Project: CoastVision: Computer vision to expand monitoring and accelerate assessment of coastal fish (2021-2025)

 

Funded by The Research Council of Norway’s Oceans Program (12.2 M nok), nr. 325862

 

CoastVision will use the power of deep learning to refine and extend a computer vision pipeline for detecting, classifying and sizing the key fish species in shallow water coastal ecosystems, facilitating a transition to fully automated video analysis. Our models will be trained on data sets from several different surveys, ensuring cost-efficient development of routines that will be widely applicable. Computer vision for re-identifying (re-ID) individuals solely based on their unique visible features will also be developed. This novel aspect of CoastVision could ultimately provide new opportunities to obtain detailed knowledge about behaviour and population dynamics in wild fish populations, with minimal negative impact on animals and habitats and at a low cost. Our focal species for re-ID are Atlantic cod, ballan wrasse, corkwing wrasse and atlantic salmon, commercially important species with complex, high-contrast skin patterns. To generate the necessary training data for re-ID we will use synchronized radio frequency identification and camera systems. CoastVision’s automated video analysis pipeline will be integrated into ongoing ecosystem surveys and case studies whose main objective is to better understand the factors that affects the reproduction, recruitment and survival of commercially important coastal species. As such, CoastVision will contribute to independent, but complementary, research objectives. The project will advance the international research front for applied machine learning in marine ecology, which ultimately can revolutionize our ability to observe, understand and respond to ecological change at scales far more refined than is currently possible.

 

 

Visualization of the re-identification part of the CoastVision pipeline (by Sørdalen, adapted from Vidal et al 2021).

Project: The interplay between life history traits and selective harvesting of lobster

Research group at Flødevigen research station

We aim to continue investigate the interactions between mating systems, life histories and selective harvesting of European lobsters using empirical data on morphology, growth, survival and deeper understanding of natural (and unatural) mating behaviour in fished and protected populations.

 

 

 

 

 

 

 

 

 

 

 

 

 

Left: figure from Sørdalen et al (2020). Right: origin unknown, modified text.

 

 

Project: WildWrasse: Eco-evolutionary effects of wrasse fisheries and their use as cleaner-fish in salmon aquaculture 

Lab: Fishlarvae.org

Wrasses are intensively harvested in Scandinavia and on the British Isles, where they are deployed as cleaner fish in salmon farms. What are the consequences for wrasse populations and the coastal ecosystems? Main objectives:

1. Selective harvesting: Understanding how selective fisheries affect species composition, phenotypic distributions and the consequences for population dynamics and mating patterns. Contrasting slot-size limits vs. minimum size limits.
2: Eco-effects: Investigating the wider ecosystem effects of depleting wrasse populations.
3:   Consequences of translocations: What happens when wrasse escapes into genetically distinct populations?

 

 

 

 

Photo: Sørdalen

©2020 by Tonje Knutsen Sørdalen