Abstract
Due to urbanization and industrialization, PM2.5 (particulate matter with a diameter less than 2.5 μm) pollution has become a serious environmental problem. The low spatial resolution and insufficient coverage of PM2.5 observation stations affect research on pollution causes and human health risks. With the launch of FY-4A, new generation of Chinese geostationary weather satellites, it is possible to obtain PM2.5 with high temporal and spatial resolution covering all China. In this study, FY-4A top-of-the-atmosphere reflectance data, meteorological factors, and geographic information were input into the deep forest (DF) model to obtain the hourly PM2.5 in China. The samples based 10-fold cross validation of DF with an hourly R2 of 0.83–0.88, and the root mean square error is 8.81–14.7 μg/m3, while the R2 of the 10-fold cross validation result based on sites was 0.77. The monthly (R2 = 0.98) and seasonal (R2 = 0.99) estimated results showed high consistency with the observations. Feature importance showed that the contribution of estimated features to the model varies with regions and seasons. Estimation results indicated the substantial spatiotemporal differences in PM2.5, and pollution was the highest between 09:00–10:00 and then gradually decreased. Regions with highest pollution of PM2.5 in China were mainly distributed in the Tarim Basin and Central China. The pollution assessment results in China indicated that: 1) In more than 80% of the winter days PM2.5 was higher than the World Health Organization interim target 3 (37.5 μg/m3); 2) The bimodal distribution of PM2.5 indicated that there are obvious differences in pollution between cities and suburbs; 3) In autumn and winter, the regions where population-weighted PM2.5 was higher than IT-3 were mainly in Beijing-Tianjin-Hebei, Central China, Guanzhong Plain, Sichuan Basin, and Yangtze River Delta. Our results showed that FY-4A has advantages of high resolution and coverage and thus shows great potential for estimating pollutants.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.