top of page
  • Facebook
  • Instagram
  • X

Faster Analysis of Data to Evaluate Bycatch Reduction Efforts in Pollock Fishery

NOAA

Nov 13, 2025

Advancements in Artificial Intelligence forms such as computer vision, machine learning, and deep learning assist with processing data. The model was highly accurate at detecting pollock and salmon.

Advancements in Artificial Intelligence forms such as computer vision, machine learning, and deep learning assist with processing data. The model was highly accurate at detecting pollock and salmon.


Scientists used a model to detect and classify fish in videos more quickly than humans. The detection model is called You Only Look Once, version 11 (or YOLOv11). It’s helping scientists evaluate the effectiveness of excluders that help salmon escape from fishing nets intended to catch pollock. 


YOLOv11 is an object detection deep learning model for images. Scientists at the Alaska Fisheries Science Center customized it to detect and identify both pollock and salmon in fishing nets. This allows scientists to semi-automate the video review process used to evaluate the effectiveness of bycatch reduction devices. They can also observe fish behavior to improve the performance of these devices.


READ THE STORY at Alaska Native News >>

Sign Up For More Info to Come

GET THE FACTS

We’re earnestly developing fact-based content to help Alaskans stay informed about the science of salmon and what’s really happening to our favorite fish. 

If you believe science matters and you’re interested in the science of salmon, please sign up to receive updates on our work.

Sign up to stay connected, learn more, and help share the truth when it matters most.
(Just your email — no spam, no selling, no pressure.)

© 2025 by Science of Salmon. Powered and secured by Wix

bottom of page