The U.S. research team from the University of Chicago, Argonne National Laboratory and the University of Wisconsin–Madison is deploying autonomous recording equipment in natural areas to eavesdrop on the animals. This project aims to help answer important scientific questions, such as which species are present and how their abundance changes over time.
Their long-term goal is to characterise natural soundscapes using artificial intelligence and to use that data as a baseline to measure how ecosystems are responding to climate change and other human-induced changes.
The new field of bioacoustics allows us to study biodiversity at a very large scale. By placing a few microphones in a forest, you can get exposure to a lot of different organisms occupying that forest without needing to detect them during fieldwork.
– Rajesh Sankaran, Computing Expert, Argonne National Laboratory
For decades, the only way for scientists to track long-term trends in animal populations over large areas was via time-intensive monitoring. Biologists would trek out into the field, take notes on what they saw, and return year after year. Then they would have to spend hundreds of hours processing data back in their labs to identify trends. However, passive acoustic biodiversity monitoring offers even bigger possibilities, thanks to technological advances that have allowed for far more efficient data processing and storage.
A computing architecture allows some data to be processed instantaneously, as it is recorded and stored. So, a recorder strapped to a tree could theoretically take advantage of this technology by filtering out non-animal sounds and storing only those that researchers are interested in. This both reduces the number of time researchers have to spend combing through data afterwards and saves huge amounts of storage space on the machines so they can record more hours of data uninterrupted.
By listening to the animals that are present, the scientists can also make inferences about those that are not present. In a healthy ecosystem, most of the acoustic space is typically occupied by one animal or another.
As soon as we start losing species, we start seeing gaps. That means that habitats change determines which species are going missing the reason why, can contribute insights that are important for reducing biodiversity loss. In a selectively logged forest, we might see a really big difference in that index of just how empty or full the forest is. What edge computing allows us to do is pare down what would be gigabytes or even petabytes of data to just the metric that we’re interested in.
– Asst. Prof. Eyal Frank, Environmental Eeconomist, Harris School of Public Policy, UChicago
Right now, the researchers are still testing their recording systems and data processing algorithms. They have planned to deploy some of the recorders in zoos—where they know all the species that are present—to test their model’s ability to recognise relevant sounds.
Testing out new algorithms and equipment setups in a local zoo is a necessary step before carrying out advanced experiments in the rainforest. Things should work perfectly at home to ensure that they will work in remote locations. Once testing is complete, the possibilities for natural experiments.
A collaboration between social scientists studying the impact of conservation policies and engineers, computer scientists and wildlife ecologists is key to the project’s success. The combination of all these fields and disciplines and expertise is needed to be able to solve this massive challenge. This interdisciplinary research allows researchers to explore a large gap in the understanding and quantification of biodiversity.
