Estimation of PM10 and PM2.5 Using Backscatter Coefficient of Ceilometer and Machine Learning
Abstract Air quality issues, including health and environmental challenges, have recently become more relevant in urban areas with large populations and active industries. Therefore, particulate matter (PM) estimation with high accuracy using various methods is required. In this study, PM10 and PM2....
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2023-10-01
|
| Series: | Aerosol and Air Quality Research |
| Subjects: | |
| Online Access: | https://doi.org/10.4209/aaqr.230033 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862804484980736 |
|---|---|
| author | Bu-Yo Kim Joo Wan Cha Yong Hee Lee |
| author_facet | Bu-Yo Kim Joo Wan Cha Yong Hee Lee |
| author_sort | Bu-Yo Kim |
| collection | DOAJ |
| description | Abstract Air quality issues, including health and environmental challenges, have recently become more relevant in urban areas with large populations and active industries. Therefore, particulate matter (PM) estimation with high accuracy using various methods is required. In this study, PM10 and PM2.5 in Cheongju city, South Korea, were estimated using the attenuated backscatter coefficient of the ceilometer and meteorological observation data from an automatic weather station with supervised machine learning (ML). The backscatter coefficient data were obtained from the vertical layer with the highest correlation with PM10 and PM2.5. The estimation methods utilized were tree-, vector-, neural-, and regularization-based supervised ML. The extreme gradient boosting method yielded the highest PM estimation accuracy. The estimation of PM10 and PM2.5 for the test data set was more accurate than that in previous studies that used satellite and ground-based meteorological data (bias = 0.10 µg m−3, root mean square error (RMSE) = 14.44 µg m−3, and R = 0.92 for PM10; and bias = 0.12 µg m−3, RMSE = 7.16 µg m−3, and R = 0.91 for PM2.5). Particularly, the correlation coefficient was the highest for the estimation results for strong haze cases (1 km < visibility ≤ 5 km) (R = 0.95 for PM10; R = 0.89 for PM2.5). Therefore, PM estimation using meteorological observation data can help obtain meteorological and PM information simultaneously, making it useful for air quality monitoring. |
| format | Article |
| id | doaj-art-4b281bbacf5540b2b9a529070835b7c3 |
| institution | Kabale University |
| issn | 1680-8584 2071-1409 |
| language | English |
| publishDate | 2023-10-01 |
| publisher | Springer |
| record_format | Article |
| series | Aerosol and Air Quality Research |
| spelling | doaj-art-4b281bbacf5540b2b9a529070835b7c32025-02-09T12:23:12ZengSpringerAerosol and Air Quality Research1680-85842071-14092023-10-01231211710.4209/aaqr.230033Estimation of PM10 and PM2.5 Using Backscatter Coefficient of Ceilometer and Machine LearningBu-Yo Kim0Joo Wan Cha1Yong Hee Lee2Research Applications Department, National Institute of Meteorological SciencesResearch Applications Department, National Institute of Meteorological SciencesResearch Applications Department, National Institute of Meteorological SciencesAbstract Air quality issues, including health and environmental challenges, have recently become more relevant in urban areas with large populations and active industries. Therefore, particulate matter (PM) estimation with high accuracy using various methods is required. In this study, PM10 and PM2.5 in Cheongju city, South Korea, were estimated using the attenuated backscatter coefficient of the ceilometer and meteorological observation data from an automatic weather station with supervised machine learning (ML). The backscatter coefficient data were obtained from the vertical layer with the highest correlation with PM10 and PM2.5. The estimation methods utilized were tree-, vector-, neural-, and regularization-based supervised ML. The extreme gradient boosting method yielded the highest PM estimation accuracy. The estimation of PM10 and PM2.5 for the test data set was more accurate than that in previous studies that used satellite and ground-based meteorological data (bias = 0.10 µg m−3, root mean square error (RMSE) = 14.44 µg m−3, and R = 0.92 for PM10; and bias = 0.12 µg m−3, RMSE = 7.16 µg m−3, and R = 0.91 for PM2.5). Particularly, the correlation coefficient was the highest for the estimation results for strong haze cases (1 km < visibility ≤ 5 km) (R = 0.95 for PM10; R = 0.89 for PM2.5). Therefore, PM estimation using meteorological observation data can help obtain meteorological and PM information simultaneously, making it useful for air quality monitoring.https://doi.org/10.4209/aaqr.230033PM10PM2.5CeilometerBackscatter coefficientMachine learningExtreme gradient boosting |
| spellingShingle | Bu-Yo Kim Joo Wan Cha Yong Hee Lee Estimation of PM10 and PM2.5 Using Backscatter Coefficient of Ceilometer and Machine Learning Aerosol and Air Quality Research PM10 PM2.5 Ceilometer Backscatter coefficient Machine learning Extreme gradient boosting |
| title | Estimation of PM10 and PM2.5 Using Backscatter Coefficient of Ceilometer and Machine Learning |
| title_full | Estimation of PM10 and PM2.5 Using Backscatter Coefficient of Ceilometer and Machine Learning |
| title_fullStr | Estimation of PM10 and PM2.5 Using Backscatter Coefficient of Ceilometer and Machine Learning |
| title_full_unstemmed | Estimation of PM10 and PM2.5 Using Backscatter Coefficient of Ceilometer and Machine Learning |
| title_short | Estimation of PM10 and PM2.5 Using Backscatter Coefficient of Ceilometer and Machine Learning |
| title_sort | estimation of pm10 and pm2 5 using backscatter coefficient of ceilometer and machine learning |
| topic | PM10 PM2.5 Ceilometer Backscatter coefficient Machine learning Extreme gradient boosting |
| url | https://doi.org/10.4209/aaqr.230033 |
| work_keys_str_mv | AT buyokim estimationofpm10andpm25usingbackscattercoefficientofceilometerandmachinelearning AT joowancha estimationofpm10andpm25usingbackscattercoefficientofceilometerandmachinelearning AT yongheelee estimationofpm10andpm25usingbackscattercoefficientofceilometerandmachinelearning |