Meteorological parameters and gaseous pollutant concentrations as predictors of daily continuous PM2.5 concentrations using deep neural network in Beijing–Tianjin–Hebei, China

Abstract The deep learning model can simulate the complex nonlinear relationship between PM2.5 and aerosol optical depth (AOD), and has great application potentiality in PM2.5 inversion. However, the underestimation of high PM2.5 concentrations problem is still exist in heavily polluted Beijing–Tianjin–Hebei (JingJinJi) region due to AOD cannot adequately represent the correlation between high PM2.5 concentrations and independent variables and neglected the effects of missing AOD. Thus, the long- and short-term PM2.5 exposure risk estimate was reduced. This work introduces gaseous pollutant data (NO2, SO2, CO, and O3) related to primary emission and secondary transformation of pollutants as predictors into a deep neural network model to improve the underestimation of high PM2.5 concentrations based on AOD and meteorological factors. We predicted the PM2.5 concentration in the missing AOD areas, generated a daily continuous PM2.5 spatial distribution, and reduced estimated bias due to AOD deficiency. Grid-based 10-fold cross-validation (CV) was used to test the model performance. Results show that daily PM2.5 concentration CV R2 is 0.87 and the root-mean-square prediction error (RMSE) is 27.11 μg/m3. The CV R2 and RMSE are higher by 0.12 and lower by 9.72 μg/m3 than the model without gaseous pollutants (GASS) as predictors. In including the missing AOD, the average concentration of PM2.5 CV R2 is 0.86 and the RMSE is 16.95 μg/m3 in heavy polluted winter; the CV R2 and RMSE are higher by 0.07 and lower by 3.95 μg/m3, respectively, than when the missing AOD was excluded. Prediction results of PM2.5 spatial distribution show that the model has high prediction accuracy and provides a complete and highly accurate spatiotemporal distribution characteristics for long- and short-term PM2.5 exposure studies, and reduces exposure misclassification of PM2.5 in heavily polluted areas.

[1]  James Martens,et al.  Deep learning via Hessian-free optimization , 2010, ICML.

[2]  T. Eck,et al.  Global evaluation of the Collection 5 MODIS dark-target aerosol products over land , 2010 .

[3]  Yang Liu,et al.  Estimating Regional Spatial and Temporal Variability of PM2.5 Concentrations Using Satellite Data, Meteorology, and Land Use Information , 2009, Environmental health perspectives.

[4]  Liangfu Chen,et al.  Satellite observation of regional haze pollution over the North China Plain , 2012 .

[5]  Yang Liu,et al.  Estimating ground-level PM2.5 in China using satellite remote sensing. , 2014, Environmental science & technology.

[6]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[7]  Anthony W. Strawa,et al.  Enhancing the Applicability of Satellite Remote Sensing for PM2.5 Estimation Using MODIS Deep Blue AOD and Land Use Regression in California, United States. , 2016, Environmental science & technology.

[8]  B. Coull,et al.  Use of satellite-based aerosol optical depth and spatial clustering to predict ambient PM2.5 concentrations. , 2012, Environmental research.

[9]  Liangfu Chen,et al.  Estimating Ground-Level PM2.5 Using Fine-Resolution Satellite Data in the Megacity of Beijing, China , 2015 .

[10]  J. Halonen,et al.  Urban air pollution, and asthma and COPD hospital emergency room visits , 2008, Thorax.

[11]  Yu Zhan,et al.  Spatiotemporal prediction of continuous daily PM2.5 concentrations across China using a spatially explicit machine learning algorithm , 2017 .

[12]  J. H. Belle,et al.  Estimating PM2.5 Concentrations in the Conterminous United States Using the Random Forest Approach. , 2017, Environmental science & technology.

[13]  Yuesi Wang,et al.  Mechanism for the formation of the January 2013 heavy haze pollution episode over central and eastern China , 2013, Science China Earth Sciences.

[14]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[15]  R. Koelemeijer,et al.  Comparison of spatial and temporal variations of aerosol optical thickness and particulate matter over Europe , 2006 .

[16]  J. Schwartz,et al.  Acute and Chronic Effects of Particles on Hospital Admissions in New-England , 2012, PloS one.

