Comparison of AOD between CALIPSO and MODIS: significant differences over major dust and biomass burning regions

Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observations (CALIPSO) provide global vertical profiles of aerosol optical properties for the first time. In this study, we employed about 6 yr (2006-2011) of CALIPSO level 3 monthly mean gridded aerosol optical depth (AOD) products (daytime and nighttime) for cloud-free conditions, to compare with the Moderate Resolution Imaging Spectroradiometer (MODIS) Terra/Aqua level 3 monthly mean AOD dataset for the same time period. While the spatial distribution and seasonal variability of CALIPSO AOD is generally consistent with that of MODIS, CALIPSO is overall lower than MODIS as MODIS has higher frequency than CALIPSO for most bins of AOD. The correlation between MODIS and CALIPSO is better over ocean than over land. We focused on four regions that have large systematic differences: two over dust regions (the Sahara and Northwest China) and two over biomass burning regions (South Africa and South America). It is found that CALIPSO AOD is significantly lower than MODIS AOD over dust regions during the whole time period, with a maximum difference of 0.3 over the Saharan region and 0.25 over Northwest China. For biomass burning regions, CALIPSO AOD is significantly higher than MODIS AOD over South Africa, with a maximum difference of 0.25. Additionally CALIPSO AOD is slightly higher than MODIS AOD over South America for most of the time period, with a few exceptions in 2006, 2007, and 2010, when biomass burning is significantly stronger than during other years. We analyzed the impact of the satellite spatial and temporal sampling issue by using level 2 CALIPSO and MODIS products, and these systematic differences can still be found. The results of this study indicate that systematic differences of CALIPSO relative to MODIS are closely associated with aerosol types, which vary by location and season. Large differences over dust and biomass burning regions may suggest that assumptions made in satellite retrievals, such as the assumed lidar ratios for CALIPSO retrievals over dust and biomass burning regions or the surface reflectance information and/or the aerosol model utilized by the MODIS algorithm, are not appropriate.