{"id":66052,"date":"2018-11-30T14:55:04","date_gmt":"2018-11-30T14:55:04","guid":{"rendered":"https:\/\/news.microsoft.com\/?p=427830"},"modified":"2018-11-30T14:55:04","modified_gmt":"2018-11-30T14:55:04","slug":"fishy-business-putting-ai-to-work-in-australias-darwin-harbour","status":"publish","type":"post","link":"https:\/\/sickgaming.net\/blog\/2018\/11\/30\/fishy-business-putting-ai-to-work-in-australias-darwin-harbour\/","title":{"rendered":"Fishy business: Putting AI to work in Australia\u2019s Darwin Harbour"},"content":{"rendered":"
<\/header>\n

<\/p>\n

\n
\n

Identifying and counting fish species in murky water filled with deadly predators is a difficult job. But fisheries scientists in the Northern Territory are working on an artificial intelligence project with Microsoft that has incredible potential for marine science around the world.<\/h2>\n<\/p>\n<\/section>\n
<\/section>\n
\n
\n

Your mission should you choose to accept it, is to go into one of Australia\u2019s largest harbours and count the fish. Think this sounds daunting? You don\u2019t know the half of it.<\/p>\n

First, there\u2019s the water. There\u2019s a lot of it in Darwin Harbour \u2013 five times more than Sydney Harbour, to be precise. Heavy tides swell more than seven metres then retract, leaving little visibility in their wake.<\/p>\n

And if you think you\u2019ve got some occupational hazards at work, try getting your job done in an environment teeming with some of the world\u2019s most intimidating apex predators \u2013 saltwater crocodiles, along with tiger, bull and hammerhead sharks. More than 300 salties are caught in the harbour each year.<\/p>\n

This is the daunting task of the Department of Primary Industry and Resources for the Northern Territory Government, as it goes about ensuring fisheries resources are sustainably managed and developed for future generations.<\/p>\n<\/p><\/div>\n<\/section>\n

\"Identifying<\/p>\n

Murky water filled with deadly predators like the saltwater crocodile make diving to count and identify fish species impossible.<\/figcaption><\/p>\n<\/figure>\n
\n
\n
\n

\u201cIf you\u2019re in the water with a crocodile you aren\u2019t taking a calculated risk. You\u2019re going to be a statistic. That\u2019s it. If you\u2019re in the water and he\u2019s there, he wants you and you\u2019re gone.\u201d\u00a0\u2013\u00a0Wayne Baldwin, Research Technical Officer, NT Fisheries<\/strong><\/p>\n<\/blockquote><\/div>\n<\/figure>\n

\n
\n

If shooting fish in a barrel is a metaphor for something all-too-easy, the correct metaphor for something exceptionally challenging might be counting fish in Darwin Harbour. Yet the NT Fisheries team, led by Dr Shane Penny, Fisheries Research Scientist, do it every day. As the old saying goes, you can\u2019t manage what you can\u2019t measure, so their work begins with knowing how many fish there are.<\/p>\n

But they were bogged down by the time it took to wade through hours of underwater footage. The team needed to assess the abundance of critical fish species faster and more accurately, while maintaining a safe distance from deadly predators.<\/p>\n

A meeting of the minds<\/h3>\n

It was from these murky depths that an innovative project showed the potential for artificial intelligence (AI) to support the important work being done by this team of marine biologists. Amid rising debate about the potential impact of AI on society, a collaboration between these scientists and Microsoft engineers became an opportunity to test out its powers as a force for good. Could technology hold the key to safely, accurately and rapidly counting fish \u2013 giving the NT Fisheries team more time to devote to analysing this data and improving the sustainable management of NT fish stocks?<\/p>\n

The NT Fisheries team had high hopes. They had been using a baited remote underwater video (BRUV) to help with high-risk data gathering. The camera allows the team to see what\u2019s in the water without going in. But even with BRUV on their side, the task was formidable.<\/p>\n<\/p><\/div>\n<\/section>\n

\"Using<\/p>\n

Shane Penny, Fisheries Research Scientist and his team using baited underwater cameras.<\/figcaption><\/p>\n<\/figure>\n
\n
\n
\n

\u201cWe\u2019ve had quite a few problems with sharks coming in and taking the baits away. Tawny sharks have learned how to open our baits and suck it all out before we have a chance to collect any video.\u201d
\u2013\u00a0Wayne Baldwin, Research Technical Officer, NT Fisheries<\/strong><\/p>\n<\/blockquote><\/div>\n<\/figure>\n

