中国区域PM2.5浓度估算以及影响因素解析

摘要/Abstract

摘要： 基于2018 年中国逐日PM2.5数据，选用随机森林方法构建了高精度PM2.5浓度估算模型，并在季节和区域尺度上验证了其时空适用性，进一步利用特征重要性方法系统阐释了各影响因子对PM2.5浓度变化的重要程度，最后利用偏依赖技术探究了不同影响因素的交互作用对PM2.5浓度变化产生的综合影响。结果表明： (1) 相比于多元线性回归与极端梯度提升树模型，利用多源数据构建的随机森林模型精度最高，可准确模拟出PM2.5的浓度，且在季节和区域尺度上也有良好的适用性； (2) PM2.5浓度估算模型的特征重要性排序分析发现，对2018 年全国日均PM2.5浓度影响显著的因子主要是时空、大气边界层高度等全局性因素，表明大气污染防治应把握PM2.5传输机制，强化区域联防联控； (3) 偏依赖交互效应研究发现温度和相对湿度以及年积日、纬度、温度和大气边界层高度的组合对PM2.5浓度变化会产生显著影响，说明提升空气质量要从多因子协同治理的角度出发。

关键词: 大气遥感, 随机森林, PM2.5, 时空关联

Abstract: Based on the daily PM2.5 data of China in 2018, a high-precision PM2.5 concentration estimation model was constructed using random forest method, and the temporal and spatial applicability of the model was verified at seasonal and regional scales. Further, the importance of each influencing factor to the change of PM2.5 concentration was systematically explained using the feature importance method. Finally, the comprehensive influence of the interaction of different influencing factors on PM2.5 concentration change was explored using the partial dependence technique. The results show that: (1) Compared with the multiple linear regression model and the extreme gradient ascending tree model, the random forest model based on multi-source data has the highest accuracy, which not only can accurately simulate the PM2.5 concentration, but also has good applicability at the seasonal and regional scales. (2) According to the ranking results of model feature importance, the factors that had significant impact on the average daily PM2.5 concentration in 2018 were mainly global factors such as space-time and atmospheric boundary layer height, which indicated that the prevention and control of air pollution should follow the PM2.5 transmission mechanism, and regional joint prevention and control should be strengthened in air pollution prevention. (3) The partial dependent interaction effect study shows that the combination of temperature, relative humidity, annual cumulative day, latitude, temperature and atmospheric boundary layer height has a significant impact on PM2.5 concentration change, indicating that to improve air quality should start from the perspective of multi-factor collaborative governance.

Key words: atmospheric remote sensing, random forest, PM2.5, spatio-temporal correlation

中图分类号:

X513

曹媛, 宫明艳, 沈非, 麻金继, 杨光, 林锡文, . 中国区域PM2.5浓度估算以及影响因素解析[J]. 大气与环境光学学报, 2023, 18(3): 245-257.

CAO Yuan , GONG Mingyan , SHEN Fei , MA Jinji , YANG Guang , LIN Xiwen , . Estimation of PM2.5 concentration and analysis of influencing factors in China[J]. Journal of Atmospheric and Environmental Optics, 2023, 18(3): 245-257.

