Taking the “Secret” out of Rendezvous at Sea

In January, SkyTruth reported on our work with DigitalGlobe to identify and photograph refrigerated cargo vessels (reefers) in the Western Indian Ocean. The goal was to capture high-resolution images of vessels that our analyst had painstakingly targeted for suspicious behavior by monitoring and analyzing their movements based on signals from their Automatic Identification System (AIS) broadcasts. We targeted reefers because they are key to transshipment—they receive catch transferred from multiple fishing vessels and carry it to port. The practice, called transshipment, saves fishing vessels time and fuel, but it is illegal in many cases because it can enable illegally caught fish to be mixed with legal catch.

The images DigitalGlobe acquired in November revealed multiple instances of reefers in rendezvous with other vessels, including fishing vessels. Now, in collaboration with Global Fishing Watch, SkyTruth data scientists have made the job of targeting reefers much easier. Together, the team has developed an artificial intelligence system capable of identifying and tracking transshipments around the world by following reefers and classifying their movements. An analysis of 21 billion AIS signals from ships at sea has created the first-ever global map of transshipment.

Today, SkyTruth and Global Fishing Watch are publishing those results in a new report: The Global View of Transshipment: Preliminary Findings. According to our analysis, from 2012 through 2016, there were more than 86,490 potential transshipments in which reefers exhibited the slow movements indicative of transshipment. Of those, 5,065 were likely transshipments because they included a rendezvous with an AIS-broadcasting fishing vessel — meaning they traveled at a specified slow speed in close proximity to one another for a certain length of time that indicated a likely transshipment.

This image of the reefer Hai Feng 648 with an unidentified fishing vessel off the coast of Argentina is just one of the images acquired on Nov 30, 2016 in collaboration with DigitalGlobe. (DigitalGlobe © 2017)

Like most activity that occurs on the ocean, transshipment has been hidden from the world. This report shines a new light over the horizon, revealing the extent and magnitude of transshipment. Based on the data generated by SkyTruth and Global Fishing Watch during this project, our partners at Oceana are publishing a complementary report today that highlights the global scale of transshipment and its complicity in illegal fishing and human rights abuses. The report identifies hotspots of transshipment and the ports that reefers visit, exposing associations between transshipment and illegal, unregulated and unreported (IUU) fishing activity.

The refrigerated cargo vessel (reefer) Leelawadee seen on November 30, 2016 with two unidentified likely fishing vessels tied alongside was featured in our post on January 16. (DigitalGlobe © 2017)

Oceana’s report calls for the banning of transshipment at sea, expanded mandates for unique identifiers and vessel tracking for fishing vessels. Currently AIS is not required on all vessels, and fishing vessels engaged in illegal activity are known to turn off their AIS when they don’t want to be seen. Having access to high-resolution satellite imagery is a game-changer when it comes to illuminating these rendezvous, especially when only one of the vessels is broadcasting AIS. That’s why we are thrilled to be working with the folks at DigitalGlobe, who are donating time and imagery from their powerful WorldView satellites to demonstrate that we can systematically shine a spotlight on these transshipment events at sea. In partnering with SkyTruth, DigitalGlobe shows how corporations and nonprofits can join together to solve some of the world’s thorniest problems.

 

Mystery Moves: What is the Chinese Squid Fleet Doing in the Pacific?

Over the past couple of months, SkyTruth analyst Bjorn Bergman has been watching some interesting activity by the Chinese fishing fleet in the Pacific. A large Chinese flagged squid-fishing fleet had been fishing at the boundary of Peru’s exclusive economic zone (EEZ) throughout the summer and fall of 2016. Then, near the middle of December, many of them suddenly began migrating some 3,000 miles to the northwest.

At their new location, around 118 degrees West longitude and just north of the equator, they met up with another group of Chinese-flagged vessels. These vessels had just moved to this remote part of the Pacific about a week or two earlier. Some arrived from China and Indonesia, and some came directly from fishing just outside the Japanese EEZ.

This screen shot from the Global Fishing Watch map shows the movement of 55 Chinese flagged vessels from early November 2016 through February 5, 2017. You can see vessels moving to a single location around 118 degrees West longitude from the western Pacific (red tracks), and from the squid fishing grounds just outside the Peru EEZ (blue tracks). Some vessels off the Peru EEZ also moved south to Argentina. You will find a link to see these tracks on the live map at the bottom of this post.

This nighttime VIIRS imagery from the Suomi-NPP satellite, taken on January 29, shows the lights of Chinese squid fishing vessels in the Pacific.

