Key Laboratory for Semi-Arid Climate Change of the Ministry of Education, College of Atmospheric Sciences, Lanzhou University, Lanzhou, 730000, China; Collaborative Innovation Center for Western Ecological Safety, Lanzhou, 730000, China.
Key Laboratory for Semi-Arid Climate Change of the Ministry of Education, College of Atmospheric Sciences, Lanzhou University, Lanzhou, 730000, China; Collaborative Innovation Center for Western Ecological Safety, Lanzhou, 730000, China.
Environ Pollut. 2022 Mar 15;297:118826. doi: 10.1016/j.envpol.2022.118826. Epub 2022 Jan 8.
PM (fine particulate matter with aerodynamics diameter <2.5 μm) is the most important component of air pollutants, and has a significant impact on the atmospheric environment and human health. Using satellite remote sensing aerosol optical depth (AOD) to explore the hourly ground PM distribution is very helpful for PM pollution control. In this study, Himawari-8 AOD, meteorological factors, geographic information, and a new deep forest model were used to construct an AOD-PM estimation model in China. Hourly cross-validation results indicated that estimated PM values were consistent with the site observation values, with an R range of 0.82-0.91 and root mean square error (RMSE) of 8.79-14.72 μg/m³, among which the model performance reached the optimum value between 13:00 and 15:00 Beijing time (R > 0.9). Analysis of the correlation coefficient between important features and PM showed that the model performance was related to AOD and affected by meteorological factors, particularly the boundary layer height. Deep forest can detect diurnal variations in pollutant concentrations, which were higher in the morning, peaked at 10:00-11:00, and then began to decline. High-resolution PM concentrations derived from the deep forest model revealed that some cities in China are seriously polluted, such as Xi 'an, Wuhan, and Chengdu. Our model can also capture the direction of PM, which conforms to the wind field. The results indicated that due to the combined effect of wind and mountains, some areas in China experience PM pollution accumulation during spring and winter. We need to be vigilant because these areas with high PM concentrations typically occur near cities.
PM（空气动力学直径<2.5μm 的细颗粒物）是空气污染物中最重要的组成部分，对大气环境和人类健康有重大影响。利用卫星遥感气溶胶光学厚度（AOD）来探索每小时地面 PM 分布，对于 PM 污染控制非常有帮助。本研究利用 Himawari-8 AOD、气象因素、地理信息和一种新的深度森林模型，构建了中国的 AOD-PM 估算模型。每小时的交叉验证结果表明，估算的 PM 值与站点观测值一致，R 范围在 0.82-0.91 之间，均方根误差（RMSE）为 8.79-14.72μg/m³，其中模型性能在北京时间 13:00-15:00 之间达到最佳值（R>0.9）。对重要特征与 PM 之间的相关系数进行分析表明，模型性能与 AOD 相关，受气象因素特别是边界层高度的影响。深度森林可以检测污染物浓度的日变化，浓度在早上较高，在 10:00-11:00 达到峰值，然后开始下降。深度森林模型得出的高分辨率 PM 浓度显示，中国的一些城市污染严重，如西安、武汉和成都。我们的模型还可以捕捉 PM 的方向，这与风向一致。结果表明，由于风和山脉的共同作用，中国的一些地区在春季和冬季会出现 PM 污染积累。由于这些高 PM 浓度的地区通常位于城市附近，我们需要保持警惕。
