Geoffroy’s spider monkeys live high in the rainforest canopy, and are difficult to observe. Their shy behavior makes it challenging for scientists to track and protect them effectively. To address this, biologist Jenna Lawson implemented an innovative solution in 2021.
Lawson strategically placed 350 audio monitors across the Osa Peninsula in Costa Rica.
The devices captured the sounds of the forest, allowing her to study the monkeys without disturbing them. This approach provided valuable insights into their movements and behavior.
The devices recorded forest sounds for a week, amassing vast data. By feeding this data into artificial intelligence (AI) systems trained to identify spider monkey calls, researchers gained insights that would otherwise take years to uncover.
This AI-driven initiative became one of the largest acoustic wildlife studies globally, and revealed troubling signs about the health of the habitats in which these animals live.
“They’re the most sensitive of the primates that we have here,” said Lawson. “The spider monkey would be the first animal to leave when there’s signs of trouble. They would be the last animal to come back once forests are restored because they need mature, secondary and primary forest to be able to survive.”
The monkeys avoid human-altered areas and rely on mature forests, making them sensitive indicators of environmental health.
The findings revealed that the monkeys avoid paved roads and plantations, which indicates that there are flaws in the government wildlife corridors which were designed to expand their range.
Lawson’s work exemplifies how AI can support biodiversity efforts. Previous research has emphasized the potential of machine-learning techniques to manage vast datasets, which would enable faster, cheaper, and more precise ecological studies.
However, technical hurdles like humidity-damaged devices and accidental destruction by animals remain.
To tackle these challenges, Microsoft’s AI for Good Lab introduced “Sparrow” – Solar-Powered Acoustic and Remote Recording Observation Watch. This energy-efficient device, designed to function autonomously for years, transmits data via low-Earth orbit satellites.
“Those remote places are also the most important places on the Earth from a biodiversity perspective,” said Juan Lavista Ferres, Microsoft’s chief data scientist.
Sparrow’s first test will monitor jaguars, birds, and spider monkeys along Colombia’s Magdalena River.
By 2025, the project aims to deploy these devices on all continents and make the data accessible to researchers while protecting sensitive location information in order to avoid alerting potential poachers and animal traders.
“What we don’t want is these devices to ever be used for poachers to understand where the animals are,” Lavista Ferres said.
AI-powered acoustic monitoring has applications beyond studying rainforests. For instance, it could help sailors detect whale sounds in shipping lanes, thus reducing the risk of collisions.
This technology is transformative because it allows scientists to study wildlife without physically intruding on their habitats, which minimizes human influence on animal behavior.
“We’re reducing our influence on their behavior. And also – they don’t want us here,” Lawson explained.
However, challenges remain. Deploying such systems requires overcoming technical issues like equipment durability and environmental conditions.
Equally important is collaboration with local communities. Lawson’s work around Costa Rica’s Corcovado National Park highlights this need. Landowner support was critical for placing audio monitors outside protected areas to enable a broader understanding of animal behavior.
Projects like Jenna Lawson’s and Microsoft’s Sparrow demonstrate how AI can revolutionize conservation efforts.
These initiatives show that AI-powered tools can collect and analyze vast quantities of data, offering insights into animal behavior and habitat health that would be difficult to obtain otherwise.
However, realizing their full potential requires overcoming technical challenges, such as maintaining equipment in harsh environments, securing adequate funding, and addressing ethical concerns – including the safe and responsible use of collected data.
With 28% of plant and animal species currently at risk of extinction, AI-assisted wildlife monitoring offers a promising way to tackle biodiversity loss.
By combining advanced technology with community-driven conservation efforts, scientists can gain a deeper understanding of ecosystems and implement effective protection strategies.
Endangered species like Geoffrey’s spider monkeys highlight the urgency of these efforts. Their unique role in the ecosystem and their vulnerability to habitat changes emphasize both the challenges of conservation and the hope that innovative solutions can bring.
These remarkable creatures remind us of the biodiversity we stand to lose – and inspire action to preserve what can still be saved.
The study is published in the Proceedings of the Royal Society B.
—–
Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates.
Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.
—–