基于随机森林模型的中国近地面NO<sub>2</sub>浓度估算

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (2263 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract In order to capture the complex and nonlinear relationship between ground-level NO₂ concentrations and predictor variables, random forest (RF) models combined with multiple types of geographic covariates were developed to estimate ground-level NO₂ concentrations. In this process, satellite-based OMI NO₂ tropospheric columns and multi-source geographic covariates (i.e., road network, meteorological factors, land use/cover, DEM and population density) were used as potential predictor variables and ground-level NO₂ concentrations were used as the dependent variable for RF models construction. The reliability of the RF models was validated by comparison with ground-measured NO₂ concentrations and typical linear land use regression (LUR) models. Afterwards, the spatial distribution characteristics of NO₂ concentration mapped by RF models across time scales in mainland China were assessed and analyzed. Results showed that RF modeling outperformed LUR modeling with obvious higher model fitting-based R² and lower RMSE, which were 0.85 and 6.08μg/m³ for monthly RF models compared with 0.53 and 10.48μg/m³ for LUR models. This was confirmed by the cross-validation-based R² and RMSE with values of 0.84 and 6.33μg/m³, while those of LUR models were 0.53 and 10.49μg/m³. The partial dependence of RF models suggested that the actual relationships between ground-level NO₂ concentrations and predictor variables were nonlinear and time-dependent. OMI NO₂ tropospheric columns contributed most strongly to the RF models of NO₂ concentrations, which had largest percentage of IncMSE (ranged from 97.40% to 116.54%). Meanwhile, the importance of different geographic variables could not be disregarded, which had values of IncMSE between 23.34% and 47.53%. Additionally, the NO₂ concentrations simulated by RF models showed that the annual average NO₂ concentrations across mainland China during the study period were 24.67μg/m³, which had significant seasonal variations with value of 31.85, 24.86, 23.24 and 18.75μg/m³ in winter, autumn, spring and summer, respectively. Spatially, higher concentrations of simulated NO₂ concentrations occurred in the North China Plain and decreased to the periphery. Compared with the existing studies focusing on tropospheric NO₂ column density, this study sheds new light on accurate monitoring of spatial-temporal distribution of ground-level NO₂ pollution. Findings from this study will provide new implications for policy making for future national prevention and control of air pollution to reduce the population health burden in China.

Key words： NO₂ spatial-temporal distribution random forest satellite remote sensing geographic covariates

Received: 03 July 2018

PACS:

X511

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	YOU Jie-wen
	ZOU Bin
	ZHAO Xiu-ge
	XU Shan
	HE Rui

Cite this article:

YOU Jie-wen,ZOU Bin,ZHAO Xiu-ge等. Estimating ground-level NO₂ concentrations across mainland China using random forests regression modeling[J]. CHINA ENVIRONMENTAL SCIENCECE, 2019, 39(3): 969-979.

URL:

