A Framework to Predict High-Resolution Spatiotemporal PM(2.5)Distributions Using a Deep-Learning Model: A Case Study of Shijiazhuang, China

doi:10.3390/rs12172825

	A Framework to Predict High-Resolution Spatiotemporal PM(2.5)Distributions Using a Deep-Learning Model: A Case Study of Shijiazhuang, China
	Zhang, Guangyuan 1; Lu, Haiyue 2; Dong, Jin 3; Poslad, Stefan 1; Li, Runkui 3,4; Zhang, Xiaoshuai 1; Rui, Xiaoping 2
刊名	REMOTE SENSING
	2020-09-01
卷号	12 期号:17 页码:33
关键词	PM2.5 AOD XGBoost prediction deep learning ConvLSTM SARIMA
DOI	10.3390/rs12172825
通讯作者	Rui, Xiaoping(ruixp@hhu.edu.cn)
英文摘要	Air-borne particulate matter, PM2.5(PM having a diameter of less than 2.5 micrometers), has aroused widespread concern and is a core indicator of severe air pollution in many cities globally. In our study, we present a validated framework to predict the daily PM(2.5)distributions, exemplified by a use case of Shijiazhuang City, China, based on daily aerosol optical depth (AOD) datasets. The framework involves obtaining the high-resolution spatiotemporal AOD distributions, estimation of the spatial distributions of PM(2.5)and the prediction of these based on a convolutional long short-term memory (ConvLSTM) model. In the estimation part, the eXtreme gradient boosting (XGBoost) model has been determined as the estimation model with the lowest root mean square error (RMSE) of 32.86 mu g/m(3)and the highest coefficient of determination regression score function (R-2) of 0.71, compared to other common models used as a baseline for comparison (linear, ridge, least absolute shrinkage and selection operator (LASSO) and cubist). For the prediction part, after validation and comparison with a seasonal autoregressive integrated moving average (SARIMA), which is a traditional time-series prediction model, in both time and space, the ConvLSTM gives a more accurate performance for the prediction, with a total average prediction RMSE of 14.94 mu g/m(3)compared to SARIMA's 17.41 mu g/m(3). Furthermore, ConvLSTM is more stable and with less fluctuations for the prediction of PM(2.5)in time, and it can also eliminate better the spatial predicted errors compared to SARIMA.
资助项目	National Key Research and Development Program of China[2017YFB0503605] ; National Natural Science Foundation of China[41771478] ; National Natural Science Foundation of China[41771435] ; Fundamental Research Funds for the Central Universities[2019B02514] ; Beijing Natural Science Foundation[8172046] ; China Scholarship Council (CSC) ; Queen Mary University of London
WOS关键词	AEROSOL OPTICAL DEPTH ; PRINCIPAL COMPONENT ANALYSIS ; PARTICULATE MATTER ; PM2.5 ; SATELLITE ; EXPOSURE ; PM10 ; ASSOCIATIONS ; REGRESSION ; POLLUTION
WOS研究方向	Remote Sensing
语种	英语
出版者	MDPI
WOS记录号	WOS:000569943700001
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Fundamental Research Funds for the Central Universities ; Beijing Natural Science Foundation ; China Scholarship Council (CSC) ; Queen Mary University of London
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/156875]
专题	中国科学院地理科学与资源研究所
通讯作者	Rui, Xiaoping
作者单位	1.Queen Mary Univ London, Sch Elect Engn & Comp Sci, IoT Lab, London E1 4NS, England 2.Hohai Univ, Sch Earth Sci & Engn, Nanjing 211000, Peoples R China 3.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Guangyuan,Lu, Haiyue,Dong, Jin,et al. A Framework to Predict High-Resolution Spatiotemporal PM(2.5)Distributions Using a Deep-Learning Model: A Case Study of Shijiazhuang, China[J]. REMOTE SENSING,2020,12(17):33.
APA	Zhang, Guangyuan.,Lu, Haiyue.,Dong, Jin.,Poslad, Stefan.,Li, Runkui.,...&Rui, Xiaoping.(2020).A Framework to Predict High-Resolution Spatiotemporal PM(2.5)Distributions Using a Deep-Learning Model: A Case Study of Shijiazhuang, China.REMOTE SENSING,12(17),33.
MLA	Zhang, Guangyuan,et al."A Framework to Predict High-Resolution Spatiotemporal PM(2.5)Distributions Using a Deep-Learning Model: A Case Study of Shijiazhuang, China".REMOTE SENSING 12.17(2020):33.