Spatiotemporal modeling of PM2.5 concentrations at the national scale combining land use regression and Bayesian maximum entropy in China

Environ Int. 2018 Jul:116:300-307. doi: 10.1016/j.envint.2018.03.047. Epub 2018 May 3.

Abstract

Concentrations of particulate matter with aerodynamic diameter <2.5 μm (PM2.5) are relatively high in China. Estimation of PM2.5 exposure is complex because PM2.5 exhibits complex spatiotemporal patterns. To improve the validity of exposure predictions, several methods have been developed and applied worldwide. A hybrid approach combining a land use regression (LUR) model and Bayesian Maximum Entropy (BME) interpolation of the LUR space-time residuals were developed to estimate the PM2.5 concentrations on a national scale in China. This hybrid model could potentially provide more valid predictions than a commonly-used LUR model. The LUR/BME model had good performance characteristics, with R2 = 0.82 and root mean square error (RMSE) of 4.6 μg/m3. Prediction errors of the LUR/BME model were reduced by incorporating soft data accounting for data uncertainty, with the R2 increasing by 6%. The performance of LUR/BME is better than OK/BME. The LUR/BME model is the most accurate fine spatial scale PM2.5 model developed to date for China.

Keywords: Bayesian maximum entropy; China; Land use regression; PM(2.5) pollution; Spatio-temporal model.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Air Pollutants / analysis*
  • Air Pollution* / analysis
  • Air Pollution* / statistics & numerical data
  • Bayes Theorem
  • China
  • Environmental Monitoring
  • Models, Statistical*
  • Particulate Matter / analysis*
  • Spatio-Temporal Analysis

Substances

  • Air Pollutants
  • Particulate Matter