Opinion | This ‘Shazam’ for Birds Could Help Save Them – The New York Times

Source: Opinion | This ‘Shazam’ for Birds Could Help Save Them – The New York Times

NASHVILLE — I spent my entire childhood playing in the woods and meadows of rural Alabama. The world back then was lush and green: cooled by creeks, carpeted by pine needles, attended by birdsong. In those days there were nearly three billion more birds in North America than there are today, and my young days played out beneath the sound of their music.

The staggering loss of birds — nearly a third of them since 1970 — is due to human behavior: to climate change, to deforestation and ecosystem fragmentation, to insecticides and free-roaming pets, to light pollution in our skies and microplastics in our waterways, to glass-encased skyscrapers protruding into migratory flyways, among other choices that favor our own convenience over the lives of our wild neighbors.

I can’t help but wonder how much of the blame lies, too, in indifference, our failure even to notice what we’ve lost. Birds can be secretive creatures, staying high in the treetops or deep in the underbrush. Even those in plain sight often move startlingly quickly, appearing as hardly more than a flash of color, a blur of wings. Except for the background sound of birdsong, many people are never aware of how many birds — or how few — they share the world with.

Apps like iNaturalist from National Geographic and the California Academy of Sciences help to close that gap, functioning as both electronic field guides and vast data-collection devices. They learn as we learn, improving with every photo and map pin we upload, helping experts understand a planet undergoing profound change. But what of the vast number of birds we never see, those we only hear? To offer that feature — one that accurately and consistently recognizes birds by sound alone — would be the birding equivalent of finding the Holy Grail.

Last month, the Cornell Lab of Ornithology released an updated version of its Merlin Bird ID app, which allows users to identify birds by song. There are other voice-recognition apps for birds, but they are accurate barely 50 percent of the time. Though Merlin doesn’t claim to be 100 percent accurate, it comes very close.

I watched as Merlin rolled out the names of bird after bird — tufted titmouse, European starling, Carolina chickadee, northern cardinal, American crow, white-breasted nuthatch, eastern towhee, house wren, American goldfinch, blue jay, eastern bluebird, American robin, Carolina wren, house finch. It didn’t miss a single one.

What amazed me was not merely the accuracy of the ID but also the way the app untangled the layers of song, correctly identifying the birds that were singing in my yard, as well the birds that were singing next door and the birds that were singing across the street. If the same bird sang a second time, the app highlighted the name it had already listed. Watching those highlights play across the growing list of birds was almost like watching fingers fly across a piano keyboard.