EDEN IAS

NEWS IMPULSE – AI BASED SURVEY OF AFRICAN ELEPHANTS| 07 JANUARY

Syllabus Section: Environment and Ecology

Why in News?

An International Team of researchers led by University of Oxford have developed a new approach to survey African Elephants using satellite images and Artificial Intelligence.

About New Approach:

  • A new approach for surveying African elephants using satellite imagery and artificial intelligence (AI) could help in solving some of the present challenges in the conservation of the species.
  • The method uses satellite orbiting in space that is capable of capturing more than five thousand square kilometres of images. The captured images is then processed through deep learning model that will detect elephants eliminated other objects.
  • The International team used a customised dataset to cover more than thousand elephants in South Africa.
  • The method eliminates the risk of double counting. Also, it makes it possible to conduct repeat surveys in short intervals.
  • The method is capable of identifying calves separately.

Advantages:

  • Machines are less prone to error.
  •  False negatives and false positives in deep learning algorithms
  • Can be rectified by systematically improving models.
  • Elephants can be detected in satellite imagery with accuracy as high as human detection capabilities.
  • Satellite monitoring is an unobtrusive technique requiring no ground presence thus eliminating the risk of disturbing species, or of concern for human safety during data collection.

Further, the remote detection method makes it possible to monitor cross-border areas without terrestrial permits. These areas are usually important to conservation planning

Source: The Hindu