When fishing for squid, fishers use powerful lights to attract the animals to the surface for an easy catch. This nighttime VIIRS imagery from the Suomi-NPP satellite, taken on January 29, 2017, shows the lights of Chinese squid fishing vessels off of Peru, and at the new location in the middle of the Pacific.

The same pattern is seen using satellite signals from fishing vessels.

This the Global Fishing Watch heat map shows the AIS signals from fishing vessels from January 9 to February 2, 2017. With one fishing track defined in blue, we can see the path of the Chinese squid fleet moving from just outside the Peru EEZ to a location on the high seas.

This Global Fishing Watch heat map shows the AIS signals from fishing vessels from January 9 to February 2, 2017. With one fishing track defined in blue, we can see the path of the Chinese squid fleet moving from just outside the Peru EEZ to a location on the high seas.

The new location of these vessels is not known for squid. It is also an unlikely habitat as squid usually live near continental shelves and canyons where there are steep changes in water depth. It’s unclear what the vessels are fishing for now, but the sudden move from the eastern Pacific may be a reflection of a dwindling catch.

Usually Chinese flagged squid fishers operating around South America concentrate off of Peru in the Pacific and Argentina in the Atlantic Ocean. For the past few years, some squid-fishing fleets have seen their catch decline in both regions.  Undercurrent News reports that some Taiwanese boat captains abandoned squid altogether because of low catch. They are now targeting Pacific saury (mackerel pike), which is found in the north Pacific.

Perhaps the Chinese fleet around South America has also given up on catching squid. We noted that when many of the Chinese vessels off Peru began moving to the northwest, some of them turned south, headed for Argentina, but according to Undercurrent, Chinese captains who moved to Argentina said they wish they had stayed in Peru because the catch was so bad.

The fleet that stayed in Peru may not have fared much better. By February 7, only three Chinese squid-fishing vessels remained in that location. Why so many have moved some 3,000 km to the northwest, and what they’re fishing for now remains a mystery to us. Whatever it is, it’s also drawn a crowd of Chinese vessels from the western Pacific. We checked in with the Southern Pacific Regional Management Organization that has jurisdiction over the area, and even they are not sure what the sudden change in location by this fleet means. 

We would be very interested to hear from anyone who can help explain it.

Click here to see these vessels on the Global Fishing Watch Map where you can manipulate the time frame, zoom in, add vessels. Note: you will need to be registered to access the map (it’s free). If you are already a registered user, and the map link isn’t working, please log in then copy the link into your browser. http://globalfishingwatch.org/map/workspace/udw-627b8ae0-02f3-4fd1-b080-119462b69c8c 

Satellites Leave No Place to Hide for Rogue Thai Fishing Fleet

Despite a dearth of monitoring and law enforcement in the remote Saya de Malha bank, there’s nothing secret about what’s going on in this distant area of the Indian Ocean east of Madagascar.

Last month, Greenpeace published a report asserting that a significant number of Thai fishing vessels have repeatedly moved their operations, which were shown to include illegal fishing and human trafficking, to evade detection and capture, and that they may now be acting with impunity on the Saya de Malha bank more than 7,000 km from their home port in Thailand.

As we know, seeing is believing, and in collaboration with DigitalGlobe, we have obtained high-resolution satellite images that corroborate Greenpeace’s assertions and reveal just how active the fleet is. Since November, we have documented Thai vessels gathering in one specific location on the Saya de Malha bank for the apparent transfer of fish.

The report, “Turn the Tide: Human Rights Abuse and Illegal Fishing of Thailand’s Overseas Fishing Industry,” outlines the Thai fleet’s exodus: first from their staple fishing grounds in Indonesian waters to a remote region off of Papua New Guinea, then to the Saya de Malha Bank. The evasive moves correspond to the hardline stance against illegal fishing by Indonesia in 2014 that included blowing up illegal vessels, and to subsequent increases in enforcement by Papua New Guinea in August of 2015.

The imagery we’ve captured from Saya de Malha Bank is part of a larger effort to gather high resolution satellite imagery of ocean surface around refrigerated cargo vessels in different parts of the world. With their large carrying capacity, these refrigerated vessels, called “reefers,” collect catch from multiple fishing vessels for transport to shore.