[17]  Antonella Zanobetti,et al.  Fine particulate air pollution and its components in association with cause-specific emergency admissions , 2009, Environmental health : a global access science source.

[18]  D. Jacob,et al.  Estimating ground-level PM2.5 in the eastern United States using satellite remote sensing. , 2005, Environmental science & technology.

[19]  J H Seinfeld,et al.  Urban Air Pollution: State of the Science , 1989, Science.

[20]  J. Schwartz,et al.  Assessing temporally and spatially resolved PM2.5 exposures for epidemiological studies using satellite aerosol optical depth measurements , 2011 .

[21]  A. Strawa,et al.  Improving retrievals of regional fine particulate matter concentrations from Moderate Resolution Imaging Spectroradiometer (MODIS) and Ozone Monitoring Instrument (OMI) multisatellite observations , 2013, Journal of the Air & Waste Management Association.

[22]  J. Xin,et al.  Mechanism for the formation of the January 2013 heavy haze pollution episode over central and eastern China , 2014 .

[23]  G. Leeuw,et al.  Exploring the relation between aerosol optical depth and PM 2.5 at Cabauw, the Netherlands , 2008 .

[24]  Ying Zhang,et al.  Satellite-based estimation of regional particulate matter (PM) in Beijing using vertical-and-RH correcting method , 2010 .

[25]  David John Lary,et al.  Estimating the global abundance of ground level presence of particulate matter (PM2.5). , 2014, Geospatial health.

[26]  W. You,et al.  Estimating PM2.5 in Xi'an, China using aerosol optical depth: a comparison between the MODIS and MISR retrieval models. , 2015, The Science of the total environment.

[27]  Yuqi Bai,et al.  Daily Estimation of Ground-Level PM2.5 Concentrations over Beijing Using 3 km Resolution MODIS AOD. , 2015, Environmental science & technology.

[28]  Navin Kumar Manaswi,et al.  Deep Learning with Applications Using Python , 2018, Apress.

[29]  Yi Li,et al.  National-Scale Estimates of Ground-Level PM2.5 Concentration in China Using Geographically Weighted Regression Based on 3 km Resolution MODIS AOD , 2016, Remote. Sens..

[30]  Bernardete Ribeiro,et al.  Deep Neural Network Models , 2018 .

[31]  Stefan Harmeling,et al.  Image denoising with multi-layer perceptrons, part 1: comparison with existing algorithms and with bounds , 2012, ArXiv.

[32]  Liang-pei Zhang,et al.  Point-surface fusion of station measurements and satellite observations for mapping PM 2.5 distribution in China: Methods and assessment , 2016, 1607.02976.

[33]  William L. Crosson,et al.  Estimating Ground-Level PM(sub 2.5) Concentrations in the Southeastern United States Using MAIAC AOD Retrievals and a Two-Stage Model , 2014 .

[34]  P. Gupta,et al.  Particulate matter air quality assessment using integrated surface, satellite, and meteorological products: Multiple regression approach , 2009 .

[35]  Louise Marston,et al.  Outdoor air pollution and respiratory health in patients with COPD , 2011, Thorax.

[36]  Yang Liu,et al.  Calibrating MODIS aerosol optical depth for predicting daily PM2.5 concentrations via statistical downscaling , 2014, Journal of Exposure Science and Environmental Epidemiology.

[37]  P. Gupta,et al.  Particulate Matter Air Quality Assessment using Integrated Surface, Satellite, and Meteorological Products , 2009 .

[38]  R. Burnett,et al.  Cardiovascular Mortality and Long-Term Exposure to Particulate Air Pollution: Epidemiological Evidence of General Pathophysiological Pathways of Disease , 2003, Circulation.

[39]  Armistead G Russell,et al.  Improving the Accuracy of Daily PM2.5 Distributions Derived from the Fusion of Ground-Level Measurements with Aerosol Optical Depth Observations, a Case Study in North China. , 2016, Environmental science & technology.

[40]  G. Pfister,et al.  Spatiotemporal prediction of fine particulate matter during the 2008 northern California wildfires using machine learning. , 2015, Environmental science & technology.

