Using sUAV imagery to map litter of invasive annual grass in dry environmental conditions

Abstract

Invasive annual grasses pose a severe threat to drylands of the United States by increasing habitat degradation and the occurrence and severity of wildfires, while simultaneously outcompeting native species. Advances in technology and accessibility of small uncrewed aerial vehicles (sUAV) provide the opportunity for small preserve managers to map and monitor plant invasions in critical habitats for rare and endemic plant species. Many remote sensing techniques rely on the invasive plants' different phenological signals to distinguish them from native plants and habitats. However, invasive annual grasses in the western United States have high variability of interannual productivity and may not green up each year. Therefore, our objective was to use an sUAV (quadcopter drone) to map invasive annual grass regardless of phenological stage in critical Mojave Desert habitat. The study locations were White Dome, a small habitat preserve, and Beehive Dome in Washington County UT, USA. These areas are critical habitats for several endangered and threatened plant species and are covered with sensitive biological soil crusts, making on-the-ground measurements destructive. Using imagery collected with an sUAV we created red, green, blue (RGB) orthomosaics and calculated the Visible Atmospherically Resistant Index (VARI) across these areas. We successfully mapped the litter of invasive annual grasses at one of the two sites. At White Dome, we attained 95.2 % and 84.3 % Producer's and User's Accuracy in mapping invasive annual grasses based on the RGB spectral signature of invasive grass litter. At Beehive Dome, the heterogeneous nature of the edaphic and topographical features made it difficult to accurately map (<20 %) using VARI and RGB alone. Here, we propose plans to increase accuracy in these dryland systems to be able to map invasive annual grasses regardless of year or environmental conditions.