Internet of Birds: Harnessing AI for Bird Tracking, Conservation
July 27th, 2020
Via CXO Today, a look at how the Internet of Things may be used to support bird conservation:
India is a biodiversity hotspot and home to over 1300 species of birds. While, these beautiful creatures are vital in maintaining the overall ecological balance, their natural habitats are increasingly under threat. A recent report, State of the World’s Birds 2018, found that one in eight birds is in danger of extinction, and 40% of the world’s 10,000+ species are declining thanks to climate change, logging, industrial farming and various other factors. Hence there is a pressing need to build an impactful and scalable conservation model, so as to engage more people, organizations and communities working in this space.
Realizing the urgency to identify and preserve birds as well as spread awareness in this area, IT consultancy firm Accenture has developed an Artificial Intelligence (AI)-based Birds platform – a first of its kind in India – that identifies bird species found in the country, in association with the Bombay Natural History Society (BNHS), a non-governmental wildlife research organization.
In an engaging conversation with CXOToday, Sanjay Podder, Managing Director at Accenture Labs (Asia Pacific) explains the technology and the rationale behind this initiative.
“We realized that most people find it difficult to identify rare birds unless they are experts or have read books on ornithology. While our country is home to a spectacularly diverse set of birds, it lacked a large centralized repository to help amateur bird lovers and conservationalists accurately identify them. This is when Accenture Labs started working with BNHS to design and develop the Internet of Birds platform,” he says.
Based in Mumbai, BNHS has been working on nature conservation and research projects in the sub-continent for the last 136 years. Launched initially as a web portal, Accenture has recently launched a mobile application for BNHS, which extends the functionality of the platform to mobile devices. The Internet of Birds platform initially identified nearly 100 species of birds in India, and can now identify nearly 700.
On the technology behind the concept, Podder says, “Internet of Birds is a cloud-based, image recognition and deep learning platform which uses AI, including machine learning and computer vision. The platform has been trained on birds found in the Indian subcontinent using a convolutional neural network, which is a deep learning algorithm that can take in an image and assign importance to various aspects in the image, with the ability to differentiate between images.”
He adds that it also uses a unique citizen crowd sourcing approach under which bird watchers can contribute to the platform by uploading information on rare birds that they come across. Data from BNHS helps confirm the identity of the birds and trains the application’s deep learning model. Each time a picture is contributed to the system, it teaches itself, increasing the platform’s accuracy in the recognition of bird species.
“In addition, its AI at the edge functionality enables mobile access to the information in remote locations such as deep jungles with poor or no internet connectivity,” says Podder.
Accenture Labs in Bangalore has provided pro-bono services to BNHS to design and build the Internet of Birds platform as part of its broader corporate focus on using technology for good. The IT firm’s Tech4Good program leverages emerging digital technologies and works with social innovators, academia, startups and government to address sustainable development goals across education, health, environment, inclusion and diversity.
Asked if the Internet of Birds use case can be replicated for other conservation solutions that leverage image identification, Podder says, “The AI at the edge functionality of the app could potentially be used in scenarios where connecting to the cloud introduces a lag or is simply not possible due to lack of connectivity.”
“The model can be applied to explore locations that are either inaccessible or hazardous for human beings such as in mines, underwater, or in space, and can be used in a variety of mission-critical industry use cases that enable safety, equipment diagnostics and troubleshooting.”
Needless to say, advanced technology is enabling new ways of mining data in the wildlife preservation activities around the world. In India, the concept is relatively nascent. There’s still a long way to go in terms of new product development and research.
While more research is going on in areas, such as IoT, big data, and advanced analytics for species protection and the public good in a scalable and sustainable manner, the Internet of Birds is a powerful example of how technology such as AI and deep learning can help drive innovation that benefits our communities and our planet.
,
Read More »Illuminating Global Fishing Activity With Satellite Tracking
July 18th, 2020
Via Spire, a look at how satellite data can be used to promote ocean sustainability:
In February this year, a Vietnamese ship entered Indonesian waters, likely fished illegally, and then returned to port without consequence. By March, it was back at sea. There were no signs to indicate that the vessel had raised suspicion, even though it had been making the same voyage since 2019. But it had in fact been spotted. Using satellite tracking data, experts at Global Fishing Watch had pieced together a history of the vessel’s every move—they’d uncovered suspicious behavior that would have otherwise continued unnoticed.
