Here’s how AI is helping Africa’s endangered elephants

“Africa’s elephants play key roles in ecosystems, economies and in our collective imagination all over the world.”

Dr Bruno Oberle, Director-General of the International Union for the Conservation of Nature (IUCN), stressed the global importance of one of Africa’s most iconic creatures back in March 2021. The IUCN also confirmed that the animals had been placed on its red list of threatened species.

Following population declines due to loss of habitat and ivory poaching, the African forest elephant was classified as ‘critically endangered’ by the IUCN. The African savannah elephant became ‘endangered’.

The IUCN says the population of both species had dropped to 415,000 and that the number of African forest elephants decreased by an alarming 86% over the previous three decades.

“We must urgently put an end to poaching and ensure that sufficient suitable habitat for both forest and savanna elephants is conserved,” Oberle added.

In collaboration with Dutch tech start-up Hack the Planet, a team of British scientists at Stirling University has developed a new camera that could help protect elephants and other wildlife. The AI-powered device connects directly to satellites and sends real-time information to forest rangers or local villagers. Traditional instruments in this space are often hampered in remote locations by poor internet availability or having to collect recordings physically.

"Real-time data from smart cameras and other sensors could revolutionize how we monitor and protect the world's most threatened ecosystems," says Dr Robin Whytock, a post-doctoral researcher at Stirling University" “The advances made in this study show that real-time data could be used to make better decisions during time-critical situation".”

During the pilot in Gabon, the researchers say, “camera systems took more than 800 photos in 72 days. 217 photos of elephants were taken. The AI model achieved an accuracy of 82% in recognizing elephants. Rangers received an alert from the system within seven minutes on average.”

The project team says the technology can detect other animal species, as well as humans. It can therefore monitor conflicts between people and wildlife as well as illegal activities in protected areas. It can even deter elephants from entering villages, the researchers say.

Gabon is home to 60-70% of all African forest elephants, numbering around 95,000, according to the Wildlife Conservation Society (WCS). It is regarded as the principal stronghold of the species, being home to more African forest elephants than any other country.

The country’s president has enlarged protected areas and created 13 new national parks since coming to power in 2009:

“Gabon, under the active leadership of President Ali Bongo Ondimba, has been able to buck the trend of forest elephant decline. This is down to the courage and dedication of our national parks rangers, who are very much in the line of fire. In Africa, there is a clear link between healthy elephant numbers and natural resource governance,” Lee White, Gabon’s Minister of Water, Forests, the Sea and the Environment told WCS.

It’s estimated that forests cover up to 85% of Gabon’s total land area. The WCS says African forest elephants promote healthy forests and their protection can have benefits for the climate as well as biodiversity.

It cites a study in 2019 which linked the presence of forest elephants to greater carbon storage. This is because their browsing thins the forests of smaller trees, thereby promoting the growth of bigger ones which can store more carbon.

Deforestation must be halted by 2030 to help the world limit global warming to 1.5C. More than 60 million hectares of primary forest have been lost in the tropics in the past two decades, that’s around the entire size of France.

The Tropical Forest Alliance, hosted by the World Economic Forum, is a leading platform comprising 180 partners from the private and public sectors working to tackle deforestation linked to the agricultural sector.

An AI software package known as PAWS (Protection Assistant for Wildlife Security) is being used in protected areas in more than 60 countries across the world. It can help predict potential poaching hotspots by using historical data to build predictive models based on previous poaching activity.

Elsewhere, AI technology is also being used to interpret animal communication to support conservation and sustainability efforts. The Earth Species Project uses machine learning algorithms to listen to different ecosystems and decode animal interactions to help understand and protect them better.