The Future of Conservation Is Basically Shazam for Wildlife

Identifying the sounds of what’s happening in nature might just help researchers save it.

Black-and-white bird in one panel and mountains in the other panel
The Atlantic. Sources: Danny Hofstadter / Biographic; Marky Mutchler / Cornell Lab / Biographic.

This article originally appeared in longer form in bioGraphic.

The eastern black rail, a subspecies of bird that’s scattered in clusters along America’s eastern coastlines, is one of the most elusive creatures a wildlife biologist can choose to study. Adults are the size of a human hand, and are dark and shy, the better to hide among the dense marsh grasses under which they skulk and scurry. The birds are maddeningly difficult to lay eyes on.

Hard-core birders try in vain to check this subspecies off their life lists; those who do usually hear the bird rather than see it. Professionals do little better: Christy Hand, a biologist with the state of South Carolina who’s been studying the eastern black rail for nearly 10 years, has seen only a few, each for just a few seconds.

For the past decade, Hand has pursued these minute birds throughout her study area in the ACE Basin, named for the Ashepoo, Combahee, and Edisto Rivers and one of the largest undeveloped estuaries along the U.S. Atlantic Coast. Though she is still unsure exactly how many eastern black rails live there—a few score? a few hundred?—they’ve inhabited her mind.

“People working with rails,” she says, “we tend to be a bit quirky. I dream about the rails. I don’t dream about wood storks so much, because I can just look at them. But with the rails, I’m always wondering what’s going on. I get these little glimpses, and I think my brain’s trying to fill in the gaps.” In her mind she hears their distinctive kickee-doo call.

The call is a great boon to Hand’s work, as it’s the easiest way to locate the birds. Yet taking census of rails by sound is problematic, because they don’t seem to have anything like a set schedule of when they are most vocal. Day, night, dawn, dusk? They seem to favor no hour.

To get a handle on the birds, Hand has had to try new ways to find them and learn how they live. For a while, she would go into their habitat and play a recording of a black rail, then listen for replies. She’d get some. But she hoped for something better and less intrusive.

About five years ago, the falling prices of autonomous recording units, or ARUs, made it practical to leave them in the field to capture all the racket near a given spot. The problem then became how to go through all that audio. Listening to it in real time would require hundreds of hours of painstaking work by people skilled at identifying birds by call—not really an option for a small team in a modestly funded state operation. So Hand tried a couple of computerized sound-analysis systems known as call recognizers. These artificial-intelligence tools analyze sonograms of field recordings to distinguish a specific bird’s call, amidst the clangor of other birds, bugs, frogs, cars, and planes that fill the marsh air with noise.

In late 2020, Hand heard about BirdNET, a call-recognition app created by a young programmer named Stefan Kahl of the Cornell Lab of Ornithology. The app creates a so-called deep neural net—an artificial-intelligence algorithm that takes inspiration from the human brain. It excels at discerning, in complex sonograms like those in Hand’s recordings, the distinctive shapes of individual species’ songs, calls, grunts, buzzes, croaks, barks, and hisses. It streamlined into one process the multiple steps of Hand’s previous tool set and could analyze hundreds of hours of sound in just a few days.

This past spring, Hand acquired 16 ARUs that her team deployed across six wetland areas in the ACE basin, where habitat management for rails was already ongoing or planned. The battery-powered units, each the size of a small paperback book, record several hours a day in the morning and evening. With these devices, Hand is finally able to gather enough data from enough points to begin to understand the rail’s distribution, as well as the effects of the department’s management practices, such as adjusting water levels in impoundments and strategically burning vegetation to create rail-friendly ground cover.

Hand is also hoping to better understand where and when the rails are breeding and raising young, as well as whether the young are living long enough to fledge. In this way she’d be getting an unprecedentedly detailed look at the birds’ life histories and how they use the different environments within the ACE basin. Although these are early days, the ARUs and BirdNET are opening new vistas for her research.

Hand is a pioneer of sorts, but she’s hardly the only scientist or conservationist to deploy ARUs and call recognizers. Over the past few years, these transformative tools have begun to take the field of bioacoustics into new and exciting terrain, both figuratively and literally, largely due to the speed with which they can gather and process information. Research teams are now using recorders to study such things as the dynamics of aggressive loon calls; monitor shipping lanes for whales so vessels can reroute around them; and observe how fish and coral larvae locate their home reef by perceiving its distinctive sound. They can even perform a sort of quickie health exam on ecosystems by analyzing how much of the sound-frequency spectrum is occupied by animal vocalizations.

The granularity of these types of data—their density in both space and time—is the key to their new power. The ability to keep tabs on species’ presence in many places constantly, rather than occasionally, essentially creates a giant new instrument exquisitely sensitive to change at both population and ecosystem levels. It’s as if a large collection of lenses were merged into one giant lens that could see things the smaller ones could not.

