fbpx

#TECH: Leaning on cloud technology to fast-track efforts to protect and save the orangutans

CLOUD technology has always been associated with helping businesses in the areas of storage, databases, networking, analytics, robotics, machine learning, artificial intelligence, Internet of Things and many others. These days, it is venturing into a whole new area — saving wildlife.

Cloud solutions provider Amazon Web Services (AWS) is showcasing cloud technology to save the orangutans in the Indonesian forest.

Collaborating with World Wildlife Fund for Nature Indonesia (WWF-Indonesia), a non-profit organisation in WWF’s global network, the cloud service provider is lending a hand in caring for these endangered primates.

Orangutans are among the most intelligent primates on Earth, capable of constructing, using tools and living in colonies with distinct cultures.

Largely solitary and spending much of their lives in trees, this attribute have made conservation efforts harder as it is difficult to accurately measure orangutan populations.

THE EFFORT

One of the key aspects of conserving and protecting the orangutans is to identify their faces for record-keeping purposes.

Since 2005, WWF-Indonesia has assessed the health of orangutan populations and conserved their 568,700-hectare habitat in Sebangau National Park in Central Kalimantan, Indonesia.

According to WWF-Indonesia’s finance and technology director, Aria Nagasastra, identifying a wildlife face can be a challenge and is one of the most challenging tasks confronting conservationists.

Traditionally, the assessment process includes experts and local community volunteers going into the field daily to find the orangutans, photograph them, download images to local computers at the base camp before the data is analysed by WWF experts in the city.

“This process can take experts up to three days to analyse as each batch can contain thousands of photos. The process is also error-prone due to the volume of data,” says Aria.

For instance, to match a selection of photos of orangutans in the wild with a primate already identified as Nani will not be easy.

However, with the help of technology, things are made easier for conservationists.

“With the help of AWS, we can now automatically gather images from mobile phones and motion-activated cameras set up near our base camp. The footage is then uploaded to Amazon S3 (for Amazon Simple Storage Service) where they are analysed,” adds Aria.

He says the use of such technology is important to accelerate efforts to save critically-endangered orangutans in the Indonesian forest. According to WWF, the Bornean orangutan population has declined by more than 50 per cent over the past 60 years. Their habitat has also been reduced by at least 55 per cent over the past 20 years.

Human activities including poaching, destruction of habitat and illegal pet trading have caused severe declines in the orangutan population, which comprises three species of great apes native to Indonesia and Malaysia.

HOW IT WORKS

Using AWS machine learning (ML) services, WWF-Indonesia can better understand the size and health of the orangutan population in their native habitat.

The non-profit is able to survey more territory with fewer resources, reduce operating expenses and channel more conservation funding to protect Indonesia’s biodiversity.

The ML technology is called Amazon SageMaker and it allows data scientists and developers to quickly build, train and deploy machine learning models. In fact, WWF Indonesia has reduced its analysis time from up to three days to less than 10 minutes.

It’s also been able to increase the accuracy and specificity of its data, which includes measurements such as gender ratio and age. It helps conservationists quickly identify whether primates are pregnant, ill or suffering from injuries requiring immediate treatment.

By adopting machine learning, WWF-Indonesia has reduced its reliance on a limited pool of experts and improved the accuracy and breadth of its data about orangutan populations. “As a non-profit, we are always looking for ways to apply our resources more effectively. Using Amazon SageMaker and Amazon S3, field surveyors, even with limited expertise and capacity, are able to identify wildlife in its natural habitat with a high degree of accuracy,” says Aria.

“This careful use of technology will help biologists and conservationists to effectively monitor wildlife behaviour. Our resources can be directed more efficiently towards conservation efforts,” he adds.

MORE COLLABORATION

As part of its efforts to conserve the Bornean orangutan, WWF-Indonesia is also in talks with its Malaysian counterpart on collaboration and sharing of knowledge.

“We share the Borneo Island and it is only natural that we share data. Conservation is a collective effort and with the help of cloud computing and other innovations, we hope the work will bear fruit sooner rather than later,” says Aria.

In the future, WWF-Indonesia plans to explore the use of additional machine learning services, such as Amazon Rekognition, an image and video analysis service, to further improve the speed and accuracy of its population identification and tracking efforts.

As conservation work is often a race with time, WWF-Indonesia plans to apply similar methods to help other endangered species including rhinoceros, tiger, sea turtles and elephants.

Source: NST