Hyperspectral remote sensing for invasive species detection and mapping

The rapid spread of non-native invasive plant species is causing irreparable damage to global ecosystems. Controlling and managing invasives requires new methods to map and monitor their spread. While digital multiband remote sensing and aerial photography have been available for many years, newer detector technologies have made it possible to accurately acquire a detailed laboratory-like spectrum of each pixel in an image from space. We discuss two case studies of detection of invasives using AVIRIS data that take advantage of this new technology to map species based on high spectral (224 10nm bands) and spatial (similar to4m) resolution spectra. We present mapping of several invasive species, including iceplant, jubata grass, fennel, and giant reed from a range of habitats at Camp Pendleton and Vandenberg Air Force Base in California. Spectral feature mapping followed by supervised classification produced accurate maps of these invasives. Validation of weed maps was based on field surveys.