Use of high-resolution multispectral imagery acquired with an autonomous unmanned aerial vehicle to quantify the spread of an invasive wetlands species

Management of wetlands resources often requires assessment of changes in wetland vegetation over time. Accurate tracking of the expansion or retraction of invasive plant species is especially critical for natural resource managers who must make decisions on the deployment of effective control measures. Many available remote sensing strategies to quantify the location of invasive plant species are either too expensive to deploy on a regular basis or lack sufficient geographic or temporal resolution to be of use to resources managers. This paper presents the results of the use of a new unmanned aerial vehicle platform, called Aggie Air™, and a new classification algorithm to track the spread of an invasive grass species, Phragmites australis, in a large and important wet-land in northern Utah. The combination of high resolution multi-spectral images (in space and time) and the classification algorithm based on advances in statistical learning theory produce quantitative land cover descriptions that identify Phragmites locations with an accuracy of 95 percent. The combination of these two tools provides wetlands managers with new and potentially valuable methods to quantify the spread of Phragmites and to evaluate the efficacy of their attempts to control it.