参考文献 37

[1]	Zhao B, Zheng H T, Wang S X, et al. Change in household fuels dominates the decrease in PM2.5 exposure and premature
	mortality in China in 2005―2015 [J]. Proceedings of the National Academy of Sciences of the United States of America,
20	18, 115(49): 12401-12406.
[2]	Lu M, Lin B L, Inoue K, et al. PM2.5-related health impacts of utilizing ammonia-hydrogen energy in Kanto Region, Japan
[J]	Frontiers of Environmental Science & Engineering, 2018, 12(2): 13.
[3]	Cai W, Li K, Liao H, et al. Weather conditions conducive to Beijing severe haze more frequent under climate change [J].
	Nature Climate Change, 2017, 7(4): 257-262.
[4]	Duan J X, Zhai W X, Cheng C Q, et al. Socio-economic factors influencing the spatial distribution of PM2.5 concentrations in
	China: An exploratory analysis [J]. Environmental Science, 2018, 39(5): 2498-2504.
	段杰雄, 翟卫欣, 程承旗, 等. 中国PM2.5污染空间分布的社会经济影响因素分析 [J]. 环境科学, 2018, 39(5): 2498-2504.
[5]	Yin X M, Zhu B, Xiong Y J, et al. Objective analysis on circulation types and its links to haze days over Beijing during 2007
	―2016 [J]. China Environmental Science, 2020, 40(1): 123-134.
	尹晓梅, 朱彬, 熊亚军, 等. 2007―2016年北京天气分型与霾日的关联 [J]. 中国环境科学, 2020, 40(1): 123-134.
[6]	Zhao H J, Che H Z, Zhang X Y, et al. Characteristics of visibility and particulate matter (PM2.5) in an urban area of Northeast
	China [J]. Atmospheric Pollution Research, 2013, 4(4): 427-434.
[7]	Ma X Y Shi G Y, Guo Y F, et al. Radiative forcing by greenhouse gases and sulfate aerosol [J]. Acta Meteorologica Sinica,
20	05, 63(1): 41-48.
	马晓燕, 石广玉, 郭裕福, 等. 温室气体和硫酸盐气溶胶的辐射强迫作用 [J]. 气象学报, 2005, 63(1): 41-48.
[8]	Wang Y S, Zhang J K, Wang L L, et al. Researching significance, status and expectation of haze in Beijing-Tianjin-Hebei
	region [J]. Advances in Earth Science, 2014, 29(3): 388-396.
	王跃思, 张军科, 王莉莉, 等. 京津冀区域大气霾污染研究意义、现状及展望 [J]. 地球科学进展, 2014, 29(3): 388-396.
[9]	Li X, Gao Z Q, Li Y B, et al. Meteorological conditions for severe foggy haze episodes over North China in 2016-2017
	winter [J]. Atmospheric Environment, 2019, 199: 284-298.
[10]	Zhao X L, Zhou W Q, Han L J, et al. Spatiotemporal variation in PM2.5 concentrations and their relationship with
	socioeconomicfactors in China's major cities [J]. Environment International, 2019, 133: 105145.
[11]	Aguilera I, Eeftens M, Meier R, et al. Land use regression models for crustal and traffic-related PM2.5 constituents in four
	areas of the SAPALDIA study [J]. Environmental Research, 2015, 140: 377-384.
[12]	He X, Lin Z S. Interactive effects of the influencing factors on the changes of PM2.5 concentration based on GAM model [J].
	Environmental Science, 2017, 38(1): 22-32.
	贺祥, 林振山. 基于GAM模型分析影响因素交互作用对PM2.5浓度变化的影响 [J]. 环境科学, 2017, 38(1): 22-32.
[13]	Zhang L K, Lu S F, Jiao K L, et al. Pollution characteristics of particulate matter in urban districts of Baotou and their
	relationships with meteorological conditions [J]. Journal of Atmospheric and Environmental Optics, 2017, 12(6): 401-410.
	张连科, 鲁尚发, 焦坤灵, 等. 包头城区冬春大气颗粒物污染特征及其与气象条件关系 [J]. 大气与环境光学学报, 2017,
12	(6): 401-410.
[14]	Zheng K L, Huang Y, Yao X Y, et al. Correlation between PM2.5, NO2 and tourism activities, weather factors in Zhangjiajie
	City [J]. Journal of Atmospheric and Environmental Optics, 2020, 15(5): 347-356.
	郑凯莉, 黄毅, 姚小云, 胡晓琰. 张家界市PM2.5、NO2与旅游活动及天气因素的相关性分析 [J]. 大气与环境光学学报,
20	20, 15(5): 347-356.
[15]	Zhang S P, Han L J, Zhou W Q, et al. Relationships between fine particulate matter (PM2.5) and meteorological factors in
	winter at typical Chinese cities [J]. Acta Ecologica Sinica, 2016, 36(24): 7897-7907.
	张淑平, 韩立建, 周伟奇, 等. 冬季PM2.5的气象影响因素解析 [J]. 生态学报, 2016, 36(24): 7897-7907.
[16]	Jing R H, Ma J J, Wang C. Methods of PM2.5 inversion based on multi-source data [J]. Journal of Atmospheric and
	Environmental Optics, 2015, 10(1): 51-62.
	景瑞环, 麻金继, 汪超. 基于多源数据的PM2.5反演方法 [J]. 大气与环境光学学报, 2015, 10(1): 51-62.
[17]	Zhang H, Dong X G, Li Q. Principal component regression analysis of influencing factors of PM2.5 concentration [J]. Journal
	of Changchun University of Technology, 2017, 38(2): 105-110.
	张红, 董小刚, 李群. PM2.5浓度影响因素的主成分回归分析 [J]. 长春工业大学学报, 2017, 38(2): 105-110.
[18]	Zhou L, Zhou C H, Yang F, et al. Spatio-temporal evolution and the influencing factors of PM2.5 in China between 2000 and
20	11 [J]. Acta Geographica Sinica, 2017, 72(11): 2079-2092.
