AI News, Deep Learning Goes To The Deep Seas And The Billion-Dollar Tuna Industry
Deep Learning Goes To The Deep Seas And The Billion-Dollar Tuna Industry
The next frontier for artificial intelligence may involve teaching computers to distinguish albacore tuna from its yellowfin cousin.
The Nature Conservancy, an environmental non-profit, is working with several Pacific Island nations and a big tuna fishing company to more easily count and identify fish caught at sea using cutting edge technology.
The goal is to use trendy artificial intelligence techniques like deep learning to help fishermen reduce the number of protected animals like sharks and turtles that are accidentally caught along with the tuna.
Derrick Wang, the vice president of Luen Thai Fishing, said that fishing operators in the Pacific Island region typically send a physical observer to accompany fishermen about 10 times out of 200 trips in a year.
The system can record most of what takes place on board to prove that the operators did nothing illegal and to back up any compliance data that they must present to officials when they deliver their catch.
Companies involved with the competitions typically submit a huge amount of data, like sales data in Walmart’s case, that researchers then use to build algorithms that can predict outcomes like when would a consumer be most likely to buy a computer in a store.
For the contest, Kaggle will give researchers access to the data set, with half of it containing the correctly labeled data and the other half scrubbed of the relevant information, Goldbloom said.
It will be up to researchers to build what’s known as convolutional neural networks, essentially software that loosely mimics how the brain learns, that they can then feed the image data into, he said.
Using the correctly labeled data as the source material, researchers can then construct an algorithm that would sift through the unlabeled data and try to identify the fish or other animals in the images.
But with the rapid advances in artificial intelligence technologies due in part to the rise of computing power and the amount of available data, Goldbloom is confident that researchers can build an algorithm that can at least count the correct number of fish in the pictures.
How AI Can Help Keep Ocean Fisheries Sustainable
“You’ve got to be able to translate that raw video data into useful information—that’s where we think machine learning can really help,”
Even if automated methods can’t completely replace human analysis, they can still provide a big benefit if they can reduce the amount of footage people need to review, saving time and potentially making it possible to transmit the video material more efficiently, Zimring says.
Right now, fishing boats participating in a voluntary pilot program are equipped with cameras and with hard drives that are periodically shipped to NOAA for human review, but the agency is developing sets of training data for machine learning algorithms to use, with an eye toward integrating automated classification around 2019.
The payoff could be even more substantial, as many of the tools, approaches and solutions being developed in the Pacific Islands are adapted and adopted by fisheries worldwide.
If retailers, restaurants and consumers are confident their seafood was caught legally and managed sustainably, many are more likely to buy solely from these highly transparent fisheries.
Wanted: artificial neural networks that can tell turtles from tuna, conservation-mindedness a plus
In one of the world’s last great high seas fisheries, the western and central tropical Pacific, it’s still a free-for-all.
It’s the first step by TNC to outfit all of the thousands of long-line tuna vessels in the tropical Pacific fleet with a suite of cameras and sensors, says Matt Merrifield, the chief technology officer at TNC of California. Within a few years, he wants to see 100% coverage. “We can’t manage these stocks efficiently if we don’t have the data,” said Merrifield in an interview.
Computer vision advances are allowing computers to recognize images of birds, name plant species, catalog rainforest species and even name individual whales.
CalTech researchers recently announced they were able to use satellite and street-level images (such as Google maps) to create inventory and identify 80,000 street trees with 80% accuracy.
To solve that challenge, the organization is sponsoring a $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.
The latest weapon in the fight against illegal fishing? Artificial intelligence
Facial recognition software is most commonly known as a tool to help police identify a suspected criminal by using machine learning algorithms to analyze his or her face against a database of thousands or millions of other faces.
The latest effort to use artificial intelligence to fight illegal fishing is coming from Virginia-based The Nature Conservancy (TNC), which launched a contest on Kaggle – a crowdsourcing site based in San Francisco that uses competitions to advance data science –earlier this week.
Inspectors, who currently spend up to six hours manually reviewing a single 10-hour fishing day, will then be able to go directly to those moments and check a fishing crew’s subsequent actions to determine whether they handled the bycatch legally – by making best efforts to return it to the sea unharmed.
Despite rules that call for government-approved auditors to be stationed on 5% of commercial fishing boats in the Western and Central Pacific, in practice the auditors are found only around 2% of the fishing boats, including tuna long liners.
The impact shows up many ways, including lost income for fishermen in the legal marketplace and harm to the tourist economy that sells snorkelers and divers the opportunity to witness protected species in the wild.
Using technology to track and prevent illegal fishing presents an opportunity for technology companies as the fishing industry seeks ways to comply with the growing demand for transparency from governments and consumers.
Whereas images from security cameras installed inside banks or other buildings are consistent and predictable, “the data from (electronic monitoring) cameras on boats is dirty, because the ships are always moving and the light keeps changing”.
Using data from a UN’s Food and Agriculture Organization report, PDS estimates that roughly 95% of those boats don’t have the types of communications and tracking radios that larger boats are required to have, partly because the boats are too small or lack the power source to run the radios.
The company sells its technology to governments, nonprofits, academic researchers and companies in the fishing industry, and expects the number of boats installed with its device to reach 1,000 in regions such as West Africa, North America and Mexico by the end of the year, Solomon says.
But its CEO, Anthony Goldbloom, thinks the TNC contest could represent the start of environmental competitions on its site because scientists from government agencies and academic institutions are collecting a growing amount of field data using cameras and sensors.
Bosworth argues that the advancement in core technologies behind things like multiplayer gaming software and smartphone apps has propelled the rise of machine learning and artificial intelligence and lowered the development costs over time.
- On 25. oktober 2021
Sustaining Food From the Seas
The world's oceans provide an important source of nutrition for more than one billion people, and employment for hundreds of millions. But is this sustainable?