http://www.zghjkx.com.cn/EN/ OR http://www.zghjkx.com.cn/EN/Y2019/V39/I3/969

[1]	WHO. Air quality guidelines:Global update 2005. Particulate matter, ozone, nitrogen dioxide and sulfur dioxide[M]. World Health Organization, 2006,331-339.
[2]	王占山,李云婷,陈添,等.北京城区臭氧日变化特征及与前体物的相关性分析[J]. 中国环境科学, 2014,34(12):3001-3008. Wang Z, Li Y, Chen T, et al. Analysis on diurnal variation characteristics of ozone and correlations with its precursors in urban atmosphere of Beijing[J]. China Environmental Science, 2014, 34(12):3001-3008.
[3]	Samoli E, Aga E, Touloumi G, et al. Short-term effects of nitrogen dioxide on mortality:an analysis within the APHEA project[J]. Environmental Health Perspectives, 2007,115(11):1578-1583.
[4]	Chiusolo M, Cadum E, Stafoggia M, et al. Short-term effects of nitrogen dioxide on mortality and susceptibility factors in 10 Italian cities:the EpiAir study[J]. Environmental Health Perspectives, 2011, 119(9):1233.
[5]	Chen R, Samoli E, Wong C M, et al. Associations between short-term exposure to nitrogen dioxide and mortality in 17Chinese cities:the China Air Pollution and Health Effects Study (CAPES)[J]. Environment International, 2012,45:32-38.
[6]	张兴赢,张鹏,张艳,等.近10a中国对流层NO2的变化趋势,时空分布特征及其来源解析[J]. 中国科学:D辑, 2007,37(10):1409-1416. Zhang X, Zhang P, Zhang Y, et al. The tropospheric NO2 trends, the temporal and spatial distribution characteristics and source apportionment for nearly 10 years in China[J]. Science in China, 2007, 37(10):1409-1416.
[7]	Vinken G C M, Boersma K F, Maasakkers J D, et al. Worldwide biogenic soil NOx emissions inferred from OMI NO2 observations[J]. Atmospheric Chemistry & Physics, 2014,14(14):10363-10381.
[8]	中华人民共和国国家统计局.中国统计年鉴[M]. 北京:中国统计出版, 2016:250-310. National bureau of statistics of the People's Republic of China, China statistical yearbook[M]. Beijing:China Statistics Press, 2016:250-310.
[9]	Krotkov N A, McLinden C A, Li C, et al. Aura OMI observations of regional SO2 and NO2 pollution changes from 2005 to 2015[J]. Atmospheric Chemistry and Physics, 2016,16(7):4605-4629.
[10]	Zou B, Zheng Z, Wan N, et al. An optimized spatial proximity model for fine particulate matter air pollution exposure assessment in areas of sparse monitoring[J]. International Journal of Geographical Information Science, 2016,30(4):727-747.
[11]	胡晨霞,邹滨,李沈鑫,等.城市微环境PM2.5浓度空间分异特征分析[J]. 中国环境科学, 2018,38(3):910-916. Hu C, Zou B, Li S, et al. Spatial heterogeneity analysis of PM2.5 concentrations in intra-urban microenvironments[J]. China Environmental Science, 2018,38(3):910-916.
[12]	周春艳,厉青,何颖霞,等.山东省近10年对流层NO2柱浓度时空变化及影响因素[J]. 中国环境科学, 2015,35(8):2281-2290. Zhou C, Li Q, He Y, et al. Spatial-temporal change of tropospheric NO2 column density and its impact factors over Shandong province during 2005~2014[J]. China Environmental Science, 2015,35(8):2281-2290.
[13]	张杰,李昂,谢品华,等.基于卫星数据研究兰州市NO2时空分布特征以及冬季NOx排放通量[J]. 中国环境科学, 2015,35(8):2291-2297. Zhang J, Li A, Xie P, et al. Research on the spatial/temporal patterns of NO2 concentration and NOx emissions of Lanzhou by applying satellite data[J]. China Environmental Science, 2015,35(8):2291-2297.
[14]	章吴婷,张秀英,刘磊,等.多源卫星遥感的华北平原大气NO2浓度时空变化[J]. 遥感学报, 2018,22(2):335-346. Zhang W, Zhang X, Liu L, et al. Spatial variations in NO2 trend in North China Plain based on multi-source satellite remote sensing[J]. Journal of Remote Sensing, 2018,22(2):335-346.
[15]	高晋徽,朱彬,王言哲,等.2005~2013年中国地区对流层二氧化氮分布及变化趋势[J]. 中国环境科学, 2015,35(8):2307-2318. Gao J, Zhu B, Wang Y, et al. Distribution and long-term variation of tropospheric NO2 over China during 2005 to 2013[J]. China Environmental Science, 2015,35(8):2307-2318.
[16]	Van der A R J, Peters D, Eskes H, et al. Detection of the trend and seasonal variation in tropospheric NO2 over China[J]. Journal of Geophysical Research:Atmospheres, 2006,111(D12):317.
[17]	Zoogman P, Liu X, Suleiman R M, et al. Tropospheric emissions:Monitoring of pollution (TEMPO)[J]. Journal of Quantitative Spectroscopy and Radiative Transfer, 2017,186:17-39.
[18]	李令军,王英.基于卫星遥感与地面监测分析北京大气NO2污染特征[J]. 环境科学学报, 2011,31(12):2762-2768. Li L, Wang Y. The characterization of NO2 pollution in Beijing based on satellite and conventional observation data[J]. Acta Scientiae Circumstantiae, 2011,31(12):2762-2768.
[19]	Lamsal L N, Krotkov N A, Celarier E A, et al. Evaluation of OMI operational standard NO2 column retrievals using in situ and surface-based NO2 observations[J]. Atmospheric Chemistry and Physics, 2014,14(21):11587-11609.
[20]	浦静姣,张艳,余琦,等.上海地区O3与NO2时空特征数值模拟个例研究[J]. 中国环境科学, 2009,29(5):461-468. Pu J, Zhang Y, Yu Q, et al. Case study on the numerical simulations of the characteristics of temporal and spatial distributions of O3 and NO2 in Shanghai Area[J]. China Environmental Science, 2009,29(5):461-468.
