Identifying partners at sea on contrasting fisheries around the world

09/05/2020 ∙ by Rocio Joo, et al. ∙ 0

Here we present an approach to identify partners at sea based on fishing track analysis, and describe this behaviour in six different fleets: 1) pelagic pair trawlers, 2) large bottom otter trawlers, 3) small bottom otter trawlers, 4) mid-water otter trawlers, all operating in the North-East Atlantic Ocean, 5) anchovy purse-seiners in the South-East Pacific Ocean, and 6) tuna purse-seiners in the Western Indian Ocean. This type of behaviour is known to exist within pelagic pair trawlers. Since these vessels need to be in pairs for their fishing operations, in practice some of them decide to move together throughout their whole fishing trips, and others for only a segment of their trips. To identify partners at sea, we used a heuristic approach based on joint-movement metrics and Gaussian mixture models. The models were first fitted on the pelagic pair trawlers and then used on the other fleets. From all of these fisheries, only the tuna purse-seiners did not present partners at sea. We then analysed the connections at the scale of vessels and identified exclusive partners. This work shows that there are collective tactics at least at a pairwise level in diverse fisheries in the world.



There are no comments yet.


page 1

page 2

page 3

page 4

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.