Global observing needs in the deep ocean

LA Levin, BJ Bett, AR Gates, P Heimbach… - Frontiers in Marine …, 2019 - frontiersin.org
The deep ocean below 200 m water depth is the least observed, but largest habitat on our
planet by volume and area. Over 150 years of exploration has revealed that this dynamic …

Ecological variables for developing a global deep-ocean monitoring and conservation strategy

R Danovaro, E Fanelli, J Aguzzi, D Billett… - Nature Ecology & …, 2020 - nature.com
The deep sea (> 200 m depth) encompasses> 95% of the world's ocean volume and
represents the largest and least explored biome on Earth (< 0.0001% of ocean surface), yet …

Ecological role of submarine canyons and need for canyon conservation: a review

U Fernandez-Arcaya, E Ramirez-Llodra… - Frontiers in Marine …, 2017 - frontiersin.org
Submarine canyons are major geomorphic features of continental margins around the world.
Several recent multidisciplinary projects focused on the study of canyons have considerably …

Tracking fish abundance by underwater image recognition

S Marini, E Fanelli, V Sbragaglia, E Azzurro… - Scientific reports, 2018 - nature.com
Marine cabled video-observatories allow the non-destructive sampling of species at
frequencies and durations that have never been attained before. Nevertheless, the lack of …

New high-tech flexible networks for the monitoring of deep-sea ecosystems

J Aguzzi, D Chatzievangelou, S Marini… - … science & technology, 2019 - ACS Publications
Increasing interest in the acquisition of biotic and abiotic resources from within the deep sea
(eg, fisheries, oil–gas extraction, and mining) urgently imposes the development of novel …

Artificial intelligence for fish behavior recognition may unlock fishing gear selectivity

AS Abangan, D Kopp, R Faillettaz - Frontiers in Marine Science, 2023 - frontiersin.org
Through the advancement of observation systems, our vision has far extended its reach into
the world of fishes, and how they interact with fishing gears—breaking through physical …

Management and sustainable exploitation of marine environments through smart monitoring and automation

F Glaviano, R Esposito, AD Cosmo, F Esposito… - Journal of Marine …, 2022 - mdpi.com
Monitoring of aquatic ecosystems has been historically accomplished by intensive
campaigns of direct measurements (by probes and other boat instruments) and indirect …

Video image enhancement and machine learning pipeline for underwater animal detection and classification at cabled observatories

V Lopez-Vazquez, JM Lopez-Guede, S Marini… - Sensors, 2020 - mdpi.com
An understanding of marine ecosystems and their biodiversity is relevant to sustainable use
of the goods and services they offer. Since marine areas host complex ecosystems, it is …

Image dataset for benchmarking automated fish detection and classification algorithms

M Francescangeli, S Marini, E Martínez, J Del Río… - Scientific data, 2023 - nature.com
Multiparametric video-cabled marine observatories are becoming strategic to monitor
remotely and in real-time the marine ecosystem. Those platforms can achieve continuous …

Setting the stage for the machine intelligence era in marine science

C Beyan, HI Browman - ICES Journal of Marine Science, 2020 - academic.oup.com
Abstract Machine learning, a subfield of artificial intelligence, offers various methods that can
be applied in marine science. It supports data-driven learning, which can result in automated …