Producing cloud-free MODIS snow cover products with conditional probability interpolation and meteorological data

Cloud cover and snow misclassifications are the two major limitations for the hydrological application of MODIS snow data. Ground-based meteorological data have the inherent potential to provide the means to reconstruct snow cover for regions in which MODIS snow maps are obstructed by clouds, and to reduce misclassified snow observations. In this study, a multistep method is developed to generate cloud-free MODIS daily snow cover products. The accuracy of the updated MODIS snow products is evaluated for a region in southwestern Germany in which winter cloud coverage and snow variability are typically high. First, we applied Aqua/Terra combination, temporal combination and spatial combination to reduce the cloud coverage and to retrieve the omitted snow. This procedure was not effective since cloud blockage occurs frequently during the snow season. A conditional probability interpolation was then employed to reclassify the remaining cloud cover on MODIS snow maps based on in situ snow depth observations. Finally, we implemented a set of meteorological filters to minimize the misclassified snow in MODIS snow products. The improved cloud-free MODIS daily snow maps showed an overall accuracy of about 92% during the snow season with significantly reduced snow overestimation errors and a slight increase in snow omission errors, compared to the overall accuracy of 87% and 94% for original MODIS Aqua and Terra data, respectively. This study suggests that the fusion of ground-based and satellite based snow observations is an effective approach for generating cloud-free remote sensing snow data. (C) 2016 Elsevier Inc. All rights reserved.