Group items matching

in title, tags, annotations or url

A new study confirms that the Gulf of St. Lawrence is an important habitat for a large proportion of the endangered North Atlantic right whale population.

Pacific Harbour Porpoise (Phocoena phocoena vomerina) occupy a large range throughout coastal waters of British Columbia. Despite their wide distribution, they remain largely data-deficient regarding abundance and population trends, and as such are listed as Special Concern under the Species At Risk Act. Harbour porpoises are also particularly sensitive to disturbance, especially vessel-related acoustic disturbance. Large aggregations of harbour porpoise have been documented in waters around the entrance to the Port of Prince Rupert during the winter months, however little is known about the annual fine-scale activity of this species in this highly trafficked area. In this multi-year study, we used a combination of land-based visual surveys and passive acoustic monitoring (PAM) devices (C-PODs and F-PODs) to address data gaps regarding density, diel patterns, and seasonality of harbour porpoise around Prince Rupert. Echolocation activity was detected during 96% of the 1086 C-POD deployment days and 100% of the 727 F-POD deployment days, with 86% of visual surveys recording harbour porpoise presence. We detected strong seasonal and diel trends in activity, with echolocation peaks between April and June and during the hours of darkness throughout the year. There was a notable increase in daytime activity of harbour porpoise between January and March, which coincides with the months of large aggregation observations. This study indicates that despite the constant presence of large vessels, harbour porpoise continue to persist within waters surrounding Prince Rupert. This suggests the area is an important habitat for this species and also may indicate some extent of acclimatization to localized disturbance.

Marine traffic, coastal planning to benefit from improved forecasts in wave variation.

It's true that ice is melting in the Arctic, but this doesn't mean the U.S. no longer needs icebreaker ships to operate in the region. And right now, the U.S. needs more than what it currently has.

Accurate and automated detection of maritime vessels present in aerial images is a considerable challenge. While significant progress has been made in recent years by adopting neural network architectures in detection and classification systems, these systems are usually designed specific to a sensor, dataset or location. In this paper, we present a system which uses multiple sensors and a convolutional neural network (CNN) architecture to test cross-sensor object detection resiliency. The system is composed of five main subsystems: Image Capture, Image Processing, Model Creation, Object-of-Interest Detection and System Evaluation. We show that the system has a high degree of cross-sensor vessel detection accuracy, paving the way for the design of similar systems which could prove robust across applications, sensors, ship types and ship sizes.

Officials: Pirates seize oil tanker in Ivory Coast.