Global Fishing Watch (GFW)—an international, independent non-profit—has pioneered the use of technology to advance ocean sustainability through increased transparency. Its key resource for detecting illegal, unreported, and unregulated (IUU) fishing is satellite automatic identification system (AIS) tracking data collected by Spire Global. And with sophisticated data analytics, the organization is revolutionizing how fishing activity is monitored.
“Having the low-cost, global coverage that you get with the Spire satellite AIS completely transforms our ability to understand what’s going on out there,” said Paul Woods, GFW’s chief innovation officer. “We also benefit from a dynamic environment where we can interact with the data and collaborate with Spire on how we are going to use it in an open way.”
“The inspiring ways in which Global Fishing Watch uses maritime activity information fuels our enthusiasm to uncover more data-driven innovation,” said Max Abouchar, a sales engineer and data analyst at Spire.
Historically, vessels simply disappeared from oversight once they ventured far from shore and then submitted fishing logs when they returned to port. Not a good system for building trust, to say the least. GFW and Spire’s partnership, however, has helped build a comprehensive picture of commercial fishing activity around the world. A feat not possible a decade ago.
“Everybody has been so used to just not knowing,” said Mr. Woods. “When you bring this data in and actually quantify and measure all these things by directly observing it with AIS, it just completely changes the way people think about what questions to ask.”
AIS uses onboard GPS-like transponders, about the size of a laptop, that regularly broadcast vessel location, identity, speed, and other critical information to nearby ships, as well as to terrestrial and satellite receivers. While the International Maritime Organization first adopted AIS to prevent collisions and boost overall sea safety, it turned out to be an invaluable system for monitoring compliance and tracking suspicious fishing behavior globally. The Vietnamese vessel, for example, transmitted its location during the weeks it spent in Indonesian waters, leaving a trail of digital breadcrumbs.
“These detailed tracking data have the potential to provide estimates of fishing activity and effort in near real-time,” according to a sweeping study published by the United Nations Food and Agriculture Organization.
Monitoring vast oceans needs big data analytics
Today, nearly three million fishing vessels operate across the seas, of which 60,000—mostly larger vessels—sail with AIS broadcasting capabilities. Before the GFW and Spire partnership, tracking this fleet outside the range of terrestrial receivers could be spotty and infrequent. To overcome these limitations and enhance visibility, GFW turned to Spire for its expansive constellation of nanosatellites and innovative solutions.
Spire’s nanosatellites, each about the size of a bread loaf, whiz around the planet collecting AIS data and observing atmospheric, sea, and earth conditions. The distributed constellation ensures satellite coverage across the oceans. And because each satellite completes a revolution in about 90 minutes, the overall group collects multiple observations of each location a day. Spire even developed Dynamic AIS coverage to improve monitoring in high-traffic zones, where individual vessel broadcasts can be lost in the noise of thousands of ships transmitting AIS data at once.
“The satellite AIS fills in coverage and turns it into a comprehensive product instead of this niche, spotty little thing,” said Mr. Woods.
The two organizations partnered in 2017, and GFW started consuming Spire’s total AIS feed. When it uploaded the data to its interactive, public map, which visualizes the world’s fishing activity, the chart lit up.
“It was pretty spectacular, it filled right in. Some of the areas where we had the greatest problems showed the greatest benefit,” said Mr. Woods. “It made everything twice as good, instantly.”
Continuing the success, the two organizations grew together. As Spire launched more satellites, GFW received additional information. Today, GFW processes up to 60 million data points a day from over 300,000 fishing and non-fishing vessels, up from about 3 million data points and 100,000 ships in 2012.
By channeling this data into advanced data analytics, GFW has been able to develop powerful monitoring tools. More specifically, it used machine learning to build two models for identifying patterns within the large datasets. One classifies fishing vessels and the gear they use, which is regulated. The other identifies when and where a ship fished, not just where it traveled.
The combined system can automatically spot fishing vessels within the vast volume of data, estimate their fishing history, and flag suspicious behavior. With it, GFW has created an extensive record of global fishing operations. Monitoring has come a long way from self-reported logs lingering in filing cabinets.
These analytics quickly created impacts. In 2019, for example, GFW helped the United States Coast Guard identify eight times as many violations during IUU fishing patrols compared to the previous year, 25 of which were grave enough to “severely impact fisheries.”
Charting a course to complete transparency
“Once we got the data feed going in and it got better and better, the next thing we wanted to do was start to use the data for more operations,” said Mr. Woods.
