Estimating Vegetation Beta Diversity from Airborne Imaging Spectroscopy and Unsupervised Clustering

Abstract

Airborne remote sensing has an important role to play in mapping and monitoring biodiversity over large spatial scales. Techniques for applying this technology to biodiversity mapping have focused on remote species identification of individual crowns; however, this requires collection of a large number of crowns to train a classifier, which may limit the usefulness of this approach in many study regions. Based on the premise that the spectral variation among sites is related to their ecological dissimilarity, we asked whether it is possible to estimate the beta diversity, or turnover in species composition, among sites without the use of training data. We evaluated alternative methods using simulated communities constructed from the spectra of field-identified tree and shrub crowns from an African savanna. A method based on the k-means clustering of crown spectra produced beta diversity estimates (measured as Bray-Curtis dissimilarity) among sites with an average pairwise correlation of ~0.5 with the true beta diversity, compared to an average correlation of ~0.8 obtained by a supervised species classification approach. When applied to savanna landscapes, the unsupervised clustering method produced beta diversity estimates similar to those obtained from supervised classification. The unsupervised method proposed here can be used to estimate the spatial structure of species turnover in a landscape when training data (e.g., tree crowns) are unavailable, providing top-down information for science, conservation and ecosystem management applications.

Keywords

• beta diversity
• Bray-Curtis
• Carnegie Airborne Observatory
• hyperspectral
• Kruger National Park
• LiDAR
• savanna
• spectral variation hypothesis
• k-means clustering
• support vector machine
• unsupervised