Artificial intelligence to help combat elephant poaching

Posted by Lauren Dold on 29 April 2021

Every 15 minutes, an African elephant is killed by a poacher. New artificial intelligence (AI) technology may well change this disturbing statistic.

Developed by British researcher Olga Isupova, this new algorithm photographs and analyses large areas to identify African elephants. Working with a satellite, the technology will greatly aid the fight against ivory poaching.

Credit: Getaway gallery

The satellite scans vast wilderness areas in a short amount of time, collecting close to 5 000 square kilometres of photos, highlighting any elephants within the images. This works especially well with elephants as they’re easier to spot due to their large size. These results are then compared to the results collected by human counting.

“The programme counts the number of elephants by itself, which no longer puts the people who used to do this task in danger. The animals are no longer disturbed and the data collection process is more efficient,” explains Isupova.

Published on March 25, 2021, the International Union for Conservation of Nature (IUCN) revealed that poaching, along with massive deforestation, is exposing the African forest elephant (in Central and West Africa) to a critical danger of extinction. Along with the more common savanna elephants, populations have declined dramatically in the last fifty years.

This technological intervention, along with human action in the fight against poaching will guide researchers as they hope to further develop the technology to include other threatened species.

Did you know?

Before colonisation in Africa, it is estimated that there may have been as many as 26 million African elephants on our continent. Today, there are fewer than half a million elephants in the wild in Africa.

Read about the work being done by Elephants Alive, a South African organisation researching, and working towards stabilising our elephant population here:

Picture: Mark Dumbleton

yoast-primary - 1004439
tcat - Environment
tcat_slug - environment
tcat2 - Wildlife
tcat2_slug - wildlife
tcat_final -