Not only does this type of transshipment allow the fishing fleet to continue working the fishing grounds for months, or even years at a time, but it facilitates the mixing of legal and illegal catch, which is why it is prohibited in many circumstances. What’s more, fishing vessels that remain at sea almost indefinitely have greater potential for abusive labor practices, including the enslavement of crew. The move by the Thai fleet to Saya de Malha almost requires the use of reefers as an efficient way of transporting catch to the home port from such distant fishing grounds.

Using AIS signals from known reefer vessels, we identified precise locations for aiming DigitalGlobe’s satellite sensors. With the knowledge that fishing vessels often don’t broadcast AIS while engaged in illegal activities such as unauthorized transshipment, we were interested in finding out if we could capture suspect vessels using imagery in the vicinity of a reefer.

One of the reefers we chose for imaging, the Thai vessel Leelawadee, seemed a good target. “I saw that it was stopped at the north end of the bank,” says our analyst Bjorn Bergman. “It’s in a location where it may be shallow enough to anchor.” In addition, Bjorn had documented a possible transshipment between the Leelawadee and an unnamed vessel in 2015. That event was documented using AIS data as part of SkyTruth’s assistance with the investigation by the Associated Press into Thai vessels fishing with trafficked and enslaved crews.  It is no surprise that it occurred in the waters of Papua New Guinea.

The first image of Leelawadee on the Saya de Malha bank was captured on Nov 23, 2016. It showed her alongside a refueling vessel, the Mahachai Marine 1.  Refueling at sea, also known as “bunkering,” is another necessity for fishing vessels operating far from their home ports for extended periods of time.

Leelawadee reefer (larger vessel) tied to bunkering vessel Mahachai Marine 1. (DigitalGlobe)

Seven days later, on the November 30, the satellite captured five vessels in one pass: the Leelawadee with two vessels tied alongside her and a vessel tied to the stern of the Mahachai Marine 1 (see images below). Although the three unknown vessels appear to be fishing boats, none were broadcasting AIS signals.

The refrigerated cargo vessel (reefer) Leelawadee with two unidentified likely fishing vessels tied alongside. Captured by DigitalGlobe on November 30, 2016. (DigitalGlobe)

Refueling vessel, Mahachai Marine 1, with unidentified vessel tied astern. (DigitalGlobe)

Since we began our efforts to target imaging satellites on reefers, we have turned up several similar “dark” fleets of fishing vessels in other parts of the Indian Ocean and the Atlantic. Combined with AIS data, we are able to flesh out an even more complete picture of what these vessels are doing. In the case of the Leelawadee, AIS-derived tracks over four years indicate that she has made repeated trips between Thailand and an area inside Papua New Guinea’s exclusive economic zone known as The Dogleg, a poorly monitored, remote region rife with suspected illegal activity. Our data reveals many instances in which vessels have crossed from Indonesian waters into the Dogleg, likely to transship their catch. On July 29, 2015, the Leelawadee rendezvoused for many hours with an unnamed fishing vessel broadcasting an irregular AIS number not tied to a vessel identity.

Then in November 2016, both vessels met again, this time on the Saya de Malha bank. They spent several hours together, indicating a possible transshipment. That rendezvous occurred hours after we captured the photograph of the Leelawadee with two “dark” vessels tied alongside, and right before she left the area on a northeasterly course back to port in Thailand.

Track of the Leelawadee (red) and an unnamed fishing vessel (white) rendezvousing in Papua New Guinea waters in July 2015, then again on the Saya de Malha bank in November 2016.

“That both vessels were seen in the Dogleg, and have now moved to the Saya de Malha Bank provides tangible evidence to support the Greenpeace report” says Bjorn. “And what’s interesting is the pattern is similar to the situation we saw with the AP investigation where these Thai reefers would return again and again to one particular location.” It’s worth noting that the encounter between the Leelawadee and the unnamed vessel that occurred in the Dogleg also followed a transshipment that was photographed in the same location by DigitalGlobe. That photograph led to the capture of the reefer Silver Sea 2, which reportedly had been receiving catch from fishing vessels with enslaved crew.  [Read our earlier post on this investigation.]

Press roundup from the public launch of Global Fishing Watch

ourocean-prelaunch-14sep2016

Last month marked a big moment for SkyTruth: the public launch of Global Fishing Watch (GFW) with our partners Google and Oceana at the State Department brought an avalanche of great press that we’re excited to share with all you skytruthers.

