It is of great significance to explore the spatial-temporal variations and estimate the relative importance of the influencing factors of PM2.5 and O3 pollution. The study established nationwide surface O3, NO2, and SO2 estimation models using the extreme gradient boosting model and the data fusion method. The cross-validation results indicated that the forecasted models performed well (R-values from 0.86 to 0.95). The results revealed that the pollution levels of O3, PM2.5, NO2, and SO2 in the North China Plain (NCP) were the highest in China. Subsequently, a multi-task learning model was utilized to estimate the relative importance of influential factors on the PM2.5 and O3 pollution in the NCP. The sensitivity analysis results indicated that the O3 pollution from 2010–2020 in the NCP was susceptible to meteorological factors such as ultraviolet radiation and temperature, as well as anthropogenic precursors such as NOX, and PM2.5 pollution in the NCP was constrained by both meteorological factors (44.62%) and anthropogenic emissions (16.86%). The impact of NO2 on PM2.5 pollution was similar to its impact on O3 pollution; therefore, the importance of NO2 emission reduction to PM2.5 pollution is as important as that of O3 pollution, whereas the impact of SO2 on PM2.5 was much greater than its impact on O3 pollution, so SO2 emission reduction is more important for PM2.5. |
ACCESS THE FULL ARTICLE
No SPIE Account? Create one
CITATIONS
Cited by 3 scholarly publications.
Pollution
Data modeling
Ultraviolet radiation
Content addressable memory
Air contamination
Atmospheric modeling
Machine learning