A hybrid model for estimating the number concentration of ultrafine particles based on machine learning algorithms in central Taiwan
Modeling is a cost-effective measure to estimate ultrafine particle (UFP) levels. Previous UFP estimates generally relied on land-use regression with insufficient temporal resolution. We carried out in-situ measurements for UFP in central Taiwan and developed a model incorporating satellite-based me...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-05-01
|
| Series: | Environment International |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0160412023002106 |
| _version_ | 1827943918375796736 |
|---|---|
| author | Chau-Ren Jung Wei-Ting Chen Li-Hao Young Ta-Chih Hsiao |
| author_facet | Chau-Ren Jung Wei-Ting Chen Li-Hao Young Ta-Chih Hsiao |
| author_sort | Chau-Ren Jung |
| collection | DOAJ |
| description | Modeling is a cost-effective measure to estimate ultrafine particle (UFP) levels. Previous UFP estimates generally relied on land-use regression with insufficient temporal resolution. We carried out in-situ measurements for UFP in central Taiwan and developed a model incorporating satellite-based measurements, meteorological variables, and land-use data to estimate daily UFP levels at a 1-km resolution. Two sampling campaigns were conducted for measuring hourly UFP concentrations at six sites between 2008–2010 and 2017–2021, respectively, using scanning mobility particle sizers. Three machine learning algorithms, namely random forest, eXtreme gradient boosting (XGBoost), and deep neural network, were used to develop UFP estimation models. The performances were evaluated with a 10-fold cross-validation, temporal, and spatial validation. A total of 1,022 effective sampling days were conducted. The XGBoost model had the best performance with a training coefficient of determination (R2) of 0.99 [normalized root mean square error (nRMSE): 6.52%] and a cross-validation R2 of 0.78 (nRMSE: 31.0%). The ten most important variables were surface pressure, distance to the nearest road, temperature, calendar year, day of the year, NO2, meridional wind, the total length of roads, PM2.5, and zonal wind. The UFP levels were elevated along the main roads across different seasons, suggesting that traffic emission is an important contributor to UFP. This hybrid model outperformed prior land use regression models and thus can provide more accurate estimates of UFP for epidemiological studies. |
| first_indexed | 2024-03-13T10:22:34Z |
| format | Article |
| id | doaj.art-2beefbc5e29a4d648240a313f0fcf67d |
| institution | Directory Open Access Journal |
| issn | 0160-4120 |
| language | English |
| last_indexed | 2024-03-13T10:22:34Z |
| publishDate | 2023-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Environment International |
| spelling | doaj.art-2beefbc5e29a4d648240a313f0fcf67d2023-05-20T04:29:13ZengElsevierEnvironment International0160-41202023-05-01175107937A hybrid model for estimating the number concentration of ultrafine particles based on machine learning algorithms in central TaiwanChau-Ren Jung0Wei-Ting Chen1Li-Hao Young2Ta-Chih Hsiao3Department of Public Health, College of Public Health, China Medical University, Taichung, Taiwan; Japan Environment and Children’s Study Programme Office, Health and Environmental Risk Division, National Institute for Environmental Studies, Tsukuba, Japan; Corresponding author at: Department of Public Health, College of Public Health, China Medical University, No. 100, Sec. 1, Jingmao Rd., Beitun Dist., Taichung City 406040, Taiwan, ROC.Department of Atmospheric Sciences, National Taiwan University, Taipei, TaiwanDepartment of Occupational Safety and Health, China Medical University, Taichung, TaiwanGraduate Institute of Environmental Engineering, National Taiwan University, Taipei, TaiwanModeling is a cost-effective measure to estimate ultrafine particle (UFP) levels. Previous UFP estimates generally relied on land-use regression with insufficient temporal resolution. We carried out in-situ measurements for UFP in central Taiwan and developed a model incorporating satellite-based measurements, meteorological variables, and land-use data to estimate daily UFP levels at a 1-km resolution. Two sampling campaigns were conducted for measuring hourly UFP concentrations at six sites between 2008–2010 and 2017–2021, respectively, using scanning mobility particle sizers. Three machine learning algorithms, namely random forest, eXtreme gradient boosting (XGBoost), and deep neural network, were used to develop UFP estimation models. The performances were evaluated with a 10-fold cross-validation, temporal, and spatial validation. A total of 1,022 effective sampling days were conducted. The XGBoost model had the best performance with a training coefficient of determination (R2) of 0.99 [normalized root mean square error (nRMSE): 6.52%] and a cross-validation R2 of 0.78 (nRMSE: 31.0%). The ten most important variables were surface pressure, distance to the nearest road, temperature, calendar year, day of the year, NO2, meridional wind, the total length of roads, PM2.5, and zonal wind. The UFP levels were elevated along the main roads across different seasons, suggesting that traffic emission is an important contributor to UFP. This hybrid model outperformed prior land use regression models and thus can provide more accurate estimates of UFP for epidemiological studies.http://www.sciencedirect.com/science/article/pii/S0160412023002106Estimation modelFeature importanceMachine learningMeteorological variablesSatellite-based measurementUltrafine particles |
| spellingShingle | Chau-Ren Jung Wei-Ting Chen Li-Hao Young Ta-Chih Hsiao A hybrid model for estimating the number concentration of ultrafine particles based on machine learning algorithms in central Taiwan Environment International Estimation model Feature importance Machine learning Meteorological variables Satellite-based measurement Ultrafine particles |
| title | A hybrid model for estimating the number concentration of ultrafine particles based on machine learning algorithms in central Taiwan |
| title_full | A hybrid model for estimating the number concentration of ultrafine particles based on machine learning algorithms in central Taiwan |
| title_fullStr | A hybrid model for estimating the number concentration of ultrafine particles based on machine learning algorithms in central Taiwan |
| title_full_unstemmed | A hybrid model for estimating the number concentration of ultrafine particles based on machine learning algorithms in central Taiwan |
| title_short | A hybrid model for estimating the number concentration of ultrafine particles based on machine learning algorithms in central Taiwan |
| title_sort | hybrid model for estimating the number concentration of ultrafine particles based on machine learning algorithms in central taiwan |
| topic | Estimation model Feature importance Machine learning Meteorological variables Satellite-based measurement Ultrafine particles |
| url | http://www.sciencedirect.com/science/article/pii/S0160412023002106 |
| work_keys_str_mv | AT chaurenjung ahybridmodelforestimatingthenumberconcentrationofultrafineparticlesbasedonmachinelearningalgorithmsincentraltaiwan AT weitingchen ahybridmodelforestimatingthenumberconcentrationofultrafineparticlesbasedonmachinelearningalgorithmsincentraltaiwan AT lihaoyoung ahybridmodelforestimatingthenumberconcentrationofultrafineparticlesbasedonmachinelearningalgorithmsincentraltaiwan AT tachihhsiao ahybridmodelforestimatingthenumberconcentrationofultrafineparticlesbasedonmachinelearningalgorithmsincentraltaiwan AT chaurenjung hybridmodelforestimatingthenumberconcentrationofultrafineparticlesbasedonmachinelearningalgorithmsincentraltaiwan AT weitingchen hybridmodelforestimatingthenumberconcentrationofultrafineparticlesbasedonmachinelearningalgorithmsincentraltaiwan AT lihaoyoung hybridmodelforestimatingthenumberconcentrationofultrafineparticlesbasedonmachinelearningalgorithmsincentraltaiwan AT tachihhsiao hybridmodelforestimatingthenumberconcentrationofultrafineparticlesbasedonmachinelearningalgorithmsincentraltaiwan |