Estimating daily ground-level PM2.5 in China with random-forest-based spatiotemporal kriging

doi:10.1016/j.scitotenv.2020.139761

	Estimating daily ground-level PM2.5 in China with random-forest-based spatiotemporal kriging
	Shao, Yanchuan 2; Ma, Zongwei 2,3; Wang, Jianghao 1,4; Bi, Jun 2
刊名	SCIENCE OF THE TOTAL ENVIRONMENT
	2020-10-20
卷号	740 页码:12
关键词	Aerosol optical depth PM2.5 Random forest Spatiotemporal kriging
ISSN号	0048-9697
DOI	10.1016/j.scitotenv.2020.139761
通讯作者	Ma, Zongwei(zma@nju.edu.cn) ; Wang, Jianghao(wangjh@lreis.ac.cn)
英文摘要	Ambient fine particulate matter (PM2.5) plays an important role in cardiovascular- and respiratory-related death. Empirical statistical models have been widely applied to estimate ambient PM2.5 concentrations with correlated variables. However, empirical statistical models ignore the nonlinear relationship between PM2.5 and covariates and assume that residuals are independent and identically distributed random variables. Here, a hybrid approach, which integrates random forest (RF) model and spatiotemporal kriging, is proposed to estimate the daily PM2.5 concentration. The proposed RF-based spatiotemporal kriging (RFSTK) model effectively captures nonlinear interactions among different predictors and accounts for the detailed spatiotemporal dependence of the PM2.5 concentration. The RFSTK model performs well in predicting the daily PM2.5 concentration. The 10-fold overall cross-validation R-2 value is 0.881, the mean absolute error (MAE) is 6.89 mu g/m(3) and the root-mean-square error (RMSE) is 11.48 mu g/m(3), indicating better performance than the original RF model (R-2 = 0.848, MAE = 7.88 mu g/m(3) and RMSE = 13.26 mu g/m(3)). The spatiotemporal prediction of the PM2.5 concentration shows that approximately 90.04% of China had a daily exposure to PM2.5 in 2018 that was below the nation's air quality standard of 75 mu g/m(3). The proposed hybrid method is entirely general and can be applied to map the ambient PM2.5 concentration over a large spatiotemporal domain. (C) 2020 Elsevier B.V. All rights reserved.
资助项目	National Natural Science Foundation of China[41531174] ; National Natural Science Foundation of China[71921003] ; National Natural Science Foundation of China[91644220]
WOS关键词	AEROSOL OPTICAL DEPTH ; SATELLITE ; MODEL ; PM10 ; REGRESSION ; EXPOSURE ; CLIMATE
WOS研究方向	Environmental Sciences & Ecology
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000562059800004
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/158032]
专题	中国科学院地理科学与资源研究所
通讯作者	Ma, Zongwei; Wang, Jianghao
作者单位	1.Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China 2.Nanjing Univ, Sch Environm, State Key Lab Pollut Control & Resource Reuse, Nanjing 210023, Jiangsu, Peoples R China 3.Nanjing Univ Informat Sci & Technol, Jiangsu Collaborat Innovat Ctr Atmospher Environm, Nanjing 210044, Jiangsu, Peoples R China 4.Jiangsu Ctr Collaborat Innovat Geog Informat Reso, Nanjing 210023, Peoples R China
推荐引用方式 GB/T 7714	Shao, Yanchuan,Ma, Zongwei,Wang, Jianghao,et al. Estimating daily ground-level PM2.5 in China with random-forest-based spatiotemporal kriging[J]. SCIENCE OF THE TOTAL ENVIRONMENT,2020,740:12.
APA	Shao, Yanchuan,Ma, Zongwei,Wang, Jianghao,&Bi, Jun.(2020).Estimating daily ground-level PM2.5 in China with random-forest-based spatiotemporal kriging.SCIENCE OF THE TOTAL ENVIRONMENT,740,12.
MLA	Shao, Yanchuan,et al."Estimating daily ground-level PM2.5 in China with random-forest-based spatiotemporal kriging".SCIENCE OF THE TOTAL ENVIRONMENT 740(2020):12.