{"id":34858,"date":"2018-11-13T18:30:27","date_gmt":"2018-11-13T23:30:27","guid":{"rendered":"https:\/\/digital.hbs.edu\/platform-rctom\/submission\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\/"},"modified":"2018-11-13T18:52:33","modified_gmt":"2018-11-13T23:52:33","slug":"one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management","status":"publish","type":"hck-submission","link":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\/","title":{"rendered":"One Fish, Two Fish: How Machine Learning Can Enhance Fisheries Management"},"content":{"rendered":"

Abstract<\/strong><\/p>\n

This paper considers the impact of machine learning on fisheries management in the United States to date, how this technology can help regulators combat overfishing in the future, and finally, offers policy recommendations before posing a set of questions.<\/p>\n

Introduction<\/strong><\/p>\n

Overfishing threatens the long-term health of the world\u2019s fisheries and the billions of people they feed. The problem isn\u2019t new — each generation has contributed to the steady decline in global fish stocks — but it has never been more severe. Commercial fishing, a $150 billion dollar industry, has reduced the population of large predatory fish by 90% since 1950, and today, 87% of all fish stocks are fully or overexploited.[1]<\/a>\u00a0The ever-growing global demand shows no signs of slowing, driven by the 3.2 billion people who rely on fish for their primary source of protein, and the seemingly endless appetite for high quality seafood in upscale markets.[2]<\/a> If this continues, fish stocks and the fishing economy could collapse. Effective fisheries management, therefore, is a critical issue.<\/p>\n

 <\/p>\n

\"\"<\/a>
Source: UN FAO, \u201cThe State of World Fisheries and Aquaculture 2016\u201d (Rome, 2016). Pp 39, Figure 13.<\/figcaption><\/figure>\n

The National Oceanic and Atmospheric Administration (NOAA) manages U.S. fisheries, and a primary obstacle in that effort is a lack of reliable, comprehensive data.[3]<\/a> This limits their ability to construct models and set sustainable catch limits. Recently, the agency has turned to machine learning (ML) to make sense of otherwise impenetrable data. ML has already demonstrated its utility, and promises to enhance NOAA\u2019s ability to combat overfishing in the future.<\/p>\n

 <\/p>\n

 <\/p>\n

 <\/p>\n

 <\/p>\n

 <\/p>\n

 <\/p>\n

Mapping the Global Fleet<\/strong><\/p>\n

Earlier this\u00a0 year, Global Fishing Watch (GFW), a partnership between Google and two non-profit organizations, produced the first ever real-time map of the global fishing fleet. The program relies on two distinct types of machine learning — feature engineering and convolutional neural networks — to process over 22 billion data points (AIS satellite transmissions provided by NOAA).[4]<\/a> The algorithm can identify ships, their location and speed, and distinguish between different fishing practices.[5]<\/a> Without ML, processing so much data would have taken a full-time worker 100 years.[6]<\/a><\/p>\n

 <\/p>\n

\"\"<\/a>
Source: Global Fishing Watch, https:\/\/globalfishingwatch.org\/map\/<\/figcaption><\/figure>\n

Ultimately, an algorithm is only as good as its data set, and GFW\u2019s is not perfect or complete.<\/a>[7]<\/a> For example,\u00a0the map relies on AIS tracking data, but smaller inland ships do often not have AIS on board, and others turn off or mask their signals to circumvent government regulators.<\/a>[8]<\/a> Even if the map is not perfect or entirely comprehensive, it provides NOAA with an entirely new monitoring capability, and demonstrates the transformational potential of ML for fisheries management.<\/p>\n

