Estimating the daily PM2.5 concentration in the Beijing-Tianjin-Hebei region using a random forest model with a 0.01° × 0.01° spatial resolution

Chen Zhao; Qing Wang; Jie Ban; Zhaorong Liu; Yayi Zhang; Runmei Ma; Shenshen Li; Tiantian Li

doi:10.1016/j.envint.2019.105297

Estimating the daily PM_2.5 concentration in the Beijing-Tianjin-Hebei region using a random forest model with a 0.01° × 0.01° spatial resolution

Environ Int. 2020 Jan:134:105297. doi: 10.1016/j.envint.2019.105297. Epub 2019 Nov 27.

Authors

Chen Zhao¹, Qing Wang², Jie Ban², Zhaorong Liu³, Yayi Zhang², Runmei Ma², Shenshen Li⁴, Tiantian Li⁵

Affiliations

¹ National Institute of Environmental Health, Chinese Center for Disease Control and Prevention, Beijing 100021, China; College of Environmental Sciences and Engineering, Peking University, Beijing 100871, China.
² National Institute of Environmental Health, Chinese Center for Disease Control and Prevention, Beijing 100021, China.
³ College of Environmental Sciences and Engineering, Peking University, Beijing 100871, China. Electronic address: zrliu@pku.edu.cn.
⁴ State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China.
⁵ National Institute of Environmental Health, Chinese Center for Disease Control and Prevention, Beijing 100021, China. Electronic address: litiantian@nieh.chinacdc.cn.

PMID: 31785527
DOI: 10.1016/j.envint.2019.105297

Abstract

High spatiotemporal resolution fine particulate matter (PM_2.5) simulations can provide important exposure data for the assessment of long-term and short-term health effects. Satellite-based aerosol optical depth (AOD) data, meteorological data, and topographic data have become key variables for PM_2.5 estimation. In this study, a random forest model was developed and used to estimate the highest resolution (0.01° × 0.01°) daily PM_2.5 concentrations in the Beijing-Tianjin-Hebei region. Our model had a suitable performance (cv-R² = 0.83 and test-R² = 0.86). The regional test-R² value in southern Beijing-Tianjin-Hebei was higher than that in northern Beijing-Tianjin-Hebei. The model performance was excellent at medium to high PM_2.5 concentrations. Our study considered meteorological lag effects and found that the boundary layer height of the one-day lag had the most important contribution to the model. AOD and elevation factors were also important factors in the modeling process. High spatiotemporal resolution PM_2.5 concentrations in 2010-2016 were estimated using a random forest model, which was based on PM_2.5 measurements from 2013 to 2016.

Keywords: High spatiotemporal resolution; Human exposure; Machine learning; PM(2.5) estimation.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Air Pollutants / analysis*
Air Pollution / analysis*
Beijing
Environmental Monitoring*
Particulate Matter / analysis*
Spatio-Temporal Analysis

Substances

Air Pollutants
Particulate Matter