To gain even greater transparency, GFW extended its use of AIS data to study the supply network of fishing vessels. Carrier ships often resupply fishing vessels and also offload catch at sea, a process known as transshipment. This allows some fishing vessels to stay at sea for months or years. But it’s also exploited by criminal operators to hide slave labor and illegal catches.
“It’s a way for them to get around reporting and do nefarious things,” said David Kroodsma, GFW’s director of research and innovation, “so it’s important for it to be transparent and tracked.”
By studying AIS tracks of supply network ships, GFW created models to identify transshipment encounters and collect data on a practice that has long avoided oversight. “Already it has been used to identify vessels potentially involved in catching sharks that were illegally transported through the Galapagos,” wrote Nate Miller, a data scientist who works with GFW.
The solutions kept coming.
Some ships broadcast false location data to avoid policing, making it look like they are far from their actual position, a practice known as location spoofing. But because Spire can provide a complete data history, including the locations of its satellites collecting AIS information, GFW has been able to reveal this masking behavior.
The solution works by looking for discrepancies between AIS data transmitted from ships and the location of the receiving satellite. If a satellite over the Bay of Bengal, for example, captures AIS data from a ship reporting a location in the Bering Sea, it’s possible the ship is concealing its real position.
Pushing the bounds of possibility even further, GFW is now using AIS to help model the total sound emitted by ships around the world to create a noise map of the ocean.
All of these cutting-edge solutions were born from the combined power of AIS transponders and nanosatellite receivers—significant results from such small devices—but it took more than technology to cultivate their success.
Going farther together
“Global Fishing Watch was one of our first customers,” said Simon van den Dries, senior sales director of global data services at Spire. “It immediately recognized the possibilities that maritime data possesses.”
Since then, the pair have enjoyed a flexible and nimble partnership that fosters innovation. GFW’s experts approach Spire’s engineers with ideas and ambitions, and together the teams design practical solutions that help ensure sustainability across our oceans.
“With the new space approach that Spire takes and the rapid growth of their constellation, and coverage that comes from it, we’ve been able to discover much more potential,” said Mr. Woods. “It’s been eye-opening for us, we keep being amazed at the scope of the potential. There are so many things that are obvious to us now that we never thought of three or four years ago.”
And more is still to come.
,
Read More »Harnessing Collective Intelligence For Conservation
July 11th, 2020
Via Ecological Society of America, an abstract of an interesting look at the potential for crowdsourcing intelligence to improve decision making around conservation:
Incorporating relevant stakeholder input into conservation decision making is fundamentally challenging yet critical for understanding both the status of, and human pressures on, natural resources. Collective intelligence (CI ), defined as the ability of a group to accomplish difficult tasks more effectively than individuals, is a growing area of investigation, with implications for improving ecological decision making. However, many questions remain about the ways in which emerging internet technologies can be used to apply CI to natural resource management. We examined how synchronous social?swarming technologies and asynchronous “wisdom of crowds” techniques can be used as potential conservation tools for estimating the status of natural resources exploited by humans. Using an example from a recreational fishery, we show that the CI of a group of anglers can be harnessed through cyber?enabled technologies. We demonstrate how such approaches – as compared against empirical data – could provide surprisingly accurate estimates that align with formal scientific estimates. Finally, we offer a practical approach for using resource stakeholders to assist in managing ecosystems, especially in data?poor situations.
,
Read More »NASA Satellite Data and Analysis Can Make Earth Better
July 6th, 2020
Via Seed Daily, a look at how NASA satellite data and analysis can make the Earth better:
The number of illegal gold mines in the Amazon is increasing so fast that activists have turned to satellite imagery to identify them. Still, with thousands of new mines a year, the work was overwhelming scientists at Earthrise Alliance – they needed more hands on deck. That’s how ninth graders in Weston, Massachusetts, began locating illegal mining activity in Brazil’s protected Yanomami territory.
Earthrise is one of numerous organizations getting Earth-observation images, data, and analysis – much of which NASA makes available for free – into the hands of people working on sustainability projects. These efforts by many different aid groups are tracking illegal mining, deforestation, and groundwater resources and informing the decisions of small farmers and governments trying to support them in regions that are feeling the worst effects of climate change.