One day this past June, I took a walk with the ecologist Aaron Weed around his workplace, the steeply hilled, sweetly forested 550 acres of Marsh-Billings-Rockefeller National Historical Park, in Woodstock, Vermont. This park’s woodlands are part of an almost contiguous forest stretching across nearly 30 million acres in northern New England and New York State. In the 1800s, settlers and sheep farmers cut this huge forest hard, clearing 80 percent of the forest in some places. Since then, partly through care and partly through benign neglect, the woods have rebounded.

Today, the ecosystem faces a century in which a different human-made force, climate change, threatens to alter the species composition and health of the forest in broad, fundamental, and sometimes troubling ways. Weed is part of a team creating a regional system of bioacoustic observations to track—and help predict and manage for—these coming changes. This venture, the Northeast Temperate Inventory and Monitoring Network, coordinates studies and data for 13 National Park Service holdings in the Northeast, from Acadia in the far north to a small holding in Morristown, New Jersey.

A significant focus of this work is monitoring bird presence within these boundaries, as one of the ”vital signs” of ecosystem health. Marsh-Billings hosts more than 125 bird species, including bobolinks and waterthrush, over the course of a year. For years, the most rigorous tallies of these populations have come from volunteers who do spring “point counts,” going at dawn to specific locations and writing down every bird species they recognize by sight or sound in 10 minutes. Yet these point counts yield only a single day’s worth of data each year, and their accuracy varies with the expertise of the volunteers.

In contrast, the ARUs that Weed deploys can tally bird presence from day to day, providing a far more dynamic picture of species presence. These ARUs, called Swifts, are similar to those used by Christy Hand: Each is a box of electronics that records every sound within earshot, every day between 5 and 10 a.m. and 7 and 8:30 p.m., as long as the temperature is between –31 and 122 degrees Fahrenheit.

By listening in on birds’ daily activities in multiple locations—not just this park but the others in the 13-site monitoring network—Weed and his collaborators will gather a richer read on how birds use specific types of woodlands. They will see, for instance, how populations grow, shrink, or shift location as the ash borer decimates ash stands, or how birds respond to various forest-management practices.

And as an altered climate imposes a fundamental transformation of these forests, Weed and his colleagues should be able to more readily see and hear birds and other species adapt (or fail to adapt) to the changing landscape.

Perhaps the busiest user of these tools and techniques is the Cornell Lab of Ornithology’s K. Lisa Yang Center for Conservation Bioacoustics, a department that has long helped lead the field. The lab today is rapidly expanding, thanks to a $24 million endowment from Yang, a philanthropist, in 2021 (which changed the center’s name to its current one). Plenty of bioacoustics conservation projects have been and are being done without Cornell’s involvement. But the center’s experience, funding, and tool development have made it one of the biggest players in the field.

And its largest project so far stands out as a prime demonstration of the discipline’s growing power and potential. This project began several years ago, high in California’s Sierra Nevada, with a simple question: Was the barred owl, an invasive species, a major factor in the ongoing decline of the native California spotted owl?

The question of whether barred owls threatened spotted owls in general was not a new one. Teams in both the Cascades of Oregon and the coastal mountains of northern California had already discovered that barred owls—which were originally limited to eastern North America until changing land use and other factors allowed them to expand westward—were bullying and driving out northern spotted owls. One team of researchers had shown in 2016 that if you removed barred owls from the disputed area (by shooting them), spotted owls would quickly reoccupy that area and resume successful breeding. But that first experiment, the paper concluded, needed to be confirmed by additional studies; if that happened, the authors predicted, “this could be the foundation for development of a long-term conservation strategy for northern spotted owls."

In the northern Sierra Nevada, meanwhile, the California spotted owl also appeared to be threatened by an expanding barred-owl population. Censuses showed that the California spotted-owl population was steadily declining. Meanwhile, the barred-owl intrusion continued southward. Many biologists worried that the California spotted owl would soon follow its northern cousin into federal threatened status. And because barred-owl intrusions can happen quickly, time was of the essence.

One of the biologists researching this issue was Zach Peery, from the University of Wisconsin at Madison. Peery had been tracking the spotted owl’s decline since 2001, and he knew that a team in the state of Washington had been experimenting with ARUs to help identify northern spotted and barred owls there. Peery and Connor Wood, one of his Ph.D. students at the time, aimed to do something similar in the Sierras, but on a much larger scale. Their goal was to collect “actionable data” from the majority of critical spotted-owl habitats in California—about 2,300 square miles, close to twice the area of Rhode Island—a feat that would have been unthinkable before 2016.

Having heard from the Washington team about the Center for Conservation Bioacoustics, Peery and Wood contacted the director, Holger Klinck, to see what he would recommend. Klinck said he might have just the thing: lightweight, easy-to-deploy, relatively inexpensive autonomous recorders that could be left in the field for weeks. Perhaps more important in making the project viable, the center had also created a software package called Raven that could be calibrated to recognize specific bird songs and calls amid the forest soundscape.