 <\/p>\n

 <\/p>\n

 <\/p>\n

Counting and Identifying Species<\/strong><\/p>\n

No one knows how many fish are in the sea, as they are quite hard to count.[9]<\/a> Since it began estimating population sizes in 1960, NOAA has relied on methods which require taking fish out of the water in order to count and identify them.[10]<\/a> This is outdated, inefficient, inaccurate and expensive, but still widely used. [11]<\/a> New technologies, however, offer a better alternative. Recently, NOAA has deployed new electronic monitoring devices (cameras, acoustic and electronic imaging tools) in pilot programs across the country. The biggest cost associated with each is not hardware, but rather the labor required to analyze the data, so NOAA turned again to ML for help.[12]<\/a> In 2016, they released data collected from a pilot program in New England, which replaced human observers with cameras.[13]<\/a>\u00a0They then co-sponsored an online competition offering a $50,000 cash prize, which generated ML algorithms that counted and identified fish with 100% and 75% accuracy, respectively.[14]<\/a> Other ML projects have had similar success in identifying species using different visual data inputs.[15]<\/a><\/p>\n

As digital observation methods become more widespread and the dataset on catch yields expands, ML can help NOAA answer fundamental questions about the state of the ocean and more effectively manage threatened species. \u00a0Ultimately, however, though this technology holds promise, it is not yet sophisticated enough to provide a true representation of ecological health due to the complexity and overwhelming number of variables at work in any environmental system.[16]<\/a> To be sure, there is much work to be done before ML is robust enough to accomplish that task.[17]<\/a><\/p>\n

Recommendations<\/strong><\/p>\n

To harness the power of machine learning to combat overfishing and promote sustainability, NOAA must collect more data and share it \u00a0widely. To the extent its budget allows, NOAA should (1) deploy new monitoring systems whenever possible, (2) begin crowdsourcing digital images to expand their dataset, (3) promote increased information sharing between agencies, governments and the public, and (4) continue partnering with groups that can provide innovative ML technology. \u00a0All this will enhance NOAA\u2019s understanding of our ocean and how to protect its natural resources.<\/p>\n

Questions<\/strong><\/p>\n

    \n
  1. To what extent might bad actors use more science to further exploit fisheries?<\/li>\n
  2. What can individuals do to combat overfishing?<\/li>\n<\/ol>\n

    Word count: 790<\/p>\n

     <\/p>\n

    Footnotes<\/strong><\/p>\n

    [1]<\/a> [1]United Nation Food and Agriculture Organization, Fisheries and Aquaculture Department, \u201cThe State of the World Fisheries and Aquaculture,\u201d (2012). http:\/\/www.fao.org\/docrep\/016\/i2727e\/i2727e00.htm<\/a>,<\/p>\n

    Andrew Revkin, \u201cCommercial Fleets Reduced Big Fish by 90%, Study Finds,\u201d The New York Times<\/em>, (2003). https:\/\/www.nytimes.com\/2003\/05\/15\/world\/commercial-fleets-reduced-big-fish-by-90-study-says.html<\/a><\/p>\n

    [2]<\/a> The World Bank, \u201cBrief: Oceans, Fisheries and Coastal Economies,\u201d (2018), http:\/\/www.worldbank.org\/en\/topic\/environment\/brief\/oceans<\/p>\n

    [3]<\/a> Adam Allington, \u201cPlenty of Fish in the Sea for Big Data, AI to Tackle,\u201d Bloomberg News<\/em>, (August, 2018). https:\/\/www.bna.com\/plenty-fish-sea-n73014481426\/<\/p>\n

    [4]<\/a> Global Fishing Watch, Research, \u201cWhat We Do,\u201d (2018). https:\/\/globalfishingwatch.org\/research\/<\/p>\n

    [5]<\/a> Ibid.<\/p>\n

    [6]<\/a> Ashley Marranzino, \u201cHow Machine Learning Reveals the True Costs of High-Seas Fishing,\u201d Massive Science,<\/em> (2018), https:\/\/massivesci.com\/articles\/international-fishing-management-practices-tracked\/<\/p>\n