The UK’s Daily Mail covers Leonardo DiCaprio’s interest in and support of the project. Read Leo’s remarks and Secretary Kerry’s introduction via the State Department transcript here. Scientific American gives our algorithm some props. The New York Times’ Andrew Revkin urges readers to register and explore GFW directly. See how the Washington Post places GFW in the context of broader ocean conservation efforts. Noted enviro reporter Chris Pala gives readers a glimpse of our work with research partners. Vox highlights the potential of GFW and gives a nod to SkyTruth’s past successes using satellite mapping. Find out about the way GFW can harness market forces to encourage more responsible fishing practices from Lauren Williams at ThinkProgress. Ted Danson gives SkyTruth and GFW some love on the Rachael Ray show (second video — good stuff starts around the 2:20 mark).

And this is just a sampling. All in all we had over 200 unique hits in press outlets around the world, creating a surge of interest not just in SkyTruth and in Global Fishing Watch but moreover in the power of sharing technology with the public to solve big environmental problems. Our team worked hard with our partners to make this moment possible. We will be growing and improving Global Fishing Watch in the months to come. In the meantime, we’ll be chewing on the question: what’s the Next Big Thing? Stay tuned.

Global Fishing Watch Goes Live

SkyTruth is helping make the world’s oceans a little less mysterious and a great deal more transparent with the public beta release of Global Fishing Watch, announced today at the Our Ocean Conference in Washington, DC. Actor and ocean advocate Leonardo DiCaprio announced in his remarks to the conference that Global Fishing Watch is now free and open to the public, and U.S. Secretary of State John Kerry personally received a demonstration of the tool from the Oceana, SkyTruth, and Google team.

In partnership with Oceana and Google, Global Fishing Watch was designed, developed, and tested by SkyTruth to enable users to map and analyze all of the world’s trackable commercial fishing activity. Global Fishing Watch is the world’s first dynamic, global, near real-time measure of fishing activity.

SkyTruth is proud to make this tool available to the public, enabling researchers, advocates, regulators, consumers, and industry to shine a light on fishing activity and pierce the fog of uncertainty surrounding global seafood supply chains.

fleets

Above: With Global Fishing Watch, users will easily be able to visualize when and where fishing activity occurs. This visualization depicts six months of fishing activity by three of the world’s most prolific fleets – fishing vessels flagged to China, Japan, and Spain.

Our oceans are under pressure from overfishing, and recent stories about crime on the high seas have riveted the public’s attention. Global Fishing Watch gives legal operators a way to show the world they’re playing by the rules and that they deserve access to premium seafood markets. Global Fishing Watch provides regulators with an easy way to visualize their own data, and GFW will empower citizens and indigenous peoples to hold regulators accountable for enforcing the rules.

Oceana, SkyTruth, and Google unveiled the prototype in November 2014 at the IUCN World Parks Congress in Sydney, Australia. Today, Global Fishing Watch unlocks the power of machine-learning, mapping, and a near real-time feed of satellite data to anyone with a modern computer and decent internet connection.

When Vessels Report False Locations

Lu Yan Yuan Yu 10 TPY9 offset GE inset logo

The red tracks show the broadcast position of the Lu Yan Yuan Yu 10 apparently transiting across Antarctica (inset). The yellow tracks show its true location along the coast of South America passing through the Strait of Magellan and into port at Lima, Peru.

Occasionally, the AIS messages transmitted from a ship provide a location that makes no sense, say, in the middle of the Antarctic or over a mountain range. In such cases, either the AIS transponder has malfunctioned, the data got scrambled in transmission, or the system has been tampered with in a deliberate attempt to disguise the vessel’s location. Read more

Scientists develop precise methods to identify and measure three very different types of fishing activity

Scientists develop precise methods to identify and measure three very different types of fishing activity

Scientists develop precise methods to identify and measure three very different types of fishing activity

On dry land, ecologists and conservationists can map our human footprints on the landscape. We can see deforestation, mountaintop removal, river damming and development, and it is relatively easy to recognize our impacts on an ecosystem and the plants and animals that live there.

In the ocean, our impacts are less tangible. Water covers more than 70 percent of the surface of the globe and its resources are exploited as vigorously as those on land. Yet our footprints are lost to the ripples and waves. The effects of our exploits lie beneath the surface in a three-dimensional, liquid “landscape” that remains out of sight and far from reach.

Satellite tracking technology and big-data processing are helping solve that problem by allowing us to see and record the tracks of ships on the ocean. This week, a new study released in the journal PLoS ONE brings finer resolution to our newly developing view of how humans are using the seas. Researchers from Dalhousie University in Halifax, Nova Scotia have developed distinct methods for identifying the activity of vessels fishing with three different types of gear.