Based on their understanding of typical spotted- and barred-owl densities and the sizes of their territories, the researchers concluded that they would need some 100 ARUs rotated through 167 sites. The plan was to have Wood and five field technicians take the Swifts, strap them to trees scattered in a randomized pattern around the spotted owl’s critical habitat over two consecutive summers, and see if the barred owls were indeed taking over the spotted owl’s terrain. If so, the uncertainty would be resolved and the bloody but necessary large-scale removal of an invasive species could be carried out.

For weeks Wood and his team set up the Swifts; deployed them; visited them a week later to switch out their batteries, remove their SD cards, and swap in fresh ones; then moved them to new sites. By the end of the first summer, the team returned to Madison with some 49,000 hours of forest noise.

Finally, after manually reviewing all apparent detections, Wood and his colleagues were able to produce a precise map of every “occupancy,” or sonic appearance, of a spotted or barred owl. The map showed that across this enormous study area, barred owls had encroached upon about 8 percent of the spotted owl’s viable habitat in California.

The next year, 2018, the research team expanded its operation with more surveys and equipment, returning that fall with an additional 145,000 hours of audio. That produced another map of the owls’ territories. The picture was not pretty: The second map showed that the barred owl had expanded its share of the spotted owl’s preferred habitat to 21 percent—a 163 percent increase in a single year.

In other words, the barred owl suddenly occupied a fifth of the California spotted owl’s best habitat and was likely spreading. The data, Wood would tell me later, could not have been clearer. The barred owl was taking over. And it was going to wipe the spotted owl off the map.

That winter, in February 2019, when Wood presented the team’s findings to the annual meeting of the Western Section of the Wildlife Society—a group that had been monitoring and debating the owls’ fates for more than two decades—the conclusion was immediate: Everyone now acknowledged that the barred owls in the study area had to go.

Within weeks, the U.S. Fish and Wildlife  Service and private timber-company landowners agreed on a barred-owl “fatal removal” campaign, which was executed that spring both on federal and private land. It was at times anguish-filled work, but a year later, barred owls inhabited just 3 percent of the disputed habitat, and the California spotted owl had recolonized 56 percent of its former range.

While ongoing management of barred owls in the region will almost certainly be necessary, the peer-reviewed study published by Wood and others concluded that the intervention had “averted the otherwise likely extirpation of California spotted owls” in the region. At the same time, it had demonstrated the power of bioacoustic tools to gather actionable data at a large scale in a short period of time, and to capture real-time dynamic events like the displacement of one species by another.

The growing ease and falling cost of bioacoustic technologies are creating a wildlife-and-ecosystem science that’s not just faster and more powerful but more inclusive. Several Yang Center programs, for instance, are providing training and equipment for local communities at remote sites in Asia, Central America, Africa, and other biodiverse spots. These investigations range from the welfare of key species to the enforcement of laws regulating logging, construction, and hunting.

At all of these locations, Yang Center researchers are turning some of their most remote projects into learning centers to give Indigenous research communities deep grounding in the operations and possibilities of these tools. The Yang Center calls this “capacity building,” and it’s one of the pillars of the Center’s mission, along with research and technology development.

Klinck and his Yang Center colleagues want to enable researchers of all origins and paths to pursue the many kinds of investigations that new bioacoustics tools make possible. To this end, Yang Center biologists are creating year-long programs in the use of ARUs, BirdNET, and other bioacoustic technologies, as well as study design, so that local collaborators are able to both use the tools themselves and teach others to do so. The goal is not only to develop collaborators but to mentor a new generation of independent researchers.

In Africa, for instance, the Yang Center’s long-running Elephant Listening Project uses ARUs to eavesdrop on elusive forest elephants and identify gunshots of poachers. It has helped train an independent team in the Republic of Congo that is running crucial aspects of a 50-site acoustic grid in the more-than-1,500-square-mile Nouabalé-Ndoki National Park. Working with the Wildlife Conservation Society, the Elephant Listening Project is also establishing an analysis and training hub in central Africa with solar-power systems and high-performance computers to process the acoustic data, and staff that can run the algorithms to detect elephants and gunshots. This hub will serve as a central processing and training center for other field teams running bioacoustic projects around the region, and will invite students from the region to work on independent research projects there. Here again, the idea is to replace the Yang Center as the hub, moving analysis capacity into the hands and lands of local people.

This distributed capacity highlights one of the great powers of the new bioacoustic technology, which is its fluid scalability. ARUs and call recognizers such as BirdNET can work at anything from a one-site operation all the way up to ecosystem and landscape scales and still be manageable both in the field and in the lab or office. “If we really want to have a global impact,” says Klinck, “we cannot be the bottleneck. It’s not scalable if people can’t do it for themselves.”