Sea Technology

FEB 2018

The industry's recognized authority for design, engineering and application of equipment and services in the global ocean community

Issue link:

Contents of this Issue


Page 43 of 52 February 2018 | ST 43 representing 6,000 individually identified sharks across 54 coun- tries over 22 years has given scien- tists a rich data set to analyze and better understand the nature of this endangered species. Through this effort, researchers have now identified 20 whale shark aggregation sites globally. ROV Video Informs Deep-Sea Food Web Study MBARI researchers have done the first comprehensive study of deep-sea food webs using hundreds of video observations of animals feeding off the central California coast. The study shows that deep- sea jellies are key predators and provides new information on life near the ocean surface. Since the late 1980s, MBARI re- searchers have used ROVs to study deep-sea animals in their own envi- ronment. In the process, MBARI has amassed more than 23,000 hours of deep-sea video footage. In this new approach, they used deep-diving vehicles to observe an- imals feeding on one another in the deep sea. Technicians in the MBARI Video Lab painstakingly analyzed every deep ROV dive, identifying animals and their behaviors and entering this information into the Video Annotation and Reference System (VARS) database. Comb- ing through the VARS database, researchers discovered almost 750 different video observations of ani- mals eating one another. The video footage shows that jelly food webs encompass animals that live near the surface. Gelati- nous animals have been found in the stomachs of animals ranging from penguins and albatrosses to sunfish and leatherback sea turtles. AI for Eco-Friendly Ship Tech Eco Marine Power (EMP) will begin using the Neural Network Console provided by Sony Network Communications Inc. as part of a strategy to incorporate artificial in- telligence (AI) into various ongoing ship-related technology projects, including the further development of the Aquarius MRE renewable en- ergy power system and EnergySail. The Neural Network Console uses deep learning for AI creation and has been used in deep-learning applied technology development within Sony since 2015. Various functions include recognition tech- nology and a full-fledged graphical user interface. Deep learning refers to a form of machine learning that uses neural networks modeled after the human brain. An initial area of focus will be studying how the Neural Network Console and AI can assist with the development of the automated con- trol system for EMP's EnergySail. This system automatically adjusts the position of the EnergySail de- pending on variables such as wind speed and direction. AI will also help analyze the results of comput- er simulations related to the Aquari- us Eco Ship. ST Choose your frequency Choose your depth rating Choose the industry innovator Rowe Technologies state-of-the- art SeaWATCH Acoustic Doppler Current Profiler (ADCP) is applicable to an array of oceanographic current measuring deployments. Operating at 300, 600, and 1200 kHz, and available in 300 to 6000-meter depth rated capsules, record all-inclusive current flow data from up to 200 cells worry-free on an industry leading 32 GB internal memory card. Rapidly download via standard Ethernet port into customizable data formats in MATLAB, CSV, and PD0. Find out more at

Articles in this issue

Links on this page

Archives of this issue

view archives of Sea Technology - FEB 2018