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 PM25 concentrations retrieved from AOD/MODIS data based on BP neural networks presents significant change with seasons. Albeit the sensitivity to seasons of PM25 retrieval from satellite, results indicated that the algorithm of BP network could be applied in retrieving long term PM concentrations from satellite.