Coastal Dune Invaders: Integrative Mapping of Carpobrotus sp. pl. (Aizoaceae) Using UAVs

Coastal dune ecosystems are highly threatened, and one of the strongest pressures is invasive alien plants (IAPs). Mitigating negative effects IAPs requires development optimal identification mapping protocols. Remote sensing offers innovative tools that have proven to be very valuable for studying IAPs. In particular, unmanned aerial vehicles (UAVs) can promising, especially in study herbaceous species, yet research UAV application still limited. this study, we used images implement an image segmentation approach followed by machine learning classification a clonal invader (Carpobrotus sp. pl.), calibrating total 27 models. Our showed that: (a) results offered simultaneous RGB multispectral data improve prediction Carpobrotus; (b) best were obtained whole plant or its vegetative parts, while flowers was worse; (c) training area corresponding 20% adequate model building. Overall, our highlighted great potential using UAVs Carpobrotus mapping, despite some limitations imposed particular biology ecology these taxa.