    [7]<\/a> Yeomans.\u00a0\u201cWhat every manager should know about machine learning<\/strong>,\u201d<\/u>.\u00a0Harvard Business Review Digital Articles<\/em>\u00a0(July 7, 2015).<\/p>\n

    [8]<\/a> Nicolas\u00a0Long\u00e9p\u00e9,\u00a0et al. \u201cCompleting fishing monitoring with spaceborne Vessel Detection System (VDS) and Automatic Identification System (AIS) to assess illegal fishing in Indonesia\u201d<\/p>\n

    Marine Pollution Bulletin, Volume 131, Part B, 2018, pp. 33-39<\/p>\n

    [9]<\/a> Nicole Twilley, et al., \u201cHow Many Fish Are in the Sea?\u201d, The Atlantic<\/em>, (October 5, 2016), https:\/\/www.theatlantic.com\/science\/archive\/2016\/10\/how-many-fish-are-in-the-sea\/502937\/<\/p>\n

    [10]<\/a> Ibid.<\/p>\n

    [11]<\/a> National Oceanic and Atmospheric Administration, Department of Fisheries, \u201cDeveloping Machine Vision to Collect More Timely Fisheries Data,\u201d (May, 2018).<\/p>\n

    https:\/\/www.fisheries.noaa.gov\/feature-story\/developing-machine-vision-collect-more-timely-fisheries-data<\/a>,<\/p>\n

    Adam Allington, \u201cPlenty of Fish in the Sea for Big Data, AI to Tackle,\u201d Bloomberg News<\/em>, (August, 2018). https:\/\/www.bna.com\/plenty-fish-sea-n73014481426\/<\/p>\n

    [12]<\/a> Meg Wilcox, \u201cThe Future of Fishing is Big Data and Artificial Intelligence,\u201d PRI<\/em>, (May, 2018). https:\/\/www.pri.org\/stories\/2018-05-10\/future-fishing-big-data-and-artificial-intelligence<\/a><\/p>\n

     <\/p>\n

    [13]<\/a> Ibid<\/p>\n

    [14]<\/a> Ibid.<\/p>\n

    [15]<\/a> Ibid.<\/p>\n

    [16]<\/a> Simone Marini, et al, \u201cTracking Fish Abundance by Underwater Image Recognition,\u201d Nature<\/em>, (September, 2018).<\/p>\n

    [17]<\/a> Ibid.<\/p>\n","protected":false},"excerpt":{"rendered":"

