Fishing tuna vessel Shen Lian Chen. (Photo: WCPFC)

NGO plans to use artificial neural networks in tuna fishery

The Nature Conservancy (TNC) has launched a program to outfit all of the thousands of longline tuna vessels in the tropical Pacific fleet with a suite of cameras and sensors.

The NGO says it has found out that in one of the world’s last great high seas fisheries, the western and central tropical Pacific, only 2 per cent of the fishing vessels are monitored by authorities, and as much of 40 per cent of the catch may be unintended or illegal, Quartz reported.

But, TNC highlights that the entity has stressed that fishing vessel Shen Lian Chen, with thousands of hooks trailing behind it, is playing by the rules. The vessel is one of four boats in the region that has allowed the TNC to install cameras recording every fish coming over the side.

“It’s the first step by TNC to outfit all of the thousands of longline tuna vessels in the tropical Pacific fleet with a suite of cameras and sensors,” pointed out Matt Merrifield, the chief technology officer at TNC of California.

The officer explained that within a few years, he wants to see 100 per cent coverage and recognised that it is impossible to manage these stocks efficiently if they do not have the data.

However, the NGO's representatives clarified that watching all the video is a huge data challenge as on a typical two-month fishing trip, each boat records about 800 hours of footage and even a highly trained fisheries monitor would need about 10 weeks to watch all of it from a single boat.

For that reason, TNC has turned to Silicon Valley and computer vision advances are allowing computers to recognize images of birds, name plant species,catalog rainforest species and even name individual whales.

The field has made strides by applying artificial neural networks—algorithms modeled on the human brain—to “learn” objects by seeing thousands or millions of examples. Every time an algorithm identifies a specific species, it increases the probability it will recognize the next one. Over time, these algorithms have made impressive progress.

TNC wants to use use satellite and street-level images like those used for Google maps to see what is on the end of a fishing line, clarifying that building an algorithm to tell the difference between a tuna and a turtle is hard and recognizing the difference between a bigeye and yellow fin tuna, as well as variations among adult and juvenile fish, is even harder.

To solve that challenge, the organization is sponsoring a USD 150,000 competition on the data competition platform Kaggle, and thousands of data scientists to test their algorithms against reams of video from the long-line tuna fishery.

Competitors must identify what, when and where a line is caught, catalog catches with 90 per cent accuracy, and reduce the time needed to review the footage by about 40 per cent.

In addition, the organization has launched the “This is Our Future” campaign, including up-close-and-personal views of the fishery in VR to raise awareness.

 
[email protected]
www.seafood.media

Address:	4245 North Fairfax Drive, Suite 100
City:	Arlington
State/ZIP:	Virginia (VA 22203-1606)
Country:	United States
Phone:	+1 703 841 5300
E-Mail:	[email protected]
More about:

Print