Characterizing the spatial variability of broadband albedo in a semidesert environment for MODIS validation

Global data sets on land surface albedo will be one of the core products to be derived from data acquired by the Moderate Resolution Imaging Spectroradiometer (MODIS), part of NASA's Earth Observing System. Widespread acceptance of this product by the user communities is dependent, in part, on a comprehensive and rigorous programme of calibration and validation. Since the MODIS albedo product will be produced at a spatial resolution of 1 km, while measurements obtained from field instruments typically relate to areas of only a few tens of meters, this requires an understanding of the spatial variability of land surface albedo and a robust means of scaling zip from field to satellite measurements. In this article, we examine these issues for a semidesert environment (the PROVE'97 field site at Jornada, New Mexico, USA). Spatial variations in field measurements of broadband albedo are related to the functional ground cover of different scene elements (live and senescent vegetation, soil and shadow) via a simple linear mixture model. Information on the fractional ground cover of the scene elements is derived from ground-based hemispherical photography. It is shown that the albedo values predicted by the mixture model are accurate to within 2% of the corresponding measured values. This approach offers considerable potential for the validation of MODIS-derived albedo values through the use of spectral mixture modelling applied to fine spatial resolution satellite sensor images. (C) Elsevier Science Inc., 2000.