Problem 

Monitoring wildlife is an essential component of conservation. Evidence-based conservation efforts, data-driven decision-making for adaptive management, and sustainable use of natural resources are all based on the premise that population declines can be detected in a timely manner. Monitoring objectives can range from assessing species presence/absence to knowing the exact density of one or more species. Monitoring data are used across multiple scales, from local (site-level) to national, regional, and global.

Solution/Approach

A study published in Nature follows how Indian researchers leverages AI and ML tools to observe and conserve species and ecosystems. Alongside best use cases, they are noting the challenges with AI and building high-quality training datasets. According to Seema Lokandwala, who is a part of the Elephant Acoustics Project, they can identify if the elephant is in conflict if they can recognise its sound. The algorithms help her clarify overlapping sounds and decipher infrasonic ones that are inaudible to humans. They also separate trumpet calls based on whether the elephants interact with their mahouts or other elephants.

Five years ago, ecologist V. V. Robin, a researcher at the Indian Institute of Science Education and Research (IISER), Tirupati, initiated a project to understand why birds found in some Western Ghats habitats did not appear in others. It took him two years to analyse avian sound recordings collected over a year. In his opinion, with AI, they would have completed the study in a year.

Impact/Implementation

Listening to these wildlife calls, a researcher could take up to 30 minutes to decode the message. Lokhandwala says AI can figure out a hundred calls in five minutes. AI-driven methods can provide continuous, real-time surveillance without the need for human intervention. Real-time AI analysis could alert authorities to activities such as illegal tree-cutting.

In Robin’s opinion, birds from India need to be better represented in AI-enabled platforms such as BirdNET, which identify birds through sounds. The algorithm represents most North American and European birds.

Nature.