Estimation of Atmospheric PM<sub>10</sub> Concentration in China Using an Interpretable Deep Learning Model and Top‐of‐the‐Atmosphere Reflectance Data From China’s New Generation Geostationary Meteorological Satellite, FY‐4A
Bin Chen, Zhihao Song, Jianping Huang, Peng Zhang, Xiuqing Hu, Xingying Zhang, Xiaodan Guan, Jinming Ge, Xingzhao Zhou
Abstract
Abstract The rapid urbanization in China and the long‐range transport dust (LRTD) from arid and semi‐arid areas has resulted in an increase of PM 10 concentration. In this study, an interpretable deep learning model [deep forest (DF)] with FY‐4A top‐of‐the‐atmosphere reflectance (TOAR) data were used to obtain the hourly PM 10 in China. The optimal hourly average R 2 of 10‐fold cross validation can achieve 0.85 (13:00 Beijing time); The R 2 (RMSE, μg/m³) of the daily, monthly, and annual averages were 0.82 (24.16), 0.97 (6.53), and 0.99 (2.30), respectively. Using TOAR data, the DF model performed better than other machine learning models. The feature importance of the TOAR‐PM 10 model showed that TOAR and meteorological elements both contributed significantly to the model. In spring, the PM 10 in northern China was greater than that in southern China, which may be related to the LRTD. Excluding the dust weather periods, the areas with high PM 10 values in China were mainly in cities and their suburbs, where were correlated with human activities. During a dust weather process, LRTD increased PM 10 in northern China by 80.4%. During a mixture haze and dust weather process, the PM 10 increased by 130.2% in northern China, of which LRTD led to an increase of 73.7%. The sources (from the Taklimakan Desert in China) and transmission paths of these two LRTD processes were similar. The contribution of LRTD to PM 10 was related to dust intensity and meteorological conditions. The results showed that LRTD and local pollution to PM 10 was both important in haze periods.