Modeling Air Pollution in Beijing with Meteorological Data

• Activity Number: 190 - Contributed Poster Presentations: Section on Statistics and the Environment
• Type: Contributed
• Date/Time: Monday, July 29, 2019 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics and the Environment
• Author(s): Ying Zhang* and Song Xi Chen and Le Bao
• Companies: Pennsylvania State University and Peking University and Pennsylvania State University
• Keywords: Air Pollution; Spatio-temporal Model; Kriging

Abstract

The air pollution problem has been a serious environmental concern in China. A commonly used measurement of air pollution is the concentration of PM2.5. PM2.5 stands for the particulate matter with a size generally less than 2.5 micrometers, and they can diminish lung function, trigger heart disease or even worse for human health. The hourly PM2.5 and other meteorological data are collected from 36 monitoring locations in Beijing, China, between 2013 and 2017. We use spatio-temporal models to estimate PM2.5 concentration over time and space, understand how it changes with meteorological variables, and extrapolate the PM2.5 at locations without ground monitoring data.