An Ensemble Spatiotemporal Model for Predicting PM2.5 Concentrations

Although fine particulate matter with a diameter of 2.5 ) has a greater negative impact on human health than particulate matter with a diameter of 10 ), measurements of PM 2.5 have only recently been performed, and the spatial coverage of these measurements is limited. Comprehensively assessing PM 2.5 pollution levels and the cumulative health effects is difficult because PM 2.5 monitoring data for prior time periods and certain regions are not available. In this paper, we propose a promising approach for robustly predicting PM 2.5 concentrations. In our approach, a generalized additive model is first used to quantify the non-linear associations between predictors and PM 2.5 , the bagging method is used to sample the dataset and train different models to reduce the bias in prediction, and the variogram for the daily residuals of the ensemble predictions is then simulated to improve our predictions. Shandong Province, China, is the study region, and data from 96 monitoring stations were included. To train and validate the models, we used PM 2.5 measurement data from 2014 with other predictors, including PM 10 data, meteorological parameters, remote sensing data, and land-use data. The validation results revealed that the R2 value was improved and reached 0.89 when PM 10 was used as a predictor and a kriging interpolation was performed for the residuals. However, when PM 10 was not used as a predictor, our method still achieved a CV R2 value of up to 0.86. The ensemble of spatial characteristics of relevant factors explained approximately 32% of the variance and improved the PM 2.5 predictions. The spatiotemporal modeling approach to estimating PM 2.5 concentrations presented in this paper has important implications for assessing PM 2.5 exposure and its cumulative health effects

Kriging · Particulates · Spatial analysis · Statistics · Variogram · Air Quality and Health Impacts · Air Quality Monitoring and Forecasting · Environmental Science · Mathematics · Vehicle emissions and performance

• An urban big data-based air quality index prediction

  Open Access•Zhiqiang Zou, Tao Cai et al.•Environment and Planning B Urban…•2020

  Incluir item

• Global and Geographically and Temporally Weighted Regression Models for Modeling PM2.5 in Heilongjiang, China from 2015 to 2018

  Open Access•Qingbin Wei, Lianjun Zhang et al.•International Journal of…•2019

  Incluir item

• Spatiotemporal Heterogeneity and the Key Influencing Factors of PM2.5 and PM10 in Heilongjiang, China from 2014 to 2018

  Open Access•Longhui Fu, Qibang Wang et al.•International Journal of…•2022

  Incluir item

• Geostatistics for Natural Resources Evaluation

  Pierre Goovaerts•Geostatistics for natural…•1997

  Incluir item

• Ensemble Methods in Machine Learning

  Thomas G Dietterich•Multiple Classifier Systems•2000

  Incluir item

• A review of land-use regression models to assess spatial variation of outdoor air pollution

  Open Access•Gerard Hoek, Rob Beelen et al.•Atmospheric Environment (1967)•2008

  Incluir item

• The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis

  Open Access•Norden E Huang, Zheng Shen et al.•Proceedings of the Royal Society…•1998

  Incluir item

• Model Selection and Akaike's Information Criterion (AIC)

  Open Access•Hamparsum Bozdogan•Psychometrika•1987

  Incluir item

• The carcinogenicity of outdoor air pollution

  Open Access•Dana Loomis, Yann Grosse et al.•The Lancet Oncology•2013

  Incluir item

• Bagging predictors

  Open Access•Leo Breiman•Machine Learning•1996

  Incluir item

• A Caution Regarding Rules of Thumb for Variance Inflation Factors

  Open Access•Robert M O’brien•Quality & Quantity•2007

  Incluir item