Mapping Coral Reef Habitats with ICESat-2 and Satellite Imagery: A Novel Spectral Unmixing Approach Compared to Machine Learning

Accurate, scalable mapping of coral reef habitats is essential for monitoring ecosystem health and detecting change over time. In this study, we introduce a novel mathematically based nonlinear spectral unmixing method for benthic habitat classification, which provides sub-pixel estimates of benthic composition, capturing the mixed benthic composition within individual pixels. We compare its performance against two machine learning approaches: semi-supervised K-Means clustering and AdaBoost decision trees. All models were applied to high-resolution PlanetScope satellite imagery and ICESat-2-derived terrain metrics. Models were trained using a ground truth dataset constructed from benthic photoquadrats collected at Heron Reef, Australia, with additional input features including band ratios, standardized band differences, and derived ICESat-2 metrics such as rugosity and slope. While AdaBoost achieved the highest overall accuracy (93.3%) and benefited most from ICESat-2 features, K-Means performed less well (85.9%) and declined when these metrics were included. The spectral unmixing method uniquely captured sub-pixel habitat abundance, offering a more nuanced and ecologically realistic view of reef composition despite lower discrete classification accuracy (64.8%). These findings highlight nonlinear spectral unmixing as a promising approach for fine-scale, transferable coral reef habitat mapping, especially in complex or heterogeneous reef environments.