	周亮, 周成虎, 杨帆, 等. 2000―2011 年中国PM2.5时空演化特征及驱动因素解析 [J]. 地理学报, 2017, 72(11): 2079-
	2092.
[19]	Wang S J, Liu X P, Yang X, et al. Spatial variations of PM2.5 in Chinese Cities for the joint impacts of human activities and
	natural conditions: A global and local regression perspective [J]. Journal of Cleaner Production, 2018, 203: 143-152.
[20]	Tu M, Liu Z, He C, et al. The relationships between urban landscape patterns and fine particulate pollution in China: A
	multiscale investigation using a geographically weighted regression model [J]. Journal of Cleaner Production, 2019, 237:
11	7744.
[21]	Peng L S, Sun H, Nie F F. The evolution of temporal and spatial pattern and influencing factors of the air pollution in China
[J]	Journal of Environmental Economics, 2017, 2(1): 42-56.
	彭丽思, 孙涵, 聂飞飞. 中国大气污染时空格局演变及影响因素研究 [J]. 环境经济研究, 2017, 2(1): 42-56.
[22]	Liu H M, Fang C L, Huang J J, et al. The spatial-temporal characteristics and influencing factors of air pollution in Beijing-
	Tianjin-Hebei urban agglomeration [J]. Acta Geographica Sinica, 2018, 73(1): 177-191.
	刘海猛, 方创琳, 黄解军, 等. 京津冀城市群大气污染的时空特征与影响因素解析 [J]. 地理学报, 2018, 73(1): 177-191.
[23]	Han J, Li Y Z, Chen X C, et al. Analysis of the influencing factors of PM2.5 concentration in the urban areas of China's towns
	based on grey correlation model [J]. Environmental Protection Science, 2018, 44(3): 69-73.
	韩婧, 李元征, 陈新闯, 等. 基于灰色关联模型的中国城镇PM2.5浓度影响因素分析 [J]. 环境保护科学, 2018, 44(3):
69	-73.
[24]	He X, Lin Z S, Liu H Y, et al. Analysis of the driving factors of PM2.5 in Jiangsu Province based on grey correlation model
[J]	Acta Geographica Sinica, 2016, 71(7): 1119-1129.
	贺祥, 林振山, 刘会玉, 等. 基于灰色关联模型对江苏省PM2.5浓度影响因素的分析 [J]. 地理学报, 2016, 71(7): 1119-
	1129.
[25]	Nan Y, Zhang Q Q, Zhang B H. Influencing factors of long-term variations on gridded PM2.5 of typical regions in China
	based on GAM model [J]. Environmental Science, 2020, 41(2): 499-509.
	南洋, 张倩倩, 张碧辉. 基于GAM模型分析中国典型区域网格化PM2.5长期变化影响因素 [J]. 环境科学, 2020, 41(2):
49	9-509.
[26]	Liu Z H, Huang J W, Kong D Y. The spatial-temporal characteristics and influencing factors of PM2.5 in Wuhan metropolitan
	area [J]. Environmental Protection Science, 2019, 45(3): 51-59.
	刘子豪, 黄建武, 孔德亚. 武汉城市圈PM2.5的时空特征及其影响因素解析 [J]. 环境保护科学, 2019, 45(3): 51-59.
[27]	Wei J, Li Z Q, Lyapustin A, et al. Reconstructing 1-km-resolution high-quality PM2.5 data records from 2000 to 2018 in
	China: Spatiotemporal variations and policy implications [J]. Remote Sensing of Environment, 2021, 252: 112136.
[28]	Wei J, Huang W, Li Z Q, et al. Estimating 1-km-resolution PM2.5 concentrations across China using the space-time random
	forest approach [J]. Remote Sensing of Environment, 2019, 231: 111221.
[29]	Zheng Y, Zhang Q, Liu Y, et al. Estimating ground-level PM2.5 concentrations over three megalopolises in China using
	satellite-derived aerosol optical depth measurements [J]. Atmospheric Environment, 2016, 124: 232-242.
[30]	Breiman L. Random forests [J]. Machine learning, 2001, 45(1): 5-32.
[31]	Guidotti R, Monreale A, Ruggieri S, et al. A survey of methods for explaining black box models [J]. ACM Computing
	Surveys, 2019, 51(5): 1-42.
[32]	Wang C, Liu Q M, Ying N, et al. Air quality evaluation on an urban scale based on MODIS satellite images [J]. Atmospheric
	Research, 2013, 132: 22-34.
[33]	Zhao X Y, Wang W J, Wan W Y. Regional inequalities of residents' health level in China: 2003―2013 [J]. Acta Geographica
	Sinica, 2017, 72(4): 685-698.
	赵雪雁, 王伟军, 万文玉. 中国居民健康水平的区域差异: 2003-2013 [J]. 地理学报, 2017, 72(4): 685-698.
[34]	Miao Y C, Liu S H, Guo J P, et al. Unraveling the relationships between boundary layer height and PM2.5 pollution in China
	based on four-year radiosonde measurements [J]. Environmental Pollution, 2018, 243: 1186-1195.
[35]	Zhang J, Liu D Y, Qian Y Y, et al. Boundary layer features of the successional fog and haze episode in Jiangsu area [J].
	Journal of Arid Meteorology, 2018, 36(3): 483-491.
	张静, 刘端阳, 钱映月, 等. 一次持续性雾霾天气的边界层结构特征 [J]. 干旱气象, 2018, 36(3): 483-491.
[36]	Zhang Y H, Li S Y. Climatological characteristics of planetary boundary layer height over Japan [J]. International Journal of
	Climatology, 2019, 39(10): 4015-4028.
[37]	Li W G, Duan F K, Zhao Q, et al. Investigating the effect of sources and meteorological conditions on wintertime haze
	formation in Northeast China: A case study in Harbin [J]. Science of the Total Environment, 2021, 801: 149631.