Can artificial intelligence give elephants a winning edge? – ProWellTech

Can artificial intelligence give elephants a winning edge? – ProWellTech

Pictures of elephants wandering the African plains is imprinted on our minds and something easily recognizable as a symbol of Africa. But the future of elephants today is uncertain. An elephant is currently being killed by poachers every 15 minutes, and humans, who love watching them so much, have declared war on their species. Most people are not poachers, ivory collectors or intentionally harm wildlife, but silence or indifference to the ongoing battle is just as deadly.

You can choose to read this article, feel bad for a moment, and then move on to your next email and start the day.

Or maybe you’ll stop to think: Our opportunities to help save wildlife, especially elephants, are right in front of us and growing every day. And some of these opportunities are rooted in machine learning (ML) and the magical achievement we affectionately call AI.

A baby elephant takes a bath in a trough among adults

Image credits: Jes Lefcourt (Opens in a new window)

Open source developers are giving elephants a neural advantage

Six months ago, in a COVID-infused world,, a large open source community owned by Avnet, and Smart Parks, a Netherlands-based organization focused on wildlife conservation, reached out to technology leaders. , including Microsoft, u-blox and Taoglas, Nordic Semiconductors, Western Digital and Edge Impulse with the idea of ​​funding the research and development, production and shipping of 10 of the most advanced elephant monitoring collars ever built.

These modern tracking collars are designed to implement advanced machine learning (ML) algorithms with the longest battery life ever provided for similar devices and a wider network range than ever before. To make this vision even bolder, they called to fully open source and freely share the results of this effort via, a conservation organization that supports open source tracking collar hardware and software for monitoring projects. environmental and wildlife.

Our opportunities to help save wildlife, especially elephants, are right in front of us and growing every day.

The tracker, ElephantEdge, would be built by specialist engineering firm Irnas, with the Hackster community joining together to create fully deployable ML models from Edge Impulse and telemetry dashboards from Avnet that will run the newly built hardware. Such an ambitious project had never been attempted before and many doubted that such a collaborative and innovative project could be completed.

Create the best elephant tracking device in the world

Only they made it. Brilliantly. The new ElephantEdge tracker is considered the most advanced of its kind, with eight years of battery life and hundreds of miles of range of LoRaWAN network repeaters, with TinyML models that will provide park rangers with a better understanding of acoustics, motion , the position and position of the elephants. environmental anomalies and more. The tracker can communicate with a series of sensors, linked by LoRaWAN technology to the phones and laptops of the park rangers.

This gives rangers a more accurate image and location to track than previous systems that captured and reported images of all wildlife, which drained the battery life of the trackers. The advanced ML software that runs on these trackers is built explicitly for elephants and developed by the community in a public design challenge.

“Elephants are the gardeners of ecosystems as their wandering by itself creates space for the prosperity of other species. Our ElephantEdge project involves people from all over the world to create the best vital technology for the survival of these gentle giants. Every day they are threatened by habitat destruction and poaching. This innovation and partnership allow us to gain a deeper insight into their behavior so that we can improve protection, ”said Tim van Dam, co-founder of Smart Parks.

A baby elephant and two adults on the plains

Image credits: Jes Lefcourt (Opens in a new window)

Open source, community-powered, conservation-AI at work

With hardware built by Irnas and Smart Parks, the community was busy building the algorithms to make it sing. Software developer and data scientist Swapnil Verma and Mausam Jain in the UK and Japan created Elephant AI. Using Edge Impulse, the team developed two ML models that will touch the tracker’s edge sensors and provide critical information for park rangers.

The first community-led project, called Human Presence Detection, will alert park rangers to the risk of poaching by using audio sampling to detect human presence in areas where humans shouldn’t be. This algorithm uses audio sensors to record sounds and images as it sends them over the LoRaWAN network directly to a ranger’s phone to create an instant alert.

The second model was called “Elephant Activity Monitoring”. Detect general elephant activity, taking time series input from the tracker’s accelerometer to locate and make sense of running, sleeping and grazing to provide conservation specialists with the critical information they need to protect the animals. elephants.

Another brilliant community development has come from the other side of the world. Sara Olsson, a Swedish software engineer with a passion for the national world, created a TinyML and IoT monitoring dashboard to help park rangers with conservation efforts.

With few resources and support, Sara built a comprehensive telemetry dashboard combined with ML algorithms to monitor camera traps and puddles, reducing network traffic by processing data on the collar and significantly saving battery life. To validate his hypothesis, he used 1,155 data models is 311 tests!

Sara Olsson's TinyML and IoT monitoring dashboard

Sara Olsson’s TinyML and IoT monitoring dashboard. Image credits: Sara Olsson

He completed his work in the Edge Impulse studio, creating the models and testing them with camera streams from Africam using an OpenMV camera from the comfort of his home.

Image credits: Sara Olsson (Opens in a new window)

Technology for good works, but human behavior must change

The ElephantEdge project is an example of how commercial and public interest can converge and translate into a collaborative sustainability effort to promote wildlife conservation efforts. The new collar can generate critical data and provide better data park rangers to make urgent, life-saving decisions about protecting their territories. By the end of 2021, at least ten elephants will sport the new collars in selected parks across Africa, in partnership with the World Wildlife Fund and Vulcan’s EarthRanger, sparking a new wave of conservation, learning and defense.

Of course, this is great, the technology works and helps elephants like never before. But in reality, the root cause of the problem goes much deeper. Humans must change their relationship with the natural world for proper habitat for elephants and population resurgence to occur.

“The threat to elephants is greater than it has ever been,” said Richard Leakey, a leading paleoanthropologist and conservationist. The main argument for allowing trophy or ivory hunting is that it raises funds for conservation and local communities. However, a recent report revealed that only 3% of hunting proceeds in Africa go to communities in hunting areas. Animals don’t need to die to make money for the communities you live in.

With great technology, collaboration, and a commitment to address the underlying cultural conditions and the ivory trade that leads to most elephant deaths, there is a real chance to save these singular creatures.

Source link

Leave a Reply

Your email address will not be published. Required fields are marked *