The overall classification accuracy of the prescription maps was of 61 %, as revealed by the confusion matrix (Table 3). In particular, all the areas without weeds were correctly identified by the UAV image classification procedure described in the Methods section on Prescription maps and herbicide treatments. On the other hand, only 57 % of the areas to be sprayed, i.e. where weeds occurred, were correctly identified (Table 3). Therefore, spraying was not carried out on 43 % of the areas actually affected by weeds; however in these areas the mean weed ground cover was rather low, i.e. about 10 %. The overall classification accuracy was higher in the 2015 season (69 %) as compared to the 2014 (53 %), probably because of the better spectral resolution of the camera used in 2015, despite a slightly lower spatial resolution. The differences between growing seasons were particularly evident for the producer’s accuracy of the weeding area (Table 3).