Satellite-based ground PM2.5 estimation using a gradient boosting decision tree.
Satellite-based ground PM2.5 estimation using a gradient boosting decision tree.
复制标题
DOI：
10.1016/j.chemosphere.2020.128801
复制
发表时间：
2020-10
期刊：
影响因子：
8.8
通讯作者：
Tianning Zhang;Weihuan He;Hui Zheng;Yaoping Cui;Hongquan Song;Shen-Ming Fu
中科院分区：
文献类型：
--
作者：
Tianning Zhang;Weihuan He;Hui Zheng;Yaoping Cui;Hongquan Song;Shen-Ming Fu
空气动力学直径小于2.5 μm的细颗粒物（PM2.5）是全球范围内对人类健康构成威胁的主要空气污染物之一。星载气溶胶光学厚度（AOD）产品是获取PM2. 5信息的有效指标，具有覆盖范围广、分辨率高的特点，弥补了现有监测站点稀疏、分布不均的不足。本文提出了一种结合人类活动和各种自然变量的梯度提升决策树（GBDT）模型，用于直接从AOD产品中估算2017年中国地面PM2. 5浓度。GBDT模型在估算PM2.5日浓度的时间变异性和空间差异性方面表现良好，拟合模型（10倍交叉验证）的决定系数相对较高，为0.98（0.81），均方根误差较低，为3.82（11.57）μg/m3，平均绝对误差为1.44（7.45）μg/m3。季节性的检查表明，夏季有最干净的空气与最高的估计精度，而冬季有最污染的空气与最低的估计精度。该模型成功地捕捉到了2017年中国各地的PM2.5分布模式，显示新疆西南部、华北平原和四川盆地的PM2.5水平较高，尤其是在冬季。与其他模型相比，GBDT模型表现出最高的性能在3公里分辨率的PM2. 5的估计。该算法可以提高PM2. 5的空间分辨率，特别是在夏季，可以提高PM2. 5的估计精度。总之，本研究为提高卫星监测PM2. 5的精度提供了一种潜在的方法。
Fine particulate matter with an aerodynamic diameter less than 2.5 μm (PM2.5) is one of the major air pollutants risks to human health worldwide. Satellite-based aerosol optical depth (AOD) products are an effective metric for acquiring PM2.5information, featuring broad coverage and high resolution, which compensate for the sparse and uneven distribution of existing monitoring stations. In this study, a gradient boosting decision tree (GBDT) model for estimating ground PM2.5concentration directly from AOD products across China in 2017, integrating human activities and various natural variables was proposed. The GBDT model performed well in estimating temporal variability and spatial contrasts in daily PM2.5concentrations, with relatively high fitted model (10-fold cross-validation) coefficients of determination of 0.98 (0.81), low root mean square errors of 3.82 (11.57) μg/m3, and mean absolute error of 1.44 (7.45) μg/m3. Seasonal examinations revealed that summer had the cleanest air with the highest estimation accuracies, whereas winter had the most polluted air with the lowest estimation accuracies. The model successfully captured the PM2.5distribution pattern across China in 2017, showing high levels in southwest Xinjiang, the North China Plain, and the Sichuan Basin, especially in winter. Compared with other models, the GBDT model showed the highest performance in the estimation of PM2.5with a 3-km resolution. This algorithm can be adopted to improve the accuracy of PM2.5estimation with higher spatial resolution, especially in summer. In general, this study provided a potential method of improving the accuracy of satellite-based ground PM2.5estimation.