 This study developed an automated system for detecting weeds in crops using UAV images. It used random forest classification to select the most relevant features from the images and then used these features to identify the presence of weeds. The accuracy of the system was tested against manual weeding and found to be comparable. The system can also be used to create prescriptions for post-emergent weed control. This article was authored by Ana Aida Castro, Jorge Torres Sanchez, Jose M. Pena and others.