Articles | Volume 14, issue 8
https://doi.org/10.5194/amt-14-5333-2021
https://doi.org/10.5194/amt-14-5333-2021
Research article
 | 
04 Aug 2021
Research article |  | 04 Aug 2021

Estimation of PM2.5 concentration in China using linear hybrid machine learning model

Zhihao Song, Bin Chen, Yue Huang, Li Dong, and Tingting Yang

Related authors

Urban-rural patterns and driving factors of particulate matter pollution decrease in eastern china
Zhihao Song and Bin Chen
EGUsphere, https://doi.org/10.5194/egusphere-2025-2194,https://doi.org/10.5194/egusphere-2025-2194, 2025
Short summary

Cited articles

Adams, M. D., Massey, F., Chastko, K., and Cupini, C.: Spatial modelling of particulate matter air pollution sensor measurements collected by community scientists while cycling, land use regression with spatial cross-validation, and applications of machine learning for data correction, Atmos. Environ., 230, https://doi.org/10.1016/j.atmosenv.2020.117479, 2020. 
Apte, J. S., Marshall, J. D., Cohen, A. J., and Brauer, M.: Addressing Global Mortality from Ambient PM2.5, Environ. Sci. Technol., 49, 8057–8066, https://doi.org/10.1021/acs.est.5b01236, 2015. 
Breiman, L.: Random forests, Mach. Learn., 45, 5–32, https://doi.org/10.1023/A:1010933404324, 2001. 
CGIAR Consortium for Spatial Information: SRTM3, available at: https://srtm.csi.cgiar.org/srtmdata/, CGIAR [data set], last access: 1 July 2021. 
Download
Short summary
The linear hybrid machine learning model achieves the expected target well. The overall inversion accuracy (R2) of the model is 0.84, and the RMSE is 12.92 µg m−3. R2 was above 0.7 in more than 70 % of the sites, whereas RMSE and mean absolute error were below 20 and 15 µg m−3, respectively. There was severe pollution in winter with an average PM2.5 concentration of 62.10 µg m−3. However, there was only slight pollution in summer with an average PM2.5 concentration of 47.39 µg m−3.
Share