    Overfishing has decimated global fish stocks and threatens food security for billions down the line, but machine learning helps regulators meet this urgent challenge with new capabilities and better science.<\/p>\n","protected":false},"author":11364,"featured_media":0,"comment_status":"open","ping_status":"closed","template":"","categories":[1230,346],"class_list":["post-34858","hck-submission","type-hck-submission","status-publish","hentry","category-fisheries","category-machine-learning","hck-taxonomy-organization-national-oceanic-and-atmospheric-administration","hck-taxonomy-industry-agriculture-and-agribusiness","hck-taxonomy-country-united-states"],"connected_submission_link":"https:\/\/d3.harvard.edu\/platform-rctom\/assignment\/rc-tom-challenge-2018\/","yoast_head":"\nOne Fish, Two Fish: How Machine Learning Can Enhance Fisheries Management - Technology and Operations Management<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"One Fish, Two Fish: How Machine Learning Can Enhance Fisheries Management - Technology and Operations Management\" \/>\n<meta property=\"og:description\" content=\"Overfishing has decimated global fish stocks and threatens food security for billions down the line, but machine learning helps regulators meet this urgent challenge with new capabilities and better science.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\/\" \/>\n<meta property=\"og:site_name\" content=\"Technology and Operations Management\" \/>\n<meta property=\"article:modified_time\" content=\"2018-11-13T23:52:33+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/d3.harvard.edu\/platform-rctom\/wp-content\/uploads\/sites\/4\/2018\/11\/Screen-Shot-2018-11-13-at-1.22.03-PM-1024x727.png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\\\/\",\"url\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\\\/\",\"name\":\"One Fish, Two Fish: How Machine Learning Can Enhance Fisheries Management - Technology and Operations Management\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2018\\\/11\\\/Screen-Shot-2018-11-13-at-1.22.03-PM-1024x727.png\",\"datePublished\":\"2018-11-13T23:30:27+00:00\",\"dateModified\":\"2018-11-13T23:52:33+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\\\/#primaryimage\",\"url\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2018\\\/11\\\/Screen-Shot-2018-11-13-at-1.22.03-PM.png\",\"contentUrl\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2018\\\/11\\\/Screen-Shot-2018-11-13-at-1.22.03-PM.png\",\"width\":1380,\"height\":980},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Submissions\",\"item\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"One Fish, Two Fish: How Machine Learning Can Enhance Fisheries Management\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/#website\",\"url\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/\",\"name\":\"Technology and Operations Management\",\"description\":\"MBA Student Perspectives\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"One Fish, Two Fish: How Machine Learning Can Enhance Fisheries Management - Technology and Operations Management","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\/","og_locale":"en_US","og_type":"article","og_title":"One Fish, Two Fish: How Machine Learning Can Enhance Fisheries Management - Technology and Operations Management","og_description":"Overfishing has decimated global fish stocks and threatens food security for billions down the line, but machine learning helps regulators meet this urgent challenge with new capabilities and better science.","og_url":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\/","og_site_name":"Technology and Operations Management","article_modified_time":"2018-11-13T23:52:33+00:00","og_image":[{"url":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-content\/uploads\/sites\/4\/2018\/11\/Screen-Shot-2018-11-13-at-1.22.03-PM-1024x727.png","type":"","width":"","height":""}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\/","url":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\/","name":"One Fish, Two Fish: How Machine Learning Can Enhance Fisheries Management - Technology and Operations Management","isPartOf":{"@id":"https:\/\/d3.harvard.edu\/platform-rctom\/#website"},"primaryImageOfPage":{"@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\/#primaryimage"},"image":{"@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\/#primaryimage"},"thumbnailUrl":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-content\/uploads\/sites\/4\/2018\/11\/Screen-Shot-2018-11-13-at-1.22.03-PM-1024x727.png","datePublished":"2018-11-13T23:30:27+00:00","dateModified":"2018-11-13T23:52:33+00:00","breadcrumb":{"@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/d3.harvard.edu\/platform-rctom\/submission\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\/#primaryimage","url":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-content\/uploads\/sites\/4\/2018\/11\/Screen-Shot-2018-11-13-at-1.22.03-PM.png","contentUrl":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-content\/uploads\/sites\/4\/2018\/11\/Screen-Shot-2018-11-13-at-1.22.03-PM.png","width":1380,"height":980},{"@type":"BreadcrumbList","@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/one-fish-two-fish-how-machine-learning-can-enhance-fisheries-management\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/d3.harvard.edu\/platform-rctom\/"},{"@type":"ListItem","position":2,"name":"Submissions","item":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/"},{"@type":"ListItem","position":3,"name":"One Fish, Two Fish: How Machine Learning Can Enhance Fisheries Management"}]},{"@type":"WebSite","@id":"https:\/\/d3.harvard.edu\/platform-rctom\/#website","url":"https:\/\/d3.harvard.edu\/platform-rctom\/","name":"Technology and Operations Management","description":"MBA Student Perspectives","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/d3.harvard.edu\/platform-rctom\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/hck-submission\/34858","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/hck-submission"}],"about":[{"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/types\/hck-submission"}],"author":[{"embeddable":true,"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/users\/11364"}],"replies":[{"embeddable":true,"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/comments?post=34858"}],"version-history":[{"count":0,"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/hck-submission\/34858\/revisions"}],"wp:attachment":[{"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/media?parent=34858"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/categories?post=34858"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}