WWF-Indonesia using machine learning to save critically endangered orangutans

June 05, 2020

Sumatran orangutan mother with baby

Image: WWF-Indonesia

World Wildlife Fund for Nature Indonesia (WWF-Indonesia) is on a mission to save critically endangered orangutans in Indonesia.

According to WWF, Bornean orangutan populations have declined by more than 50% over the past 60 years and the species’ habitat has been reduced by at least 55% over the past 20 years.

Severe declines in the orangutan population native to Indonesia and Malaysia can be traced directly back to humans and their cruel poaching and illegal pet trade practices, as well as causing the destruction of habitats.

As orangutans are largely solitary and spend much of their lives in trees, conservation efforts to accurately measure remaining populations are complicated and time-consuming, WWF-Indonesia explained.

In an attempt to accelerate efforts to save the orangutans, WWF-Indonesia has turned to Amazon Web Services (AWS) to use machine learning services to better understand the size and health of orangutan populations in their native habitat.

Must read: The Internet of Wild Things: How the IoT joined the battle against climate change

The non-profit said this allows them to survey more territories with fewer resources, reduce operating expenses, and channel more of the conservation funding to protect the biodiversity of Indonesia.

“With careful use of technology, this innovation will help the biologists and conservationists to effectively and cost-efficiently monitor the wildlife behaviour through time and thus we can allocate our resources to scale up the monitoring efforts and invest more in conservation actions,” WWF-Indonesia finance and technology director Aria Nagasastra said.

“The collaboration between WWF-Indonesia and AWS on innovative new technology solutions can lead to the opportunity to elevate the biodiversity conservation practices in Indonesia to the next level.”

Sumatran orangutan male

Image: WWF-Indonesia

For around 15 years, WWF-Indonesia has assessed the health of orangutan populations and conserved their 568,700-hectare habitat in Sebangau National Park in Central Kalimantan, Indonesia.

The organisation said previously, the assessment had required experts and local community volunteers going into the field daily to find orangutans, photograph them, download images to local computers at the basecamp, and transport the data back to the city for analysis by a WWF expert.

This process, however, would take the teams three days to analyse each batch of thousands of photos. WWF-Indonesia said it has now reduced its analysis time down to less than 10 minutes.

Using cloud, WWF-Indonesia now automatically gathers images from mobile phones and motion-activated cameras at its basecamp and uploads them to Amazon Simple Storage Service (Amazon S3) for analysing.

Through the use of Amazon SageMaker, data scientists and developers are able to quickly build, train, and deploy machine learning models at scale.

In addition to saving time, the organisation said it has also been able to increase the accuracy and specificity of its data, which includes measurements such as gender ratio and age, along with assessments on the viability of populations. WWF-Indonesia can also now quickly identify whether individuals are pregnant, ill, or suffering from injuries that require immediate treatment.