Field spectroradiometer and simulated multispectral bands for discriminating invasive species from morphologically similar cohabitant plants

Abstract

One of the challenges in fighting plant invasions is the inefficiency of identifying their distribution using field inventory techniques. Remote sensing has the potential to alleviate this problem effectively using spectral profiling for species discrimination. However, little is known about the capability of remote sensing in discriminating between shrubby invasive plants with narrow leaf structures and other cohabitants with similar ecological niche. The aims of this study were therefore to (1) assess the classification performance of field spectroradiometer data among three bushy and shruby plants (Artemesia afra, Asparagus laricinus, and Seriphium plumosum) from the coexistent plant species largely dominated by acacia and grass species, and (2) explore the performance of simulated spectral bands of five space-borne images (Landsat 8, Sentinel 2A, SPOT 6, Pleiades 1B, and WorldView-3). Two machine-learning classifiers (boosted trees classification and support vector machines) were used to classify raw hyperspectral (n = 688) and simulated multispectral wavelengths. Relatively high classification accuracies were obtained for the invasive species using the original hyperspectral bands for both classifiers (overall accuracy, OA = 83–97%). The simulated data resulted in higher accuracies for Landsat 8, Sentinel 2A, and WorldView-3 compared to those computed for bands simulated to SPOT 6 and Pleiades 1B data. These findings suggest the potential of remote-sensing techniques in the discrimination of different plant species with similar morphological characteristics occupying the same niche.

Keywords

• remote sensing
• invasive plants
• gradient boosted trees modeling
• support vector machine