Primary information of great importance to various grand challenges such as sustainable agricultural intensification, food insecurity, and climate change impacts, can be obtained indirectly from land cover monitoring. However, in arid-to-semiarid regions, such as Iraq, accurate discrimination of different vegetation types is challenging due to their similar spectral responses. Moreover, Iraq has been subjected to major disturbances, both natural and anthropogenic which have affected the distribution of land cover types through space and time. Reliable information about croplands and natural vegetation in such regions is generally scarce. This research aimed to develop a phenology-based classification approach using support vector machines for the assessment of space-time distribution of the dominant vegetation land cover (VLC) types in Iraq, particularly croplands, from 2002 to 2012. Thirteen successive years of 8-day composites of MODISNDVI data at a spatial resolution of 250 m were employed to estimate 11 phenological parameters. The classification methodology was assessed using reference samples taken from fine spatial resolution imagery and independent testing data obtained through fieldwork. Overall accuracies were generally >85 %, with relatively high Kappa coefficients (>0.86) across the classified land cover types. The predicted cropland class area and the Global MODIS land cover product were compared with ground statistical data at the governorate level, revealing a significantly larger coefficient of determination for the present phenology-based approach (R2 = 0.70 against R2 = 0.33 for MODIS, p<; 0.05). The resulting maps delimit for the first time, at a fine spatial resolution, the spatial and interannual variability in the dominant VLC classes across Iraq.