FathomNet: A global image database for enabling artificial intelligence in the ocean.

The ocean is experiencing unprecedented rapid change, and visually monitoring marine biota at the spatiotemporal scales needed for responsible stewardship is a formidable task. As baselines are sought by the research community, the volume and rate of this required data collection rapidly outpaces our abilities to process and analyze them. Recent advances in machine learning enables fast, sophisticated analysis of visual data, but have had limited success in the ocean due to lack of data standardization, insufficient formatting, and demand for large, labeled datasets. To address this need, we built FathomNet, an open-source image database that standardizes and aggregates expertly curated labeled data. FathomNet has been seeded with existing iconic and non-iconic imagery of marine animals, underwater equipment, debris, and other concepts, and allows for future contributions from distributed data sources. We demonstrate how FathomNet data can be used to train and deploy models on other institutional video to reduce annotation effort, and enable automated tracking of underwater concepts when integrated with robotic vehicles. As FathomNet continues to grow and incorporate more labeled data from the community, we can accelerate the processing of visual data to achieve a healthy and sustainable global ocean.

My Deep Sea, My Backyard: a pilot study to build capacity for global deep-ocean exploration and research.

The deep ocean is the largest ecosystem on the planet, constituting greater than 90% of all habitable space. Over three-quarters of countries globally have deep ocean within their Exclusive Economic Zones. While maintaining deep-ocean function is key to ensuring planetary health, deficiencies in knowledge and governance, as well as inequitable global capacity, challenge our ability to safeguard the resilience of this vast realm, leaving the fate of the deep ocean in the hands of a few. Historically, deep-ocean scientific exploration and research have been the purview of a limited number of nations, resulting in most of humankind not knowing the deep ocean within their national jurisdiction or beyond. In this article, we highlight the inequities and need for increased deep-ocean knowledge generation, and discuss experiences in piloting an innovative project 'My Deep Sea, My Backyard' toward this goal. Recognizing that many deep-ocean endeavours take place in countries without deep-ocean access, this project aimed to reduce dependency on external expertise and promote local efforts in two small island developing states, Trinidad and Tobago and Kiribati, to explore their deep-sea backyards using comparatively low-cost technology while building lasting in-country capacity. We share lessons learned so future efforts can bring us closer to achieving this goal. This article is part of the theme issue 'Nurturing resilient marine ecosystems'.

First records of the seven-gilled Notorynchus cepedianus and six-gilled Hexanchus griseus sharks (Chondrichthyes: Hexanchiformes: Hexanchidae) found in the Galápagos Marine Reserve.

This study reports the first records of cowsharks (Hexanchidae) in the Galápagos Islands, in particular Notorynchus cepedianus and Hexanchus griseus, observed between depths of 210 and 418 m on footage from free-falling autonomous deep-ocean cameras. These sightings provide new information on the habitat preferences and range distribution for N. cepedianus and the first records of H. griseus in Ecuadorian waters. The findings support the formulation of regional conservation strategies for these large apex predator species and highlight the limited biological knowledge of Galápagos' deep-water ecosystems.