气候变化领域集成服务门户(CCPortal): Gaussian Markov random fields improve ensemble predictions of daily 1 km PM2.5 and PM10 across France

CCPortal

DOI	10.1016/j.atmosenv.2021.118693
	Gaussian Markov random fields improve ensemble predictions of daily 1 km PM2.5 and PM10 across France
	Hough I.; Sarafian R.; Shtein A.; Zhou B.; Lepeule J.; Kloog I.
发表日期	2021
ISSN	1352-2310
卷号	264
英文摘要	Understanding the health impacts of particulate matter (PM) requires spatiotemporally continuous exposure estimates. We developed a multi-stage ensemble model that estimates daily mean PM2.5 and PM10 at 1 km spatial resolution across France from 2000 to 2019. First, we alleviated the sparsity of PM2.5 monitors by imputing PM2.5 at more common PM10 monitors. We also imputed missing satellite aerosol optical depth (AOD) based on modelled AOD from atmospheric reanalyses. Next, we trained three base learners (mixed models, Gaussian Markov random fields, and random forests) to predict daily PM concentrations based on AOD, meteorology, and other variables. Finally, we generated ensemble predictions using a generalized additive model with spatiotemporally varying weights that exploit the strengths and weaknesses of each base learner. The Gaussian Markov random field dominated the ensemble, outperforming mixed models and random forests at most locations on most days. Rigorous cross-validation showed that the ensemble predictions were quite accurate, with mean absolute error (MAE) of 2.72 μg/m3 and R2 of 0.76 for PM2.5; PM10 MAE was 4.26 μg/m3 and R2 0.71. Our predictions are available to improve epidemiological studies of acute and chronic PM exposure in urban and rural France. © 2021 Elsevier Ltd
关键词	Aerosol optical depth Ensemble model Epidemiology Exposure assessment Particulate matter
语种	英语
scopus关键词	Atmospheric aerosols; Forecasting; Gaussian distribution; Image segmentation; Markov processes; Optical properties; Particles (particulate matter); Aerosol optical depths; Base learners; Ensemble models; Ensemble prediction; Exposure assessment; Gaussian Markov random field; Mean absolute error; Mixed modeling; Particulate Matter; Particulate matter 10; Decision trees; additive; aerosol; Gaussian method; health impact; optical depth; particulate matter; spatial resolution; aerosol; article; cross validation; France; human; Markov random field; meteorology; optical depth; particulate matter 10; particulate matter 2.5; particulate matter exposure; prediction; random forest; France; Varanidae
来源期刊	ATMOSPHERIC ENVIRONMENT
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/248228
作者单位	Univ. Grenoble Alpes, Inserm, CNRS, IABLa Tronche, France; Department of Geography and Environmental Development, Ben-Gurion University of the Negev, Be'er Sheva, Israel; Department of Industrial Engineering, Ben-Gurion University of the Negev, Be'er Sheva, Israel; Potsdam Institute for Climate Impact Research (PIK), Member of the Leibniz Association, Potsdam, Germany
推荐引用方式 GB/T 7714	Hough I.,Sarafian R.,Shtein A.,et al. Gaussian Markov random fields improve ensemble predictions of daily 1 km PM2.5 and PM10 across France[J],2021,264.
APA	Hough I.,Sarafian R.,Shtein A.,Zhou B.,Lepeule J.,&Kloog I..(2021).Gaussian Markov random fields improve ensemble predictions of daily 1 km PM2.5 and PM10 across France.ATMOSPHERIC ENVIRONMENT,264.
MLA	Hough I.,et al."Gaussian Markov random fields improve ensemble predictions of daily 1 km PM2.5 and PM10 across France".ATMOSPHERIC ENVIRONMENT 264(2021).