Earthrise was working with Survival International, a group that has been reporting on illegal mines in the Yanomami territory for years. Miners bring disease, like malaria and tuberculosis, which can devastate local tribes that have had little contact with people outside their communities, according to Survival International. The highly contagious novel coronavirus now also threatens the region. In addition, the mines themselves pollute the land and waterways with mercury and other toxic substances.
Earthrise illustrated a striking rise in the number of new mines in the area in a graphic for Survival International. A few months later, shortly before schools across the United States closed in early 2020 amid the global pandemic, Earthrise asked Weston High School freshmen to comb Earth-observation data for environmental stories.
Examining satellite imagery from NASA, the European Space Agency, and the company Maxar Technologies, the students identified previously unreported illegal mines. The program is part of the Earthrise Education initiative, which provides students with an internet-based tool to use satellite imagery to investigate real problems that are in the news.
Headquartered in Washington, D.C., the Earthrise Alliance was founded in 2019 by former NASA officials as a merging of several projects that were using space resources to improve environmental conditions on Earth. The organization’s chief technology officer, Dan Hammer, previously worked as a presidential innovation fellow with NASA’s chief technology officer for information technology, where he made NASA data more accessible to the public.
“We offer additional perspective, which was the idea of Earthrise in the first place,” said Hammer, referring to the Apollo 8 photo for which the organization is named. Taken during the first crewed mission into lunar orbit, the photo shows Earth rising over the Moon’s horizon, giving humanity a first glimpse of the home planet from another celestial body.
“That original image alone was able to shift perspective for a lot of people,” Hammer said. “We’re offering that perspective for emerging news events, the spaceship Earth perspective.”
Self-Reflection
NASA has been looking back at Earth since the agency was established. In 1960, the agency began sending satellites into orbit to capture Earth images to improve weather predictions and maps. In 1961, Alan Shepard caught a view of Earth as the first American in suborbital space with Project Mercury.
Astronauts in the Apollo program in the 1960s and ’70s received photography training, not only to learn how to use the equipment, like cameras bracket-mounted to their spacesuits, but also to develop an eye for science images. These efforts led to the Earthrise photo and other famous images, including the iconic Blue Marble shot.
Images from these early Mercury and Apollo missions were the inspiration for the Landsat Program, which in 1972 launched the first satellite tasked specifically with observing and collecting data on Earth’s landmasses. The program has been in continuous operation since then, in partnership with the U.S. Geological Survey, which currently operates Landsat 8.
Today NASA has a fleet of satellites gathering Earth data, in addition to ambitious airborne and ground-based observation campaigns. Other governments and private companies have billions of dollars’ worth of satellites looking back at Earth. NASA also has the resources to process this data and develop predictive models and analysis.
The agency makes its Earth data available for free to the public. In some cases, organizations are working directly with NASA, benefiting from the agency’s computing power, modeling, and analysis. Organizations can also access the rapidly increasing Earth-observation data from the space agency and other governments and companies around the world.
Striking Gold, Helping Farmers
The problem of illegal gold mines isn’t unique to Brazil. It’s a global phenomenon that gets worse when gold prices rise.
In Ghana, environmental officials used Landsat data and algorithms developed by NASA to identify hotspots of illegal mining activity and revoke licenses from scores of companies collecting gold while avoiding environmental oversight and taxes.
Davis Adieno, who oversees the collaboration from Nairobi, Kenya, where he is program director for the Global Partnership for Sustainable Development Data, said the project is also forward-looking.
“The Ghanaian government is using this data to communicate the impact of illegal mines, but also, more importantly, how areas that have already been impacted could be recovered,” he said.
Working with the Global Partnership and other partners, NASA’s Brian Killough produced the initial data cube platform for five African countries – Ghana, Kenya, Sierra Leone, Senegal, and Tanzania – tailoring it to specific projects and training initial users. The successful model has now been scaled up for Digital Earth Africa, which makes free Earth-observation data available and usable in an increasing number of countries across the continent.
Data cubes are stacks of satellite data configured to allow the use of powerful cloud computing and rapid analyses, Killough explained. Satellite data from many days or years can be organized into a cube, with dimensions of space (latitude and longitude) and time. These cubes are made of small pixels that hold data at a scale of 30-meters – about the size of a baseball diamond – which is Landsat’s resolution. Once in a cube, it is much easier to analyze and apply the data.
Killough and his team at NASA’s Langley Research Center in Hampton, Virginia, work directly with the users of the data resources they’ve created.
