Using machine learning to map where sharks face the greatest dangers from longline fishing

Spatial distribution of tRFMO catches and voltage data. tRFMO Mean annual catches of sharks (count, a), effort associated with catching sharks (hooks, b) and cost of sharks (count/hook, c) from publicly available longline data between 2012–2020. Data from each tRFMO were scaled independently using quantities between 0 and 1 in increments of 0.1. Blue colors indicate areas of low shark catch, effort, and CPUE, while red colors indicate areas of high shark catch, effort, and CPUE. Black lines indicate tRFMO limits. credit: Frontiers in Marine Sciences (2023). DOI: 10.3389/fmars.2022.1062447

The ocean can be a dangerous place, even for sharks. Despite being at the top of the food chain, these predators are now suffering from devastating human activities such as overfishing, pollution and climate change.

Researchers at the University of California, Santa Barbara have focused on an issue particularly troublesome for sharks: entanglement with longline tuna. Using data from regional fisheries management organizations and machine learning algorithms, the scientists were able to identify hotspots where shark species face the greatest threat from longline fishing. Results published in Frontiers in Marine Scienceshighlighting key areas where sharks can be protected with minimal impact on tuna fisheries.

Marine longline fisheries take a particularly heavy toll on ocean life. The non-selective technique has the highest rate of bycatch of sharks. “Longline fishing gear is exactly what it sounds like: a long line with lots of hooks attached to a bait. It can be left in the water, waiting for fish to bite, for a very long time,” explained co-lead author Darcy Bradley, who heads the Ocean and Fisheries Program at the University of California, Santa Barbara in the Environmental Markets Laboratory (emLab). These baited hooks catch predators such as tuna, but many nearby sharks will also converge on the bait.

Rather than simply reporting how many sharks have been caught and where they were caught, the authors aim to assess the relative risks facing sharks across different regions of the ocean. “One of the key questions was ‘Where is the highest risk of shark hunting, and does that interfere with fishing efforts?'” said co-lead author Eshel Burns, project scientist at emLab. ”

To answer this question, Burns, Bradley and co-author Lennon Thomas (also at emLab) searched for data on longline fisheries. They obtained publicly available data from regional tuna fisheries management organizations. These intergovernmental institutions manage, collect data, and conduct scientific assessments of tuna and tuna-like species.

The authors have compiled data on shark catches from industrial longline fishing across all tuna fisheries in the world into one comprehensive resource. This was quite a task. Each fisheries management organization operates differently, which means that their data is not always in the same format. “Now anyone interested in shark fishing and other events in the global longline fishery can access that information,” Bradley said.

The authors correlate spatial shark catch data with environmental data such as sea surface temperature and factors associated with food abundance. It also included economic data such as the ship price — the price fishermen charge directly for their catch — for different shark species each year. “Because you can’t catch a shark where it doesn’t live, we used species distribution models to identify where different sharks actually live in the ocean to inform our risk assessment,” Bradley added.

However, there were many unknowns. Not every fishing vessel has a neutral observer who records catches for fisheries management organizations. And not every report is completely accurate. So Burns, Bradley, and Thomas used a model to fill in the gaps, identify trends, and draw conclusions from this incomplete data. “The whole reason we use the model is because we have incomplete data,” Bradley said. “If we knew everything, we wouldn’t need a model.”

This was a novel approach for estimating interactions between fisheries and marine species. Using machine learning enabled the team to extrapolate trends from chaotic datasets. First, the model assessed whether a shark species was present in an area, and if so, how likely it was that they would be caught there. Then he looked at how many sharks of each species had been caught in the area.

The authors prioritized predictive power in this study. “Our goal was to identify where sharks are at risk in longline tuna fisheries,” Bradley explained. “For this study, we weren’t trying to understand how different factors influence this risk.”

The authors used a random forest model, which combines the outputs of several decision trees. Each decision tree considers a different variable, the result of which is a vote for the final prediction. “The basic idea is that a group of poor decision makers, the trees, can exchange information to finally make a better decision: the forest,” Bradley said. While this method does not provide a clear picture of how each factor affects the system, it is very good at understanding messy and incomplete datasets. What emerges is a map of the fishing hazards of sharks around the world.

Tuna and sharks are predators and target similar prey, so they are often found together. But while they may share some traits, sharks and tuna are fundamentally different types of animals. Tuna grow quickly and produce many offspring, while sharks mature relatively late and reproduce slowly. As a result, tuna can withstand much higher fishing pressures than sharks, and even a small impact on shark populations can affect the population of endangered species.

Fortunately, scientists have found that hotspots for prolonged interactions with sharks do not correspond to preferred hunting grounds. “This suggests that we can design management strategies that can protect vulnerable and threatened shark species without having to close the most productive tuna fishing grounds,” Bradley said. The team found this particularly encouraging, as it could encourage actions that help sharks while also attracting fishermen.

The difference between hotspots and good fishing spots can stem from those differences between tuna and sharks. “For example, we’ve observed that some shark hunting hotspots overlap areas that play an important role in the life cycle of sharks,” added Thomas. Take in the ocean off the coast of Namibia, a popular nursery habitat and juvenile feeding ground for blue sharks.

In fact, interactions with longline fishing fleets have been dominated by blue sharks. These common and widespread species contributed to more than 78% of the total shark catch reported by RFMOs between 2012 and 2020. As a result, the majority of the paper’s findings on sharks as a whole are driven by blue shark fishing In particular. This was one of the reasons why the authors investigated the hotspots of 12 species separately in their Supplementary Material.

The team is working on a follow-up study to estimate global shark mortality due to fishing as a whole — not just longlines. They also plan to assess whether the regulations have helped prevent shark hunting. Furthermore, the random forest model of this paper can provide insights into other species threatened by poaching.

Better data will allow the team to improve their model, but it does provide useful lessons. For example, we can design management strategies to protect vulnerable and threatened shark species without disrupting key tuna fishing grounds. “Making small adjustments to tuna fishing regulations to avoid shark fishing hotspots can make a huge difference to future shark numbers, while ensuring the continued success of tuna fisheries,” Burns said.

more information:
Echelle S. Burns et al, Global Hotspots of Shark Interactions with Industrial Longline Fisheries, Frontiers in Marine Sciences (2023). DOI: 10.3389/fmars.2022.1062447

Provided by the University of California – Santa Barbara

the quote: Using Machine Learning to Map Where Sharks Face the Greatest Longline Fishing Threats (2023, January 12), Retrieved January 12, 2023 from https://phys.org/news/2023-01-machine-sharks-longline -fishing. html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.

Leave a Comment