LB 36-299 - Classifying a highly polymorphic tree species across landscapes using airborne imaging spectroscopy

Vegetation classifications on large geographic scales are necessary to inform conservation decisions and monitor keystone, invasive, and endangered species. These classifications are typically achieved by applying models to imaging spectroscopy, or hyperspectral remote sensing, data, but are often limited in spatial extent. Here we provide accurate, high-resolution spatial data on the keystone species Metrosideros polymorpha, a highly polymorphic tree species distributed across biomes and environmental gradients on Hawai'i island, using airborne imaging spectroscopy and LiDAR. We compare two tree species classification techniques, support vector machine (SVM) and spectral unmixing, to assess their ability to map M. polymorpha over 28,000 square kilometers where differences in topography, background vegetation, sun angle relative to the aircraft, and day of data collection, among others, challenges accurate classification. To capture spatial variability in model performance, we applied gaussian process classification (GPC) to estimate the spatial probability density of M. polymorpha occurrence independent of the spectral data. We found that, while SVM and spectral unmixing models exhibit similar raw score accuracy over the test set (96.0% and 93.4%, respectively), SVM better reproduces the spatial distribution of M. polymorpha than spectral unmixing. We developed a final 2 m x 2 m M. polymorpha presence dataset and a 30 m x 30 m M. polymorpha density dataset using SVM classifications that have been made publicly available for use in conservation applications.