Water hyacinth, locally named as â€™Enbochâ€™, is an invasive aquatic weed posing arngreat threat to the worldwide aquatic ecosystem. Its existence has been reported torngreatly diminish water surfacesâ€™ ecological value causing extensive nutrient reduction.rnAn intuitive, but much feasible and inexpensive solution relies on the early detection ofrnits presence followed by an action. This paper focuses on the design of a controller for arnquadrotor able to perform area surveillance specifically suited for the detection of thernhyacinth plant. The control design is done by taking the multivariate and non-linearrnnature of the problem into full consideration. The developed model reference adaptiverncontroller (MRAC) comprising of both a standalone baseline controller and an adaptivernaugmentation is found to be able to stabilize the system in nominal scenarios and alsornrestores nominal design performance in the presence of disturbances and parametricrnuncertainties. For the task of water hyacinth detection, the technique of transferrnlearning have been applied using the state-of-the-art VGG-16 model to perform featurernextraction for a CNN architecture. The problem has been formulated as a multi-classrnclassification problem considering three other aquatic plants identified as most probablernon the habitats of water hyacinth. The trained model obtained an accuracy level ofrn93.34% through the training phase, 94.25% on a validation set, and 93% on a testing set.