[21]	丁宇宇,彭丽,冉靓,等.利用OMI卫星资料计算NO2地面浓度的方法研究[J]. 北京大学学报:自然科学版, 2011,47(4):671-676. Ding Y, Peng L, Ran L, et al. A method of inferring ground level NO2 using satellite-borne OMI observations[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2011,47(4):671-676.
[22]	陈良富,顾坚斌,王甜甜,等.近地面NO2浓度卫星遥感估算问题[J]. 环境监控与预警, 2016,8(3):1-5. Chen L, Gu J, Wang T, et al. Scientific problems for ground NO2 concentration estimation using doas method from satellite observation[J]. Environmental Monitoring and Forewarning, 20106,8(3):1-5.
[23]	Geddes J A, Martin R V, Boys B L, et al. Long-term trends worldwide in ambient NO2 concentrations inferred from satellite observations[J]. Environmental Health Perspectives, 2016,124(3):281.
[24]	Liu Y, Park R J, Jacob D J, et al. Mapping annual mean ground-level PM2.5 concentrations using Multiangle Imaging Spectroradiometer aerosol optical thickness over the contiguous United States[J]. Journal of Geophysical Research:Atmospheres, 2004,109(D22).
[25]	薛文博,王金南,杨金田,等.国内外空气质量模型研究进展[J]. 环境与可持续发展, 2013,38(3):14-20. Xue W, Wang J, Yang J, et al. Domestic and foreign research progress of air quality model[J]. Environment and Sustainable Development, 2013,38(3):14-20.
[26]	王占山,李晓倩,王宗爽,等.空气质量模型CMAQ的国内外研究现状[J]. 环境科学与技术, 2013,36(6L):386-391. Wang Z, Li X, Wang Z, et al. Application status of Models-3/CMAQ in environmental management[J]. Environmental Science & Technology, 2013,36(6L):386-391.
[27]	Qin K, Rao L, Xu J, et al. Estimating ground level NO2 Concentrations over central-Eastern China using a satellite-based geographically and temporally weighted regression model[J]. Remote Sensing, 2017,9(9):950.
[28]	Zou B, Luo Y, Wan N, et al. Performance comparison of LUR and OK in PM2.5 concentration mapping:a multidimensional perspective[J]. Scientific Reports, 2015,5(5):8698.
[29]	吴健生,谢舞丹,李嘉诚.土地利用回归模型在大气污染时空分异研究中的应用[J]. 环境科学, 2016,37(2):413-419. Wu J, Xie W, Li J. Application of land-use regression models in spatial-temporal differentiation of air pollution[J]. Environmental Science, 2016,37(2):413-419.
[30]	Ma Z, Hu X, Sayer A M, et al. Satellite-based spatiotemporal trends in PM2.5 concentrations:China, 2004~2013[J]. Environmental health perspectives, 2016,124(2):184.
[31]	Xu S, Zou B, Shafi S, et al. A hybrid Grey-Markov/LUR model for PM10 concentration prediction under future urban scenarios[J]. Atmospheric Environment, 2018,187:401-409.
[32]	Hystad P, Demers P A, Johnson K C, et al. Spatiotemporal air pollution exposure assessment for a Canadian population-based lung cancer case-control study[J]. Environmental Health, 2012,11(1):22.
[33]	薛文博,武卫玲,雷宇,等.中国高分辨率近地面NO2浓度反演[J]. 中国环境监测, 2015,31(2):153-156. Xue W, Wu W, Lei Y, et al. Retrieval of NO2 concentrations in high resolution near-surface in China[J]. Environmental Monitoring in China, 2015,31(2):153-156.
[34]	Briggs D J, Collins S, Elliott P, et al. Mapping urban air pollution using GIS:a regression-based approach[J]. International Journal of Geographical Information Science, 1997,11(7):699-718.
[35]	Beelen R, Hoek G, Vienneau D, et al. Development of NO2, and NOx, land use regression models for estimating air pollution exposure in 36study areas in Europe-The ESCAPE project[J]. Atmospheric Environment, 2013,72(2012):10-23.
[36]	Fotheringham A S, Charlton M, Brunsdon C. The geography of parameter space:An investigation of spatial non-stationarity[J]. International Journal of Geographical Information Systems, 1996, 10(5):605-627.
[37]	Zou B, Pu Q, Bilal M, et al. High-resolution satellite mapping of fine particulates based on geographically weighted regression[J]. IEEE Geoscience & Remote Sensing Letters, 2017,13(4):495-499.
[38]	Zhan Y, Luo Y, Deng X, et al. Satellite-based estimates of daily NO2 exposure in china using hybrid random forest and spatiotemporal kriging model[J]. Environmental Science & Technology, 2018,52(7):4180-4189.
[39]	Brokamp C, Jandarov R, Hossain M, et al. Predicting daily urban fine particulate matter concentrations using a random forest model[J]. Environmental Science & Technology, 2018,52(7):4173-4179.
[40]	赵佳楠,徐建华,卢德彬,等.基于RF-LUR模型的PM2.5空间分布模拟-以长江三角洲地区为例[J]. 地理与地理信息科学, 2018,34(1):18-23. Zhao J, Xu J, Lu D, et al. The spatial distribution simulation of PM2.5 concentration based on RF-LUR model:a case study of Yangtze River Delta. 2018[J]. Geography and Geo-Information Science, 2018,34(1):18-23.
[41]	《环境空气质量监测规范(试行)》(国家环境保护总局公告2007年第4号)[S]. Regulations on environmental air quality monitoring (trial) (State Environmental Protection Administration Announcement No.4of 2007)[S].
[42]	GB 3095-2012环境空气质量标准[S]. GB 3095-2012 Ambient air quality standards[S].
[43]	Breiman L. Random forest[J]. Machine Learning, 2001,45:5-32.