A benthic substrate classification method for seabed images using deep learning: Application to management of deep‐sea coral reefs

Abstract

Protecting deep‐sea coral‐based vulnerable marine ecosystems (VMEs) from human impacts, particularly bottom trawling, is a major conservation challenge in world oceans. Management processes for these ecosystems are weakened by key uncertainties that could be substantially addressed by having much greater volumes of quantitative image‐derived data that detail the distribution and abundance of coral reefs and the nature of impacts upon them. Considerably greater volumes of data could be available if the resource costs of image annotation are reduced. In this paper we propose a solution: a deep learning system capable of automatically identifying reef‐building stony corals amongst other seabed substrata in much larger volumes of seabed imagery than was previously possible. Using a previously annotated dataset, we trained a convolutional neural network on approximately 70,000 classified images (‘snips’) comprising six benthic substrate classes, including reef‐building stony coral—‘coral matrix’. Model performance improvements, chiefly by dataset cleaning, transfer learning and hyperparameter optimisation, resulted in the final trained model achieving validation accuracy of 98.19%. The classification was robust: benthic substrate types were accurately differentiated, and in some cases more consistently than was achieved by human annotators. Synthesis and applications. The availability of much larger volumes of automatically annotated image‐derived data will improve spatial management of impacts on coral‐based VMEs in the deep sea by (1) improved cross‐validation and performance of spatial models required to predict coral distribution and abundance over the large scales of managed areas, and (2) establishing empirical relationships between coral abundance on the seabed and coral bycatch landed during fishing operations.

New interactive machine learning tool for marine image analysis

“…Supplied annotations are then used by the tools to complete training in the absence of user input. This passive training process may compensate for the additional time required by users to create a manually annotated training dataset but may also limit the extent of model optimization possible compared to a human-in-the-loop approach, such as with RootPainter [91]. As all software has advantages and disadvantages depending on user needs, a conscious decision regarding choice of machine learning tool for a desired investigation needs to be made.…”