Journal
ATMOSPHERIC ENVIRONMENT
Volume 249, Issue -, Pages -Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.atmosenv.2021.118212
Keywords
PM2.5; AOD; CatBoost; Wavelet decomposition; Remote sensing; Beijing-Tianjin-Hebei
Funding
- National key research and development project [2017YFB0504203]
- Central Guide Local Science and Technology Development projects [2017L3012]
- Natural Science Foundation of China [41906019]
- Natural Science Foundation of Fujian Province [2019J01650]
- China Postdoctoral Science Foundation [2019M652245]
Ask authors/readers for more resources
The study introduces a new method using CatBoost machine learning approach to reconstruct satellite AOD data and estimate PM2.5, which substantially improves the performance of AOD reconstruction and shows that wavelet decomposition helps improve estimation accuracy. The approach has a good performance in estimating PM2.5 with a cross-validation R-2 of 0.88 and root-mean-squared error of 17.79 µg/m(3).
High-resolution data of fine particulate matters (PM2.5) are of great interest for air pollution prevention and control. However, due to the uneven spatial distribution of ground stations, satellite acquisition cycle, and cloud/rain, high-resolution products cannot be provided on a complete spatio-temporal scale. To provide a full daily PM2.5 product in recent years at 1-km grid of the Beijing-Tianjin-Hebei (BTH) region, here we apply a state-ofthe-art machine learning approach, CatBoost, to (1) reconstruct satellite aerosol optical depth (AOD) data; and to (2) estimate gridded PM2.5 from station measurements combining elevation, meteorological factors, and the reconstructed AOD data. Compared with existing approaches, CatBoost substantially improved the performance of AOD reconstruction by similar to 16%. We further show that a wavelet decomposition procedure on the station-based PM2.5 and input variables is helpful to improve the estimation accuracy. Overall, the approach has a good performance in estimating PM2.5 with a cross-validation R-2 of 0.88 and root-mean-squared error of 17.79 mu g/m(3). From the new dataset, population-weighted PM2.5 revealed heterogeneous spatial distribution of exposure in different areas, consistently higher in the Southern and Eastern BTH and lower in Beijing and Northern BTH. In recent years, both AOD and PM2.5 in the BTH region had notable interannual decreases, which can be attributed to the emission reduction efforts and interannual natural variabilities.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available