“We help them interpret the data and adjust the tools for their needs,” he said. “We also conduct training in each country, where we give people an understanding of the data and tools and let them use it on their own.”
Adieno said Killough “introduced what is possible – what type of data is available, the duration, what you can actually do with the infrastructure, with the algorithms that are available – which helped the countries identify who was best-placed to use it.”
In most cases, the satellite data tools are being used by people who have already been working with satellite imagery, but with less powerful capabilities and extremely cumbersome and often untenable downloading and processing times.
Adieno said officials in Senegal purchased private data for their project but then later moved to the data cube infrastructure for their analysis. “The results were more or less the same, which means they didn’t need to spend that money,” Davis said. “The value here is access to free, open source satellite data that’s analysis-ready.”
Killough agreed. “People in the developing countries we’ve been working with recognize that satellite data could have a huge impact,” he says. “But they have struggled with the preparation and the understanding of how to directly apply it to their applications. That’s where I think we’ve made great progress.”
The data resources are “certainly very efficient and effective,” said Victor Addabor, who heads Ghana’s National Disaster Management Organization.
Addabor worked with Killough to use Landsat data to identify the rate at which small farmers in the country’s north are adopting new growing techniques, like using drought-resistant seeds. This type of information helps the government determine the best ways to support small farmers in remote areas who are making decisions individually while also playing a major role in the country’s food security.
“That One Right Decision”
Indeed, unlike large agricultural producers in Europe and the United States, the vast majority of farmers around the world are working small plots of land, feeding much of Earth’s population without coordination. These farmers are disproportionately affected by decreasing water resources and rising temperatures
“In many places, if farmers don’t make that one right decision, it can mean the whole year is incredibly challenging for them. It can mean that the kids don’t go to school or families don’t have enough to eat,” said Eliot Levine, director of the Environment Technical Support Unit at Mercy Corps.
The Portland-based organization has been providing humanitarian relief around the world for decades and, more recently, is working with NASA on a partnership that uses satellite data to support science-informed policy and sometimes deliver information directly to people who need it.
Mercy Corps and NASA are collaborating in Kenya to reach farmers with a combination of precise weather and agronomic information. The work is part of Mercy Corps’ AgriFin program, which focuses on building the capacities of smallholder farmers, using cellphones and texting technology to deliver information about weather forecasts, seed types, financial products, market prices, and other relevant resources.
“Through our partnership with NASA, we are providing farmers with information and tools they have never had access to before,” Levine said.
“Should you plant now or wait? Water now or wait because rain is coming? Farmers need access to information,” Levine said. “We envision a future where every small-holder farmer prospers in a digitally interconnected world.”
The effort is part of a growing collaboration between NASA and Mercy Corps, a partnership that began in 2015 with an early project to map groundwater resources in Niger and was formalized in 2019 with a Space Act Agreement.
Shanna McClain, global partnerships manager at NASA Headquarters in Washington, said the agency was looking to “engage with partners that it hasn’t worked with in the past in the hope of achieving new ways of understanding complex human and environmental challenges.”
As the collaboration with Mercy Corps matured, McClain and Levine saw increasing possibilities for future work, as they had hoped they would.
“We didn’t just want to work with a new type of partner,” McClain said. “We wanted to see the magic that comes only from partnership.”
The formal agreement “essentially helps recognize our interest in doing this work as a shared endeavor,” she said, noting no money is changing hands. “We’re putting in an equal amount of funding and capacity.”
NASA scientists have worked with Mercy Corps from their desks and at the sites of international projects. The agency provides Earth science insights, in addition to data and analysis that Mercy Corps wouldn’t be able to produce on its own.
Together, NASA and Mercy Corps are helping to strengthen the resilience of communities around the world.
Earth Data for Earth
Earthrise estimates that more than half a trillion dollars has been spent on public and private satellites looking back at our own planet, primarily for military intelligence and profit-driven fields like commodity trading.
Earthrise, along with Digital Earth Africa and Mercy Corps, is repurposing this technology.
“There’s value that filters down when you’re fundamentally aware,” said Earthrise’s Hammer. “We’re leveraging the hundreds of billions of dollars of existing investment for Earth literacy.”
With Earth-observation data, people can assess how their own lands are changing and what they can do to alter the direction of the change.
“Satellite data can be complex,” NASA’s Killough noted. “Making the data accessible and useable gives the local users more power to control their future.
,
Read More »