Correlation between PM concentrations and Aerosol Optical Depth in eastern China based on BP neural networks

Two years (2007–2008) of observational particulate matter (PM) data from ten ground-stations over eastern China, as well as collocated Aerosol Optical Depth (hereafter called AOD) derived from Moderate Resolution Imaging Spectroradiometer (MODIS), in conjunction with meteorological parameters, such as planetary boundary layer height (PBLH), relative humid (RH), temperature (TEMP), wind speed (WS), wind direction (WD), were applied to investigate the correlation between PM and AOD with the back propagation (BP) neural networks algorithm, notably the PM-AOD correlation change with seasons. The PM2.5 concentrations retrieved from AOD/MODIS data based on BP neural networks presents significant change with seasons. Albeit the sensitivity to seasons of PM2.5 retrieval from satellite, results indicated that the algorithm of BP network could be applied in retrieving long term PM concentrations from satellite.

[1]  Gokmen Tayfur,et al.  Forecasting Ambient Air SO2 Concentrations Using Artificial Neural Networks , 2006 .

[2]  Mukesh Khare,et al.  Artificial neural network based carbon monoxide persistence models for episodic urban air quality management , 2008, Environmental monitoring and assessment.

[3]  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 .

[4]  A. Cacciari,et al.  MODIS AEROSOL OPTICAL PROPERTIES OVER NORTH ITALY FOR ESTIMATING SURFACE-LEVEL PM2.5 , 2007 .

[5]  Pawan Kumar Gupta.  Particulate matter air quality assessment over southeast United States using satellite and ground measurements , 2008 .

[6]  L. Dawidowski,et al.  Artificial neural network for the identification of unknown air pollution sources , 1999 .

[7]  Jie Guang,et al.  Correlation between PM concentrations and aerosol optical depth in eastern China , 2009 .

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

[9]  D. Palmer-Brown,et al.  Investigating microclimatic influences on ozone injury in clover (Trifolium subterraneum) using artificial neural networks , 1996 .

[10]  Naresh Kumar,et al.  An empirical relationship between PM(2.5) and aerosol optical depth in Delhi Metropolitan. , 2007, Atmospheric environment.

[11]  M. Gardner,et al.  Neural network modelling and prediction of hourly NOx and NO2 concentrations in urban air in London , 1999 .

[12]  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 .

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

[14]  Osman N. Ucan,et al.  an artificial neural network-baSed model for Short-term predictionS of daily mean pm10 concentrationS , 2010 .

[15]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.