摘要：Cold-water coral (CWC) mounds are biogenic, long-lived morphostructures composed primarily by scleractinian CWC's and hemipelagic sediments that form complex deep-sea microhabitats found globally but specifically along the European-Atlantic margin. In this work, high-resolution mapping was applied to identify individual organismal distribution and zonation across a CWC Piddington Mound within the Porcupine Seabight, Ireland Margin. Marine Object-Based Image Analysis (MOBIA) and different machine learning classification methods (decision tree, logistic regression, and deep neural network) were applied to a high-resolution (2 mm) reef-scale video mosaic and ROV-mounted multibeam data in order to provide new insights into the spatial organization of coral frameworks and environmental factors on CWC mounds. The results showed an accurate quantification of the amount of Coral Framework (14.5%; ~2% live and ~12.5% dead) and sponges (~3.5%) with heterogeneous distribution, restricted to a certain portion of the mound. This is the first object level quantification of live and dead coral framework facies and individual sponges across an entire CWC mound. This approach has application for habitat and conservation studies, provides a quantification tool for carbon budget assessments and can provide a baseline to assess CWC mound change. The approach can also be modified for application in other habitats.
