Vijay Ramesh, 30, Sarika Khanwilkar, 29, and Pooja Choksi, 31, are pursuing doctorates in ecology, evolution and environmental biology at Columbia University. Their research collaboration, Project Dhvani, has been collecting soundscape recordings from sites across central India and the Western Ghats since 2018.
Project Dhvani’s ecologists place audio recorders at selected spots to continually capture the different frequencies of an ecosystem.
In addition to understanding the patterns of presence or absence of a species, the project uses artificial intelligence and machine learning to analyse the data collected and study how various species interact with their environment and react to changes in their habitat.
Preliminary results are encouraging. In the dense, mountainous terrain of the Western Ghats, Ramesh’s research found that rainforest birds are returning to some of the restored habitats in the Valparai plateau of the Anamalai Hills, complementing previous research conducted through manual surveys. “From an acoustic lens, what is fascinating is that a lot of the previously empty soundscapes are showing activity at different frequencies,” Ramesh says.
The soundscapes Project Dhvani studies range from protected areas to unprotected human-dominated landscapes. Once recordings have been collected, the effort moves to a computer lab, where raw data is first manually sifted and bird calls are manually annotated by naturalists and ecologists.
Recordings are then fed into a deep-learning model, where calls are logged by frequency, intensity and other such metrics. Over time, as more recordings are made at each site, the data begins to offer a picture of the biodiversity, and ways in which it may be changing.
The deep-learning program is improving too. “For instance, it can now pinpoint the calls of the Nilgiri flycatcher with 35% greater accuracy and the calls of the great hornbill with 9% greater accuracy,” says Keshav Bhandari, a research affiliate working on the project.
Choksi’s preliminary results from research around Kanha show that birds’ vocalising behaviour may be changing: sites with high canopy cover but different vegetation sound similar. And when certain invasive species (like the Lantana camara) take over a patch of land with little canopy cover, the soundscape is much quieter.
A key focus area in the years ahead will be understanding how the presence and behaviour of a few species may alter as a function of local climatic and land-use changes. “We are combining traditional methods of surveying landscapes with these non-traditional methods. When you put them together, the results tell us a lot more,” Choksi says.
E-Paper
