To find out how wildlife is faring, scientists try to listen

[ad_1]

An AI-assisted computer model was able to detect bird songs from recordings made in the Chocó region of Ecuador

An AI-assisted computer model was able to detect bird songs from recordings made in the Chocó region of Ecuador.

A reed pipe and a high-pitched trill in duet against the backdrop of a low insect hum. His symphony is the sound of a forest and is monitored by scientists to measure biodiversity.

The forest recording in Ecuador is part of new research looking at how artificial intelligence could track animal life in recovering habitats.

When scientists want to measure reforestation, they can study large swaths of land with tools like satellites and lidar.

But determining how quickly and abundantly wildlife returns to an area presents a more difficult challenge, sometimes requiring an expert to review sound recordings and detect animal calls.

Jorg Muller, professor and field ornithologist at the University of Würzburg Biocenter, wondered if there was a different way.

“I saw the gap that we need, particularly in the tropics, better methods to quantify the enormous diversity… to improve conservation actions,” he told AFP.

He turned to bioacoustics, which uses sound to learn more about the lives and habitats of animals.

It is a long-standing research tool, but more recently it is being combined with computer learning to process large amounts of data more quickly.

Muller and his team recorded audio at sites in Ecuador’s Chocó region, ranging from recently abandoned cocoa plantations and pastures to reclaimed agricultural land and ancient forests.







Sound of an ancient forest. Credit: Jörg Müller

They first had experts listen to the recordings and select birds, mammals and amphibians.

They then carried out an acoustic index analysis, which provides a measure of biodiversity based on broad metrics of a soundscape, such as the volume and frequency of noises.

Finally, they made two weeks of recordings through an AI-assisted computer program trained to distinguish 75 bird songs.

More recordings needed

The program was able to consistently select the calls it was trained on, but could it correctly identify the relative biodiversity of each location?

To verify this, the team used two baselines: one from experts who listened to the audio recordings and a second based on insect samples from each place, which offer an approximation to biodiversity.

While the library of sounds available to train the AI ​​model meant it was only able to identify a quarter of the bird songs that experts could, it was still able to correctly measure biodiversity levels at each location, according to the study.

“Our results show that soundscape analysis is a powerful tool to monitor the recovery of faunal communities in the hyperdiverse tropical forest,” stated the research published Tuesday in the journal Nature Communications.

The tool has some limitations, including the relatively few bird songs available with which to train the computer model.

The tool has some limitations, including the relatively few bird songs available with which to train the computer model.

“Soundscape diversity can be cost-effectively and robustly quantified across the entire gradient, from active agriculture to old-growth and recovering forests,” he added.

There are still shortcomings, including a shortage of animal sounds with which to train AI models.

And the approach can only capture species that announce their presence.

“Of course, there is no information on silent plants or animals. However, birds and amphibians are very sensitive to ecological integrity, they are a very good substitute,” Müller told AFP.

He believes the tool could become increasingly useful given the current push for “biodiversity credits,” a way to monetize the protection of animals in their natural habitat.

“Being able to directly quantify biodiversity, rather than relying on indicators such as tree cultivation, encourages and enables external evaluation of conservation actions and promotes transparency,” the study says.

More information:
Jörg Müller, Soundscapes and deep learning make it possible to track biodiversity recovery in tropical forests, Nature Communications (2023). DOI: 10.1038/s41467-023-41693-w. www.nature.com/articles/s41467-023-41693-w

© 2023 AFP

Citation: To find out how wildlife is faring, scientists try to listen (October 22, 2023) retrieved October 22, 2023 from https://phys.org/news/2023-10-wildlife-scientists.html

This document is subject to copyright. Apart from any fair dealing for private study or research purposes, no part may be reproduced without written permission. The content is provided for informational purposes only.



[ad_2]
Source link

Check Also

Unraveling the secrets of this strange beetle’s 48-hour clock | Trending Viral hub

[ad_1] Unraveling the secrets of this strange beetle’s 48-hour clock New research examines the molecular …

The dark side of nostalgia for wild and unspoilt places | Trending Viral hub

[ad_1] The dark side of nostalgia for wild and unspoilt places A novel about the …

In matters of scientific debate, follow the Houdini rule | Trending Viral hub

[ad_1] In matters of scientific debate, follow the Houdini rule Scientific experience is usually limited …

Leave a Reply

Your email address will not be published. Required fields are marked *