Widespread anthropogenic land-cover change over the last five centuries has influenced the global climate system through both biogeochemical and biophysical processes. Models indicate that warming from carbon emissions associated with land-cover conversion have been partially offset by cooling from elevated albedo, but considerable uncertainty remains partly because of uncertainty in model treatments of albedo. This study incorporates a new spatially and temporally explicit, land-cover specific albedo product derived from MODIS with a historical land-use dataset (Land Use Harmonization product) to provide more precise, observationally derived estimates of albedo impacts from anthropogenic land-cover change with a complete range of dataset specific uncertainty. The mean annual global albedo increase due to land-cover change during 1700–2005 was estimated as 0.00106 ± 0.00008 (mean ± standard deviation), mainly driven by snow exposure due to land-cover transitions from natural vegetation to agriculture. This translates to a top-of-atmosphere (TOA) radiative cooling of −0.15 ± 0.1 W m−2 (mean ± standard deviation). Our estimate was in the middle of the IPCC AR5 range of −0.05 to −0.25 W m−2, and incorporates variability in albedo within land-cover classes.