Guo Bin, Wu Haojie, Pei Lin, Zhu Xiaowei, Zhang Dingming, Wang Yan, Luo Pingping
College of Geomatics, Xi'an University of Science and Technology, Xi'an, Shaanxi 710054, China.
College of Geomatics, Xi'an University of Science and Technology, Xi'an, Shaanxi 710054, China.
Environ Int. 2022 Dec;170:107606. doi: 10.1016/j.envint.2022.107606. Epub 2022 Nov 3.
Surface ozone (O), one of the harmful air pollutants, generated significantly negative effects on human health and plants. Existing O datasets with coarse spatiotemporal resolution and limited coverage, and the uncertainties of O influential factors seriously restrain related epidemiology and air pollution studies. To tackle above issues, we proposed a novel scheme to estimate daily O concentrations on a fine grid scale (1 km × 1 km) from 2018 to 2020 across China based on machine learning methods using hourly observed ground-level pollutant concentrations data, meteorological data, satellite data, and auxiliary data including digital elevation model (DEM), land use data (LUD), normalized difference vegetation index (NDVI), population (POP), and nighttime light images (NTL), and to identify the difference of influential factors of O on diverse urbanization and topography conditions. Some findings were achieved. The correlation coefficients (R) between O concentrations and surface net solar radiation (SNSR), boundary layer height (BLH), 2 m temperature (T2M), 10 m v-component (MVW), and NDVI were 0.80, 0.40, 0.35, 0.30, and 0.20, respectively. The random forest (RF) demonstrated the highest validation R (0.86) and lowest validation RMSE (13.74 μg/m) in estimating O concentrations, followed by support vector machine (SVM) (R = 0.75, RMSE = 18.39 μg/m), backpropagation neural network (BP) (R = 0.74, RMSE = 19.26 μg/m), and multiple linear regression (MLR) (R = 0.52, RMSE = 25.99 μg/m). Our China High-Resolution O Dataset (CHROD) exhibited an acceptable accuracy at different spatial-temporal scales. Additionally, O concentrations showed decreasing trend and represented obviously spatiotemporal heterogeneity across China from 2018 to 2020. Overall, O was mainly affected by human activities in higher urbanization regions, while O was mainly controlled by meteorological factors, vegetation coverage, and elevation in lower urbanization regions. The scheme of this study is useful and valuable in understanding the mechanism of O formation and improving the quality of the O dataset.
地表臭氧（O₃）作为有害空气污染物之一，对人类健康和植物产生了显著的负面影响。现有的臭氧数据集时空分辨率粗糙、覆盖范围有限，且臭氧影响因素存在不确定性，严重制约了相关流行病学和空气污染研究。为解决上述问题，我们提出了一种新颖的方案，基于机器学习方法，利用每小时观测的地面污染物浓度数据、气象数据、卫星数据以及包括数字高程模型（DEM）、土地利用数据（LUD）、归一化植被指数（NDVI）、人口（POP）和夜间灯光图像（NTL）在内的辅助数据，估算2018年至2020年中国范围内精细网格尺度（1千米×1千米）上的每日臭氧浓度，并识别不同城市化和地形条件下臭氧影响因素的差异。取得了一些研究结果。臭氧浓度与地表净太阳辐射（SNSR）、边界层高度（BLH）、2米温度（T2M）、10米风速v分量（MVW）和NDVI之间的相关系数（R）分别为0.80、0.40、0.35、0.30和0.20。在估算臭氧浓度方面，随机森林（RF）的验证R值最高（0.86），验证均方根误差（RMSE）最低（13.74μg/m³），其次是支持向量机（SVM）（R = 0.75，RMSE = 18.39μg/m³）、反向传播神经网络（BP）（R = 0.74，RMSE = 19.26μg/m³）和多元线性回归（MLR）（R = 0.52，RMSE = 25.99μg/m³）。我们的中国高分辨率臭氧数据集（CHROD）在不同时空尺度上展现出了可接受的精度。此外，2018年至2020年期间，中国臭氧浓度呈下降趋势，并表现出明显的时空异质性。总体而言，在城市化程度较高的地区，臭氧主要受人类活动影响；而在城市化程度较低的地区，臭氧主要受气象因素、植被覆盖和海拔高度的控制。本研究方案对于理解臭氧形成机制和提高臭氧数据集质量具有重要作用和价值。
