气候变化领域集成服务门户(CCPortal): Prediction of PM2.5 daily concentrations for grid points throughout a vast area using remote sensing data and an improved dynamic spatial panel model

CCPortal

DOI	10.1016/j.atmosenv.2020.117667
	Prediction of PM2.5 daily concentrations for grid points throughout a vast area using remote sensing data and an improved dynamic spatial panel model
	Fu M.; Kelly J.A.; Clinch J.P.
发表日期	2020
ISSN	13522310
卷号	237
英文摘要	The incorporation of spatial and temporal correlations can significantly improve the accuracy of PM2.5 concentration prediction models. However, the dynamic spatial panel model which explicitly deals with these two correlations remains absent from current approaches to out-of-sample concentration prediction. An issue is that the prediction of daily concentrations for grid points across a vast area may well overwhelm existing algorithms, as it requires an enormous amount of computational resources and an enlarged spatial weight matrix. This paper develops improved algorithms that address this issue. The dynamic spatial panel approaches used in this paper predict daily series PM2.5 concentrations for grid points covering Mainland China, using daily aerosol, vegetational and meteorological remote sensing data as the explanatory variables. The predicted concentration maps offer more realistic detail in areas where monitoring stations are sparse. Indeed, the error map for the out-of-sample prediction shows that MAPE is less than 30% in most regions, and the average MAPE is 24.28%, which is relatively low compared with similar studies. In contrast to methods which cannot provide coefficients of variables, the developed method offers coefficients to assess the contributions of explanatory variables and temporal-spatial correlation terms, allows quantification of convergence effects, and can distinguish between spillover effects and local effects. A performance comparison of models with various spatial weight matrices shows that model achieves the optimal fitting levels by using the neighbouring unit number threshold of 18 or the distance threshold of 150 km. The case analysis in this paper finds that spillover effects are about three times larger than local effects, and the spatial correlation is greater than the cumulative effects of earlier concentrations. This finding adds further weight to the notion that management of PM2.5 pollution and associated impacts requires multi-regional and even multi-national coordination and effort. © 2020 Elsevier Ltd
英文关键词	Dynamic spatial panel model; Out-of-sample prediction; PM2.5 concentration; Remote sensing; Temporal-spatial correlation
语种	英语
scopus关键词	Forecasting; Matrix algebra; Remote sensing; Computational resources; Explanatory variables; Performance comparison; Sample concentration; Spatial and temporal correlation; Spatial correlations; Spatial weight matrixes; Temporal-spatial correlations; Predictive analytics; algorithm; concentration (composition); correlation; model; particulate matter; prediction; satellite data; threshold; aerosol; algorithm; article; case study; China; explanatory variable; prediction; remote sensing; China
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/145037
作者单位	School of Economics and Trade, Guangdong University of Foreign Studies, Guangzhou, China; EnvEcon, 11 Priory Office Park, Stillorgan Road, Blackrock, Co. Dublin, Ireland; UCD Environmental Policy, UCD Geary Institute and UCD Earth Institute, University College Dublin, Belfield, Dublin 4, Ireland
推荐引用方式 GB/T 7714	Fu M.,Kelly J.A.,Clinch J.P.. Prediction of PM2.5 daily concentrations for grid points throughout a vast area using remote sensing data and an improved dynamic spatial panel model[J],2020,237.
APA	Fu M.,Kelly J.A.,&Clinch J.P..(2020).Prediction of PM2.5 daily concentrations for grid points throughout a vast area using remote sensing data and an improved dynamic spatial panel model.Atmospheric Environment,237.
MLA	Fu M.,et al."Prediction of PM2.5 daily concentrations for grid points throughout a vast area using remote sensing data and an improved dynamic spatial panel model".Atmospheric Environment 237(2020).