This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

The deep learning (DL) revolution is touching all scientific disciplines and corners of our lives as a means of harnessing the power of big data. Marine ecology is no exception. New methods provide analysis of data from sensors, cameras, and acoustic recorders, even in real time, in ways that are reproducible and rapid. Off-the-shelf algorithms find, count, and classify species from digital images or video and detect cryptic patterns in noisy data. These endeavours require collaboration across ecological and data science disciplines, which can be challenging to initiate. To promote the use of DL towards ecosystem-based management of the sea, this paper aims to bridge the gap between marine ecologists and computer scientists. We provide insight into popular DL approaches for ecological data analysis, focusing on supervised learning techniques with deep neural networks, and illustrate challenges and opportunities through established and emerging applications of DL to marine ecology. We present case studies on plankton, fish, marine mammals, pollution, and nutrient cycling that involve object detection, classification, tracking, and segmentation of visualized data. We conclude with a broad outlook of the field’s opportunities and challenges, including potential technological advances and issues with managing complex data sets.

The European lobster Homarus gammarus is heavily exploited in the Norwegian fishery, and several management actions have been implemented to protect the species. Three marine protected areas (MPAs) excluding all but hook and line type fishing gear were established along the Skagerrak coast in 2006, effectively banning the trap-based fishery for European lobster. Lobster populations within MPAs and adjacent control areas were studied by capture-markrecapture and recovery methods every year from prior to MPA establishment to the present. During 2006−2014, a total of 4682 and 3317 lobsters were captured (including recaptures) in the MPAs and control areas, respectively. In all MPAs, protection led to a shift in demography, with an increase in mean total length of 15% during 2006−2014, thereby opposing the effects of a sizeselective fishery. No difference was found in rates of movement out from MPAs and control areas, but lobsters moving from MPAs and caught in fished areas were significantly larger than lobsters moving out of control areas. In instances where lobsters tagged in a control area moved into an MPA, the immigrating lobsters had a larger body size than the mean in their area of origin. The range of movement undertaken by recovered lobsters extended beyond the home range sizes suggested by previous shorter-term studies, and well beyond the sizes of the small coastal MPAs studied herein. In summary, demographic changes should be accounted for when interpreting the value of spillover from MPAs, and also potential 'spill in' from fished areas to MPAs.