir Martin Mayfield Daniel Coca Lyudmila S Mihaylova |
| author_facet | Said Munir Martin Mayfield Daniel Coca Lyudmila S Mihaylova |
| author_sort | Said Munir |
| collection | DOAJ |
| description | Land Use Regression (LUR) based on multiple linear regression model is one of the techniques used most frequently for modelling the spatial variability of air pollution and assessing exposure in urban areas. In this paper, a nonlinear generalised additive model is proposed for LUR and its performance is compared to a linear model in Sheffield, UK for the year 2019. Pollution models were estimated using NO<sub>2</sub> measurements obtained from 188 diffusion tubes and 40 low-cost sensors. Performance of the models was assessed by calculating several statistical metrics including correlation coefficient (R) and root mean square error (RMSE). High resolution (100 m × 100 m) maps demonstrated higher levels of NO<sub>2</sub> in the city centre, eastern side of the city and on major roads. The results showed that the nonlinear model outperformed the linear counterpart and that the model estimated using NO<sub>2</sub> data from diffusion tubes outperformed the models using data from low-cost sensors or both low-cost sensors and diffusion tubes. The proposed method provides a basis for further application of advanced nonlinear modelling approaches to constructing LUR models in urban areas which enable quantifying small scale variability in pollution levels. |
| first_indexed | 2024-03-10T18:32:15Z |
| format | Article |
| id | doaj.art-0fd4c3bd035042e5a292aa718d76a548 |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-03-10T18:32:15Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-0fd4c3bd035042e5a292aa718d76a5482023-11-20T06:29:29ZengMDPI AGAtmosphere2073-44332020-07-0111773610.3390/atmos11070736A Nonlinear Land Use Regression Approach for Modelling NO<sub>2</sub> Concentrations in Urban Areas—Using Data from Low-Cost Sensors and Diffusion TubesSaid Munir0Martin Mayfield1Daniel Coca2Lyudmila S Mihaylova3Department of Civil and Structural Engineering, the University of Sheffield, Sheffield S1 3JD, UKDepartment of Civil and Structural Engineering, the University of Sheffield, Sheffield S1 3JD, UKDepartment of Automatic Control and Systems Engineering, the University of Sheffield, Sheffield S1 3JD, UKDepartment of Automatic Control and Systems Engineering, the University of Sheffield, Sheffield S1 3JD, UKLand Use Regression (LUR) based on multiple linear regression model is one of the techniques used most frequently for modelling the spatial variability of air pollution and assessing exposure in urban areas. In this paper, a nonlinear generalised additive model is proposed for LUR and its performance is compared to a linear model in Sheffield, UK for the year 2019. Pollution models were estimated using NO<sub>2</sub> measurements obtained from 188 diffusion tubes and 40 low-cost sensors. Performance of the models was assessed by calculating several statistical metrics including correlation coefficient (R) and root mean square error (RMSE). High resolution (100 m × 100 m) maps demonstrated higher levels of NO<sub>2</sub> in the city centre, eastern side of the city and on major roads. The results showed that the nonlinear model outperformed the linear counterpart and that the model estimated using NO<sub>2</sub> data from diffusion tubes outperformed the models using data from low-cost sensors or both low-cost sensors and diffusion tubes. The proposed method provides a basis for further application of advanced nonlinear modelling approaches to constructing LUR models in urban areas which enable quantifying small scale variability in pollution levels.https://www.mdpi.com/2073-4433/11/7/736air quality modellingland use regressionnonlinear regressionSheffieldspatial analysislow-cost sensors |
| spellingShingle | Said Munir Martin Mayfield Daniel Coca Lyudmila S Mihaylova A Nonlinear Land Use Regression Approach for Modelling NO<sub>2</sub> Concentrations in Urban Areas—Using Data from Low-Cost Sensors and Diffusion Tubes Atmosphere air quality modelling land use regression nonlinear regression Sheffield spatial analysis low-cost sensors |
| title | A Nonlinear Land Use Regression Approach for Modelling NO<sub>2</sub> Concentrations in Urban Areas—Using Data from Low-Cost Sensors and Diffusion Tubes |
| title_full | A Nonlinear Land Use Regression Approach for Modelling NO<sub>2</sub> Concentrations in Urban Areas—Using Data from Low-Cost Sensors and Diffusion Tubes |
| title_fullStr | A Nonlinear Land Use Regression Approach for Modelling NO<sub>2</sub> Concentrations in Urban Areas—Using Data from Low-Cost Sensors and Diffusion Tubes |
| title_full_unstemmed | A Nonlinear Land Use Regression Approach for Modelling NO<sub>2</sub> Concentrations in Urban Areas—Using Data from Low-Cost Sensors and Diffusion Tubes |
| title_short | A Nonlinear Land Use Regression Approach for Modelling NO<sub>2</sub> Concentrations in Urban Areas—Using Data from Low-Cost Sensors and Diffusion Tubes |
| title_sort | nonlinear land use regression approach for modelling no sub 2 sub concentrations in urban areas using data from low cost sensors and diffusion tubes |
| topic | air quality modelling land use regression nonlinear regression Sheffield spatial analysis low-cost sensors |
| url | https://www.mdpi.com/2073-4433/11/7/736 |
| work_keys_str_mv | AT saidmunir anonlinearlanduseregressionapproachformodellingnosub2subconcentrationsinurbanareasusingdatafromlowcostsensorsanddiffusiontubes AT martinmayfield anonlinearlanduseregressionapproachformodellingnosub2subconcentrationsinurbanareasusingdatafromlowcostsensorsanddiffusiontubes AT danielcoca anonlinearlanduseregressionapproachformodellingnosub2subconcentrationsinurbanareasusingdatafromlowcostsensorsanddiffusiontubes AT lyudmilasmihaylova anonlinearlanduseregressionapproachformodellingnosub2subconcentrationsinurbanareasusingdatafromlowcostsensorsanddiffusiontubes AT saidmunir nonlinearlanduseregressionapproachformodellingnosub2subconcentrationsinurbanareasusingdatafromlowcostsensorsanddiffusiontubes AT martinmayfield nonlinearlanduseregressionapproachformodellingnosub2subconcentrationsinurbanareasusingdatafromlowcostsensorsanddiffusiontubes AT danielcoca nonlinearlanduseregressionapproachformodellingnosub2subconcentrationsinurbanareasusingdatafromlowcostsensorsanddiffusiontubes AT lyudmilasmihaylova nonlinearlanduseregressionapproachformodellingnosub2subconcentrationsinurbanareasusingdatafromlowcostsensorsanddiffusiontubes |