Commercial fishing vessels regularly broadcast their positions to satellites via an Automatic Identification System (AIS). By plotting these signals on a map of the ocean we can recreate their tracks and identify movement or behavior consistent with fishing. Until now, remote sensing methods have provided only a broad or incomplete view of fishing behavior.

The broad view, which tries to capture all fishing activity without considering the type of gear being used, is somewhat like trying to quantify land-based farming for a given area without distinguishing between livestock, row-crops or orchard farming.

There has also been work to develop more fine-scale views that focus in on a specific type of fishing. Previous studies have looked at trawling, for instance. While this work is significant, it doesn’t allow for a comprehensive view of fishing activity. Again, to take an analogy from the land, analyzing wheat farms doesn’t allow us to make conclusions about land use relative to all farming.

This new work allows researchers to take a comprehensive look at how fishers use the oceans by combining fine-scale analyses of three of the most common types of fishing, trawling, longlining and purse seining. It also allows them to see the amount of time spent actually fishing as opposed to something else such as transiting or hanging at anchor.

“We’re very much aware of the differences of the gear types, and we’ve tailor made our algorithms for that so we can really tell what is happening out there,” says Kristina Boerder, one of our academic partners and an author on the paper. “Because all three algorithms were developed in one place to fit into the same framework, it is the first opportunity to run these analyses all together.”

According to Elizabeth Madin, researcher from Macquarie University in New South Wales Australia, this work helps to fill critical gaps in the scientific understanding of how and where fishing is occurring on the high seas. “It’s something that’s been notoriously difficult to quantify over large scales with any accuracy in the past,” she says. “Perhaps equally importantly, this study improves our ability to harness the full power of the vast dataset of fishing patterns globally that has emerged through the use of satellite AIS technology. Marine scientists and ocean resource managers will find this incredibly valuable.

To develop their tools, Kristina and her team analyzed satellite-based AIS tracks from 2011 to Oct 2015. They looked at characteristics such as speed, changes in direction, how a vessel moves, and how long it engages in certain types of movement. Some characteristics were more important than others in identifying each type of gear. So in order to automate the identification process, they had to take a different approach for each fishing method.

For trawlers, they applied a machine learning approach. They fed a computer thousands of examples of trawling vessel tracks (millions of individual AIS signals) and asked the computer to identify patterns among those tracks. Having established the set of rules to define trawler patterns, the computer could then apply those rules to unidentified tracks and pick out trawling behavior.

Purse seiner behavior is distinct in that vessels move very quickly in a circle around a school of fish to set the net, then move very slowly for a period of time, drifting as they haul up their nets. For these vessels, the researchers applied a filtering process by which, step-by-step, the computer eliminated behavior that did not fit with the behavior of pulling up the net. By re-evaluating after each filter, and applying the next level of elimination, the algorithm narrowed in on purse seine fishing events with 97 percent accuracy.

Longliners posed a slightly different challenge because speed was not as relevant to longlining as it was to the other two gear types. In this case, the researchers used a data mining technique and applied methodology from land-based ecologists who study animal movements. Other work has shown that human fishing activity resembles that of animals searching for and hunting prey. “If an animal spends a lot of time in one confined area,” Kristina says, “there has to be something of interest there—they could be sleeping, or foraging, or hiding.” Longliners offer the same clues by spending a lot of time traveling back and forth over the same territory as they set and retrieve their lines and hooks.

Kristina says the team fed AIS signals into their computer and asked the computer to mine the data and pull out tracks that met a certain set of expectations for what longliner fishing behavior over time and space looked like. Evaluating each vessel track, the computer took note when a vessel began to behave according to the expectations given. It then applied the next level of expectations, highlighting tracks that met those, and re-evaluated again. This is the first time an automated process has been developed to identify fishing activity of longliners.

The new Dalhousie algorithms can be a game changer for fisheries management and conservation, especially in combination with Global Fishing Watch’s list of individual fishing vessels, which helps identify the species of fish being harvested. Knowing where and when a given species is being taken from the ocean allows for a much better assessment of fisheries management on a global scale.

Researchers will be able to study more precisely how human activity overlaps with such things as migration patterns of tuna, nursery areas for sharks, or ecosystems surrounding marine protected areas. “It is a tailor-made approach that can be used to search and evaluate fishing effort for any fleet anywhere in the world,” says Kristina. “We hope that other researchers and ocean managers will use our tools to further their work. It opens the door to a whole host of research questions that couldn’t be asked before.”