摘要
This research examines uncertainty in MODerate resolution Imaging Spectroradiometer(MODIS)observations,and demonstrates the direct influence of geometric distortions resulting from the standard practice of geolocating swath observations.MODIS observations vary dependent on the ground sample distance,which varies dependent on the view zenith angle that changes with every orbit.MODIS Level 2G(L2G)land products are generated by applying a geolocation algorithm that resamples the variable observation geometries to a consistent grid of fixed pixel size and location,a process which itself introduces variability associated with the changing observational footprint.For this study,broadband albedo was simulated for five validation sites,representing five distinct land cover types,exhibiting quantifiable variability,with additional seasonal variability exhibited in some sites.All site simulations exhibit compounded uncertainty attributable to the geometric distortion sufficient to influence climate models(i.e.ranges from 0.01 to 0.045 albedo).These results indicate there is a minimum level of uncertainty associated with the variable geometry that should be factored into L2Gbased products,particularly for nominal 250 m band data.Aggregating the data to coarser resolutions and smoothing the data through average resampling can mitigate the uncertainty.
