Analysis of AOD from MODIS-Merged DT-DB Products Over the Arabian Peninsula

The satellite-based aerosol estimation has attracted immense scientific attention in a multiplicity of applications related to global warming, climate change, and air pollution research globally. Numerous aerosols from widespread deserts across the Arabian Peninsula have a significant function in the regional climate and air quality. The aim of this study is to analyze the spatiotemporal variations of aerosols over the Arabian Peninsula for the period 2003-2017. For this, the study uses the Terra and Aqua Satellite on-board Moderate Resolution Imaging Spectroradiometer (MODIS)-based Merged Dark Target (DT) and Deep Blue (DB) collection of six aerosol products (550 nm). The study also uses the Aerosol Robotic Network (AERONET)-derived AOD to evaluate MODIS-Merged DT-DB AOD across the peninsula. A linear regression technique, root mean square error, mean absolute error, relative mean bias (RMB), and EE envelope (expected error) methods are used to calculate the uncertainty in the MODIS-merged DT-DB AOD products. The results of the spatial distribution show that Terra demonstrates the highest AOD over the southern Red Sea and the west coast of the Arabian Gulf that extends up to central Saudi Arabia. However, the Aqua displays the highest AOD mostly over the southern Red Sea. AOD is increasing annually at Kuwait University, Dhabi, and Hamim stations while decreasing at KAUST and Masdar-Institute. The Solar Village (for Aqua) shows a slightly increasing trend), Dhadnah, and Mezaira showing an almost a stable condition. Aqua has the better retrievals of AOD, which fall within EE envelope (similar to 6087%) for seven stations, whereas the Terra shows better AOD retrieval only for Dhabi (EE=similar to 81%). However, RMB reveals the correct information that the merged AOD product overestimates at all stations for both satellites, while the Aqua underestimates for the Solar Village, Kuwait University, and Dhadnah. This under- and overestimation is due to the defective surface reflectance computation and inaccurate use of aerosol model schemes in the Look-Up Table. Further qualitative research is recommended to enhance the aerosol retrieval efficiency of the DB and DT algorithms over the bright-reflecting surface.