Spectral Unmixing and Mapping of Coral Reef Benthic Cover

Abstract

Coral reefs are an important ecosystem to the local communi- ties and indigenous wildlife that rely on them. However, reefs have greatly degraded in recent decades with the remaining at increasing risk of loss. Quantitatively mapping these reefs would provide a resource for us to monitor changes and un- derstand their health. We explore methods leveraging limited spectral data and resources for efficient global scale model- ing of coral reefs. We then evaluate performance on a Deep Neural Network and our previously developed Deep Condi- tional Dirichlet Model. Regions of high uncertainty based on the model output prediction are used to determine informa- tive in situ sampling. An ergodic planner is implemented to generate a path through these regions to acquire samples that best improve the coral map. The result is a resource efficient learning based pipeline that augments existing spectral data and maps coral reefs globally to improve our understanding of their condition.