Statistical PM<sub>2.5</sub> Prediction in an Urban Area Using Vertical Meteorological Factors
A key concern related to particulate air pollution is the development of an early warning system that can predict local PM<sub>2.5</sub> levels and excessive PM<sub>2.5</sub> concentration episodes using vertical meteorological factors. Machine learning (ML) algorithms, parti...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/14/3/589 |
| _version_ | 1797613594496466944 |
|---|---|
| author | Jutapas Saiohai Surat Bualert Thunyapat Thongyen Kittichai Duangmal Parkpoom Choomanee Wladyslaw W. Szymanski |
| author_facet | Jutapas Saiohai Surat Bualert Thunyapat Thongyen Kittichai Duangmal Parkpoom Choomanee Wladyslaw W. Szymanski |
| author_sort | Jutapas Saiohai |
| collection | DOAJ |
| description | A key concern related to particulate air pollution is the development of an early warning system that can predict local PM<sub>2.5</sub> levels and excessive PM<sub>2.5</sub> concentration episodes using vertical meteorological factors. Machine learning (ML) algorithms, particularly those with recognition tasks, show great potential for this purpose. The objective of this study was to compare the performance of multiple linear regression (MLR) and multilayer perceptron (MLP) in predicting PM<sub>2.5</sub> levels. The software was trained to predict PM<sub>2.5</sub> levels up to 7 days in advance using data from long-term measurements of vertical meteorological factors taken at five heights above ground level (AGL)—10, 30, 50, 75, and 110 m—and PM<sub>2.5</sub> concentrations measured 30 m AGL. The data used were collected between 2015 and 2020 at the Microclimate and Air Pollutants Monitoring Tower station at Kasetsart University, Bangkok, Thailand. The results showed that the correlation coefficients of PM<sub>2.5</sub> predicted and observed using MLR and MLP were in the range of 0.69–0.86 and 0.64–0.82, respectively, for 1–3 days ahead. Both models showed satisfactory agreement with the measured data, and MLR performed better than MLP at PM<sub>2.5</sub> prediction. In conclusion, this study demonstrates that the proposed approach can be used as a component of an early warning system in cities, contributing to sustainable air quality management in urban areas. |
| first_indexed | 2024-03-11T06:56:59Z |
| format | Article |
| id | doaj.art-f7d643c205c34f4d84fbe5d8a0182a5e |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-03-11T06:56:59Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-f7d643c205c34f4d84fbe5d8a0182a5e2023-11-17T09:33:51ZengMDPI AGAtmosphere2073-44332023-03-0114358910.3390/atmos14030589Statistical PM<sub>2.5</sub> Prediction in an Urban Area Using Vertical Meteorological FactorsJutapas Saiohai0Surat Bualert1Thunyapat Thongyen2Kittichai Duangmal3Parkpoom Choomanee4Wladyslaw W. Szymanski5Department of Environmental Science, Faculty of Environment, Kasetsart University, Bangkok 10900, ThailandDepartment of Environmental Science, Faculty of Environment, Kasetsart University, Bangkok 10900, ThailandDepartment of Environmental Technology and Management, Faculty of Environment, Kasetsart University, Bangkok 10900, ThailandDepartment of Environmental Science, Faculty of Environment, Kasetsart University, Bangkok 10900, ThailandDepartment of Environmental Science, Faculty of Environment, Kasetsart University, Bangkok 10900, ThailandDepartment of Environmental Science, Faculty of Environment, Kasetsart University, Bangkok 10900, ThailandA key concern related to particulate air pollution is the development of an early warning system that can predict local PM<sub>2.5</sub> levels and excessive PM<sub>2.5</sub> concentration episodes using vertical meteorological factors. Machine learning (ML) algorithms, particularly those with recognition tasks, show great potential for this purpose. The objective of this study was to compare the performance of multiple linear regression (MLR) and multilayer perceptron (MLP) in predicting PM<sub>2.5</sub> levels. The software was trained to predict PM<sub>2.5</sub> levels up to 7 days in advance using data from long-term measurements of vertical meteorological factors taken at five heights above ground level (AGL)—10, 30, 50, 75, and 110 m—and PM<sub>2.5</sub> concentrations measured 30 m AGL. The data used were collected between 2015 and 2020 at the Microclimate and Air Pollutants Monitoring Tower station at Kasetsart University, Bangkok, Thailand. The results showed that the correlation coefficients of PM<sub>2.5</sub> predicted and observed using MLR and MLP were in the range of 0.69–0.86 and 0.64–0.82, respectively, for 1–3 days ahead. Both models showed satisfactory agreement with the measured data, and MLR performed better than MLP at PM<sub>2.5</sub> prediction. In conclusion, this study demonstrates that the proposed approach can be used as a component of an early warning system in cities, contributing to sustainable air quality management in urban areas.https://www.mdpi.com/2073-4433/14/3/589PM<sub>2.5</sub> predictionvertical meteorological factorsmultiple linear regressionmultilayer perceptron |
| spellingShingle | Jutapas Saiohai Surat Bualert Thunyapat Thongyen Kittichai Duangmal Parkpoom Choomanee Wladyslaw W. Szymanski Statistical PM<sub>2.5</sub> Prediction in an Urban Area Using Vertical Meteorological Factors Atmosphere PM<sub>2.5</sub> prediction vertical meteorological factors multiple linear regression multilayer perceptron |
| title | Statistical PM<sub>2.5</sub> Prediction in an Urban Area Using Vertical Meteorological Factors |
| title_full | Statistical PM<sub>2.5</sub> Prediction in an Urban Area Using Vertical Meteorological Factors |
| title_fullStr | Statistical PM<sub>2.5</sub> Prediction in an Urban Area Using Vertical Meteorological Factors |
| title_full_unstemmed | Statistical PM<sub>2.5</sub> Prediction in an Urban Area Using Vertical Meteorological Factors |
| title_short | Statistical PM<sub>2.5</sub> Prediction in an Urban Area Using Vertical Meteorological Factors |
| title_sort | statistical pm sub 2 5 sub prediction in an urban area using vertical meteorological factors |
| topic | PM<sub>2.5</sub> prediction vertical meteorological factors multiple linear regression multilayer perceptron |
| url | https://www.mdpi.com/2073-4433/14/3/589 |
| work_keys_str_mv | AT jutapassaiohai statisticalpmsub25subpredictioninanurbanareausingverticalmeteorologicalfactors AT suratbualert statisticalpmsub25subpredictioninanurbanareausingverticalmeteorologicalfactors AT thunyapatthongyen statisticalpmsub25subpredictioninanurbanareausingverticalmeteorologicalfactors AT kittichaiduangmal statisticalpmsub25subpredictioninanurbanareausingverticalmeteorologicalfactors AT parkpoomchoomanee statisticalpmsub25subpredictioninanurbanareausingverticalmeteorologicalfactors AT wladyslawwszymanski statisticalpmsub25subpredictioninanurbanareausingverticalmeteorologicalfactors |