Retrieval of ice cloud properties using an optimal estimation algorithm and MODIS infrared observations: 2. Retrieval evaluation

Abstract

An infrared-based optimal estimation (OE-IR) algorithm for retrieving ice cloud properties is evaluated. Specifically, the implementation of the algorithm with MODerate resolution Imaging Spectroradiometer (MODIS) observations is assessed in comparison with the operational retrieval products from MODIS on the Aqua satellite (MYD06), Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP), and the Imaging Infrared Radiometer (IIR); the latter two instruments fly on the Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) satellite in the Afternoon Constellation (A-Train) with Aqua. The results show that OE-IR cloud optical thickness (τ) and effective radius (reff) retrievals perform best for ice clouds having 0.5 <50 µm. For global ice clouds, the averaged retrieval uncertainties of τ and reff are 19% and 33%, respectively. For optically thick ice clouds with τ larger than 10, however, the t and reff retrieval uncertainties can exceed 30% and 50%, respectively. For ice cloud top height (h), the averaged global uncertainty is 0.48 km. Relatively large h uncertainty (e.g., >1 km) occurs for τ <0.5. Analysis of 1month of the OE-IR retrievals shows large τ and reff uncertainties in storm track regions and the southern oceans where convective clouds are frequently observed, as well as in high-latitude regions where temperature differences between the surface and cloud top are more ambiguous. Generally, comparisons between the OE-IR and the operational products show consistent t and h retrievals. However, obvious differences between the OE-IR and the MODIS Collection 6 reff are found.