[41]  R. Webster,et al.  Kriging: a method of interpolation for geographical information systems , 1990, Int. J. Geogr. Inf. Sci..

[42]  Yang Liu,et al.  Using aerosol optical thickness to predict ground-level PM2.5 concentrations in the St. Louis area: A comparison between MISR and MODIS , 2007 .

[43]  Leo Breiman,et al.  Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author) , 2001 .

[44]  N. Lu,et al.  Spatiotemporal distribution and short-term trends of particulate matter concentration over China, 2006–2010 , 2014, Environmental Science and Pollution Research.

[45]  J. Schwartz,et al.  A novel calibration approach of MODIS AOD data to predict PM2.5 concentrations , 2011 .

[46]  Jiahua Zhang,et al.  Synergy of satellite and ground based observations in estimation of particulate matter in eastern China. , 2012, The Science of the total environment.

[47]  Jingfeng Huang,et al.  A satellite-based geographically weighted regression model for regional PM2.5 estimation over the Pearl River Delta region in China , 2014 .

[48]  Jonathan D. W. Kahl,et al.  Improved estimation of PM2.5 using Lagrangian satellite-measured aerosol optical depth , 2014 .

[49]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.

[50]  Alexei Lyapustin,et al.  A critical assessment of high-resolution aerosol optical depth retrievals for fine particulate matter predictions , 2013 .

[51]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[52]  Basil W. Coutant,et al.  Qualitative and quantitative evaluation of MODIS satellite sensor data for regional and urban scale air quality , 2004 .

[53]  Jun Wang,et al.  Satellite remote sensing of particulate matter and air quality assessment over global cities , 2006 .

[54]  Yang Liu,et al.  Estimating ground-level PM 2.5 concentrations over three megalopolises in China using satellite-derived aerosol optical depth measurements , 2016 .

[55]  A. Faustini,et al.  Impact of Fine and Ultrafine Particles on Emergency Hospital Admissions for Cardiac and Respiratory Diseases , 2010, Epidemiology.

[56]  Michal Krzyzanowski,et al.  Satellite-based estimates of ground-level fine particulate matter during extreme events: A case study of the Moscow fires in 2010 , 2011 .

[57]  Hong-Lei Yang,et al.  Estimating PM2.5 Concentrations in Xi'an City Using a Generalized Additive Model with Multi-Source Monitoring Data , 2015, PloS one.

[58]  F. Dominici,et al.  Fine particulate air pollution and hospital admission for cardiovascular and respiratory diseases. , 2006, JAMA.

[59]  Yang Liu,et al.  Spatiotemporal associations between GOES aerosol optical depth retrievals and ground-level PM2.5. , 2008, Environmental science & technology.

[60]  W. You,et al.  Estimating national-scale ground-level PM25 concentration in China using geographically weighted regression based on MODIS and MISR AOD , 2016, Environmental Science and Pollution Research.

[61]  R. Muller,et al.  Air Pollution in China: Mapping of Concentrations and Sources , 2015, PloS one.

[62]  Jun Wang,et al.  Intercomparison between satellite‐derived aerosol optical thickness and PM2.5 mass: Implications for air quality studies , 2003 .

[63]  M. Sköld,et al.  Regionally-varying combustion sources of the January 2013 severe haze events over eastern China. , 2015, Environmental science & technology.

[64]  Jie Tian,et al.  A semi-empirical model for predicting hourly ground-level fine particulate matter (PM2.5) concentration in southern Ontario from satellite remote sensing and ground-based meteorological measurements , 2010 .

[65]  Liangpei Zhang,et al.  Estimating Ground‐Level PM2.5 by Fusing Satellite and Station Observations: A Geo‐Intelligent Deep Learning Approach , 2017, 1707.03558.

[66]  M. Brauer,et al.  Risk of Nonaccidental and Cardiovascular Mortality in Relation to Long-term Exposure to Low Concentrations of Fine Particulate Matter: A Canadian National-Level Cohort Study , 2012, Environmental health perspectives.

[67]  M. Molina,et al.  Elucidating severe urban haze formation in China , 2014, Proceedings of the National Academy of Sciences.