Can MODIS cloud fraction fully represent the diurnal and seasonal variations at DOE ARM SGP and Manus sites?

Though cloud fraction (CF) from Moderate Resolution Imaging Spectroradiometer (MODIS) has been widely used, it remains unclear whether it can fully represent the diurnal variations. This study evaluates the time representation (i.e., satellite passes' mean value per day to represent daily average value) error in MODIS CF by using daytime-only total sky cover and continuous day-and-night radar/lidar CF (Active Remote Sensing of Clouds product, ARSCL) from 2000 to 2010 for two Atmospheric Radiation Measurement (ARM) program climate regime sites of Southern Great Plains (SGP) and Manus. By comparing the daily averaged CFs from ARSCL between using all hourly and using the MODIS-passing-time observations, it shows a correlation coefficient of 0.93 (0.88) and root mean square deviation (RMSD) of 12.68% (13.27%) over SGP (Manus) site for daily averaged CFs. Differently, it shows a better correlation coefficient of 0.97 (0.97) and smaller RMSD of 2.98% (3.97%) over SGP (Manus) site for monthly averaged CFs. These suggest that considerable errors could be introduced while using the MODIS CF observed at several fixed time points a day to represent average CF at different time scales. Monthly time representation errors have also been evaluated for daytime only and nighttime only, which show even larger values. A further analysis shows that uncertainties caused by the time representation account for about 23% (21%) of the total differences between surface and MODIS CFs over SGP (Manus) site at monthly time scale.