News

Use of Artificial Intelligence (AI) to Monitor Steller Sea Lion Populations

Article and Figures Provided By: Katie Sweeney, Marine Mammal Laboratory, Alaska Fisheries Science Center, NOAA Fisheries

Kenneth Vierra 0 866 Article rating: No rating
Every year, Alaska Fisheries Science Center’s Marine Mammal Laboratory of NOAA Fisheries uses crewed and uncrewed systems to conduct aerial surveys of known Steller sea lion sites across Alaska. These surveys are essential to monitoring the endangered western population of Steller sea lions in Alaska. While the population as a whole has begun to show signs of recovery, one region in the westernmost part of the population range has declined 94% in the last 40 years (showing no signs of recovery), and rookeries - sites where sea lions mate, give birth, and rest - have begun to disappear. In the Gulf of Alaska, anomalous warm water events beginning in 2014 are becoming more commonplace and are likely causing the observed declines in the area - an area which was previously showing signs of sea lion population recovery and began to increase in 2002.

Multi-spectral Imaging of Polar Bears at Cochrane Polar Bear Habitat

Article Provided By: Erin Moreland

Kenneth Vierra 0 3571 Article rating: 5.0

During the first week of April, NOAA researchers from the Alaska Fisheries Science Center’s Marine Mammal Laboratory (MML) collected multi-spectral imagery of polar bears at the Cochrane Polar Bear Habitat in Ontario, Canada. Color, infrared, and ultraviolet photos were collected using two APH-28 hexacopters. This ongoing work was partially funded by the UAS Program. One platform carried the FLIR Duo Pro R camera and the other carried a new UV payload (developed by Ben Hou at MML) paired with a color camera and laser altimeter. This imagery will help improve remote sensing of bears during aerial surveys for ice-associated seals and polar bears on the sea ice habitat of the Bering, Chukchi, and Beaufort seas. The team also collected thermal data of resting bears and bears coming out of cold water to see how these behaviors affect the thermal signature detected from the airborne cameras. Multi-spectral imagery of bears on ice, in open snow fields, and near rocks will be used in the development of an automated bear detection model in support of upcoming international survey efforts of the Beaufort Sea for ice seals and polar bears.  NOAA’s Canadian partners primary focus is bears, so this work also helps build that partnership so we can get more meaningful seal data from the full Beaufort surveys. Polar bears are listed as threatened under the ESA (as are ringed and bearded seals).

Development of an Autonomous Payload for Detection of Seals and Polar Bears on Sea Ice

Article Provided By: Erin Moreland (NMFS/AFSC/NMML)

Kenneth Vierra 0 2743 Article rating: 5.0

Polar bears and Ice-associated seals (bearded, ringed, spotted, and ribbon seals) are key components of Arctic marine ecosystems and are important resources for coastal Alaska Native communities. Reliable abundance estimates for ice seals are needed for developing sound management decisions under the Marine Mammal Protection Act and extinction risk assessments under the Endangered Species Act. The animals’ broad and patchy geographic distributions and rapidly changing sea ice habitat make these species particularly challenging to study.

An autonomous payload is required to integrate UAS into surveys of ice-associated mammals, in order to improve the efficiency and human safety in gathering essential data for NOAA stewardship. Moving from occupied aircraft to long-range UAS operations will require an efficient and “smart” payload to collect images needed for abundance estimation and habitat analysis while providing situational awareness to the pilot in command.

The Alaska Fisheries Science Center’s Marine Mammal Lab is developing a system that can run advanced machine learning algorithms on-board the aircraft to process multispectral imagery in real time, minimizing the collection of extraneous imagery that requires burdensome data storage, management, and processing.  Algorithm development is utilizing a neural network approach known as YOLO, which processes imagery at a rate of 60-100 frames per second.  Over 1.8 million color and thermal images are being used to train YOLO to detect animals on the sea ice and classify detections to species. This algorithm will be tested in-flight during April 2019.

RSS