气候变化领域集成服务门户(CCPortal): Spatiotemporal ozone pollution LUR models: Suitable statistical algorithms and time scales for a megacity scale

CCPortal

DOI	10.1016/j.atmosenv.2020.117671
	Spatiotemporal ozone pollution LUR models: Suitable statistical algorithms and time scales for a megacity scale
	Wang J.; Cohan D.S.; Xu H.
发表日期	2020
ISSN	1352-2310
卷号	237
英文摘要	Ambient air ozone (O3), a secondary photochemical pollutant, is seriously harmful to human health. Accurate estimation of O3 exposure requires the ability to monitor O3 surface concentration with a high spatiotemporal resolution. Several spatiotemporal land use regression (LUR) models have integrated meteorological factors based on different statistical algorithms to support such epidemiological studies. From among such various existing statistical algorithms, we aim to identify a high-efficiency modeling method, as well as the most suitable lengths of the modeling period (time scale). Three types of typical spatiotemporal LUR models based on parametric, semi-parametric, and non-parametric statistic methods, respectively, are considered to predict daily ground-level O3 in the megacity of Tianjin, China. Based on monthly, seasonal (cold and warm), and annual time scales, these models include: a series of monthly hybrid LUR (Two-stage) models consisting of two sub-models based on the multiple linear regression (MLR) algorithm, general additive mixed models (GAMMs), and land use random forest (LURF) models. Leave-one-out cross-validation was performed to evaluate the temporal and spatial predictive accuracy of each model using the adjusted coefficient of determination (adjR2CV) and root mean square error (RMSECV). In the GAMMs and LURF models, models using a shorter time scale (monthly models) outperformed those using a longer one. In monthly models, the GAMMs performed the best, with the highest average adjR2CV (0.747) and the lowest average RMSECV (15.721 μg/m3), followed by the LURF models (average adjR2CV = 0.695, average RMSECV = 16.405), and the Two-stage models (average adjR2CV = 0.466, average RMSECV = 23.934). Thus, the modeling format consisting of a shorter time scale and the GAMM algorithm performs relatively well in predicting daily O3 pollution on a megacity scale. These findings can be used to select appropriate modeling methods for epidemiological research of O3 pollution. © 2020 Elsevier Ltd
关键词	Epidemiological study General additive mixed model Land use regression Ozone Random forest Spatiotemporal
语种	英语
scopus关键词	Decision trees; Land use; Linear regression; Mean square error; Ozone; Time measurement; Coefficient of determination; Epidemiological studies; Leave-one-out cross validations; Meteorological factors; Multiple linear regressions; Non-parametric statistics; Root mean square errors; Spatio-temporal resolution; Air pollution; ozone; algorithm; atmospheric modeling; epidemiology; megacity; ozone; seasonal variation; spatiotemporal analysis; air pollution; algorithm; ambient air; Article; controlled study; health hazard; land use; leave one out cross validation; machine learning; mathematical model; multiple linear regression analysis; priority journal; random forest; seasonal variation; spatiotemporal analysis; surface property; China; Tianjin
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/249065
作者单位	College of Environmental Science and Engineering, Nankai University, Tianjin, 300350, China; Department of Civil and Environmental Engineering, Rice University, Houston, TX 77005, United States
推荐引用方式 GB/T 7714	Wang J.,Cohan D.S.,Xu H.. Spatiotemporal ozone pollution LUR models: Suitable statistical algorithms and time scales for a megacity scale[J],2020,237.
APA	Wang J.,Cohan D.S.,&Xu H..(2020).Spatiotemporal ozone pollution LUR models: Suitable statistical algorithms and time scales for a megacity scale.ATMOSPHERIC ENVIRONMENT,237.
MLA	Wang J.,et al."Spatiotemporal ozone pollution LUR models: Suitable statistical algorithms and time scales for a megacity scale".ATMOSPHERIC ENVIRONMENT 237(2020).