Predicting the bleaching responses of corals is crucial in light of frequent heat stress events to manage further losses of biodiversity and ecosystem functioning, especially for reefs impacted by urbanisation. We examined if the coral cover and community at various Singapore sites changed during the 2016 global coral bleaching event. Bleaching prevalence varied widely among sites in June 2016, and was best explained by site and coral species. While some sites were minimally impacted, others registered significant decreases in coral cover and community changes persisting till March 2017, when normal colouration was mostly regained by corals. Bleaching susceptibility was associated with larger corallites in hermaphrodites and smaller corallites in gonochores (probably due to the cost of maintaining dual sexual functions in hermaphrodites), and with increasing proximity between polyps (likely because thermal damage would be less contained among polyps with greater physiological integration). However, bleaching resilience-the capacity to regain baseline pigmentation-was poorly explained by the traits studied. Our findings suggest that the interplay between local conditions and species composition strongly affects bleaching outcomes on urbanised reefs, and underscore the utility of coral traits for predicting bleaching responses to help in formulating appropriate management strategies.

This paper describes a large dataset of underwater hyperspectral imagery that can be used by researchers in the domains of computer vision, machine learning, remote sensing, and coral reef ecology. We present the details of underwater data acquisition, processing and curation to create this large dataset of coral reef imagery annotated for habitat mapping. A diver-operated hyperspectral imaging system (HyperDiver) was used to survey 147 transects at 8 coral reef sites around the Caribbean island of Curaçao. The underwater proximal sensing approach produced fine-scale images of the seafloor, with more than 2.2 billion points of detailed optical spectra. Of these, more than 10 million data points have been annotated for habitat descriptors or taxonomic identity with a total of 47 class labels up to genus- and species-levels. In addition to HyperDiver survey data, we also include images and annotations from traditional (color photo) quadrat surveys conducted along 23 of the 147 transects, which enables comparative reef description between two types of reef survey methods. This dataset promises benefits for efforts in classification algorithms, hyperspectral image segmentation and automated habitat mapping.