气候变化领域集成服务门户(CCPortal): A comparison of statistical and machine learning methods for creating national daily maps of ambient PM2.5 concentration

CCPortal

DOI	10.1016/j.atmosenv.2019.117130
	A comparison of statistical and machine learning methods for creating national daily maps of ambient PM2.5 concentration
	Berrocal V.J.; Guan Y.; Muyskens A.; Wang H.; Reich B.J.; Mulholland J.A.; Chang H.H.
发表日期	2020
ISSN	13522310
卷号	222
英文摘要	A typical challenge in air pollution epidemiology is to perform detailed exposure assessment for individuals for which health data are available. To address this problem, in the last few years, substantial research efforts have been placed in developing statistical methods or machine learning techniques to generate estimates of air pollution at fine spatial and temporal scales (daily, usually) with complete coverage. However, it is not clear how much the predicted exposures yielded by the various methods differ, and which method generates more reliable estimates. In this paper, we aim to address this gap by evaluating a variety of exposure modeling approaches, comparing their predictive performance. Using PM2.5 in year 2011 over the continental U.S. as a case study, we generate national maps of ambient PM2.5 concentration using: (i) ordinary least squares and inverse distance weighting; (ii) kriging; (iii) statistical downscaling models, that is, spatial statistical models that use the information contained in air quality model outputs; (iv) land use regression, that is, linear regression modeling approaches that leverage the information in Geographical Information System (GIS) covariates; and (v) machine learning methods, such as neural networks, random forests and support vector regression. We examine the various methods’ predictive performance via cross-validation using Root Mean Squared Error, Mean Absolute Deviation, Pearson correlation, and Mean Spatial Pearson Correlation. Additionally, we evaluated whether factors such as, season, urbanicity, and levels of PM2.5 concentration (low, medium or high) affected the performance of the different methods. Overall, statistical methods that explicitly modeled the spatial correlation, e.g. universal kriging and the downscaler model, outperform all the other exposure assessment approaches regardless of season, urbanicity and PM2.5 concentration level. We posit that the better predictive performance of spatial statistical models over machine learning methods is due to the fact that they explicitly account for spatial dependence, thus borrowing information from neighboring observations. In light of our findings, we suggest that future exposure assessment methods for regional PM2.5 incorporate information from neighboring sites when deriving predictions at unsampled locations or attempt to account for spatial dependence. © 2019 Elsevier Ltd
学科领域	Air quality; Correlation methods; Decision trees; Information use; Interpolation; Land use; Learning algorithms; Least squares approximations; Machine learning; Mean square error; Regression analysis; Statistics; Inverse distance weighting; Linear regression models; Machine learning methods; Machine learning techniques; Mean absolute deviations; Root mean squared errors; Spatial and temporal scale; Support vector regression (SVR); Inverse problems; air quality; ambient air; atmospheric pollution; comparative study; concentration (composition); epidemiology; GIS; machine learning; methodology; particulate matter; pollution exposure; statistical analysis; air pollution; air quality; article; artificial neural network; geographic information system; gravity model; kriging; land use; least square analysis; linear regression analysis; prediction; random forest; season; support vector machine
语种	英语
scopus关键词	Air quality; Correlation methods; Decision trees; Information use; Interpolation; Land use; Learning algorithms; Least squares approximations; Machine learning; Mean square error; Regression analysis; Statistics; Inverse distance weighting; Linear regression models; Machine learning methods; Machine learning techniques; Mean absolute deviations; Root mean squared errors; Spatial and temporal scale; Support vector regression (SVR); Inverse problems; air quality; ambient air; atmospheric pollution; comparative study; concentration (composition); epidemiology; GIS; machine learning; methodology; particulate matter; pollution exposure; statistical analysis; air pollution; air quality; article; artificial neural network; geographic information system; gravity model; kriging; land use; least square analysis; linear regression analysis; prediction; random forest; season; support vector machine
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/120788
作者单位	University of California - Irvine, Department of Statistics, Irvine, CA, United States; University of Nebraska, Department of Statistics, Lincoln, NE, United States; Lawrence Livermore National Laboratory, Livermore, CA, United States; SAS, CaryNC, United States; Georgia Institute of Technology, Atlanta, United States; Emory University, Department of Biostatistics and Bioinformatics, Atlanta, United States
推荐引用方式 GB/T 7714	Berrocal V.J.,Guan Y.,Muyskens A.,et al. A comparison of statistical and machine learning methods for creating national daily maps of ambient PM2.5 concentration[J],2020,222.
APA	Berrocal V.J..,Guan Y..,Muyskens A..,Wang H..,Reich B.J..,...&Chang H.H..(2020).A comparison of statistical and machine learning methods for creating national daily maps of ambient PM2.5 concentration.Atmospheric Environment,222.
MLA	Berrocal V.J.,et al."A comparison of statistical and machine learning methods for creating national daily maps of ambient PM2.5 concentration".Atmospheric Environment 222(2020).