\n
\n

Then there was the sheer quantity of work involved. Once the video is collected, terabytes of footage must be viewed, and its content scoured and quantified. To put this in perspective, a single terabyte would store 500-hours of your favourite movies. The team was identifying vast quantities of different fish species and tracking their behaviour. This diversity and the murkiness of the water meant classification was often far from simple.<\/p>\n

Steve van Bodegraven, a Microsoft machine learning engineer and Darwin local, worked with the NT Fisheries team over several months to see whether computer vision would be up to the ambitious task of identifying fish in underwater images.<\/p>\n

In a similar way to how tags are suggested for friends and relatives in the photos you upload to social media \u2013 through repeated exposure and the discovery of patterns \u2013 the project\u2019s success depended on feeding the system with training images. Along the way they had to confront an array of unusual problems. For example, how would Microsoft\u2019s AI solution respond to fish like gold-spotted cod that can change colour to blend into their environment?<\/p>\n

\u201cWe went in and talked to them about how they work and the challenges they face,\u201d van Bodegraven says. \u201cFrom that we tried to figure out how we could help. Everything we do is explorative, so we don\u2019t necessarily have solutions out of the box.\u201d<\/p>\n

Three months and thousands of images later, results are encouraging to the scientists. To date the system is showing great potential, having learnt to identify 15 different species, from black jewfish to golden snapper which are under careful management to rebuild breeding stocks.<\/p>\n<\/p><\/div>\n<\/section>\n

\"fisheries<\/p>\n

The AI solution automates the laborious process of counting local fish stocks by progressively learning to identify different varieties of fish.<\/figcaption><\/p>\n<\/figure>\n
\n
\n
\n

\u201cWe threw a few test images of fish it\u2019s never seen before and it\u2019s managed to pull those out and differentiate them from the fish it does know about.\u00a0Once we had that first positive identification of a fish, we really felt we were onto something. From there it was just a matter of finding the right tools to improve and optimise.\u201d
\u2013 Dr Shane Penny,\u00a0Fisheries Research Scientist<\/strong><\/p>\n<\/blockquote><\/div>\n<\/figure>\n

\n
\n

With each new fish analysed, the power of the machine learning technology increases. Samantha Nowland, the team\u2019s Darwin-born research assistant, sees the potential for such systems to change the game in marine management. \u00a0NT has some of the most pristine waters in the world with healthy populations of endangered species such as sawfish and sharks. The development of this technology and its availability may help other areas of the world to improve their understanding of aquatic resources and ensure they are managed sustainably.<\/p>\n

Beyond the harbour<\/h3>\n

While there\u2019s already talk of using the system to create a global database of fish species, the NT Fisheries team is focused on analysing trends, coming up with management plans and expanding its reach.<\/p>\n

\u201cIt\u2019s going to help us monitor any marine species in Darwin Harbour and around the region,\u201d Penny says. \u201cWe have a lot of endangered species and many more where we don\u2019t have enough data. We need research projects that can identify species accurately.\u201d<\/p>\n

Microsoft\u2019s van Bodegraven hopes it will open people\u2019s eyes to the transformative potential of AI in fisheries and marine management and beyond. The project has already piqued the interest of fisheries departments across Australia, while the possibility of using the technology to monitor other animal species, like the iconic Kookaburra, is being actively explored.<\/p>\n

Microsoft is also exploring how it could support similar projects elsewhere. By making the technology available via open source platform GitHub, the technology giant is encouraging others to build AI solutions that address their unique scenarios.<\/p>\n

\u201cProjects like this set a new precedent. Hopefully it will make people curious and give them the confidence to explore the application of AI in their industries,\u201d van Bodegraven says. \u201cIt\u2019s going to change industries and societies. The potential is only limited by imagination.\u201d<\/p>\n<\/p><\/div>\n<\/section>\n

\"Steve<\/figure>\n<\/div>\n
\n

More Stories<\/h2>\n<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"

Identifying and counting fish species in murky water filled with deadly predators is a difficult job. But fisheries scientists in the Northern Territory are working on an artificial intelligence project with Microsoft that has incredible potential for marine science around the world. Your mission should you choose to accept it, is to go into one […]<\/p>\n","protected":false},"author":2,"featured_media":66053,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[49],"tags":[135,415],"class_list":["post-66052","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-microsoft-news","tag-artificial-intelligence","tag-feature-stories"],"_links":{"self":[{"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/posts\/66052","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/comments?post=66052"}],"version-history":[{"count":0,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/posts\/66052\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/media\/66053"}],"wp:attachment":[{"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/media?parent=66052"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/categories?post=66052"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/tags?post=66052"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}