Testing the ability of unmanned aerial systems and machine learning to map weeds at subfield scales: a test with the weed Alopecurus myosuroides (Huds) - Lambert - - Pest Management Science - Wiley Online Library

#artificialintelligence 

The core objective of plant population ecology is to understand changes in numbers of individuals/organisms across time and space.1 Achieving this depends on methods that permit plants to be mapped and monitored at informative scales.2-4 Surveys of plant populations have been undertaken using a variety of different methods such as transect sampling, quadrat sampling and with unmanned aerial systems (UAS).5-7 Each of these methods has an inherent trade‐off between the area that can be surveyed and the intensity at which the subjects in that area can be studied.8 Transect and quadrat sampling can be used for either small area, high‐intensity studies or large area, low‐intensity studies, but typically not both.9 UAS present a unique opportunity for ecological monitoring because, potentially, they can yield data across both large spatial areas and at high survey intensity.