If you were a miner in California during the Gold Rush, you might have dined on a California red-legged frog.
The largest native frog in the western United States, this Golden State denizen used to be found as far inland as the Sierra Nevada mountains and south, into Baja California. But overharvesting, predation by invasive bullfrogs and habitat loss took their toll on the frogs: Today, they're listed as threatened under the Endangered Species Act.
Over the past five years, a team of conservationists carefully translocated a population of these red-legged frogs, moving them from northwestern Mexico to two sites in California. Once they got there, though, they were stuck with another problem: how to monitor that population's growth.
Luckily, the California red-legged frog has a distinctive mating call that scientists can look out for. It's low-pitched and creaky, like the noise you get when you rub your finger on a balloon. But listening for them every night — and picking those calls out of the turkey calls and coyote howls and car horns of a night in Southern California — is a huge task, even for the most enthusiastic amphibian expert.
That's where AI comes in. Scientists can use special machine learning models to sort through thousands of hours of recordings, identifying the places where California red-legged frogs were heard and surveying their success. It's saving the conservation team time and money, so that they can focus on translocating more frogs in the future.
Want to hear more stories about critters or conservation? Let us know at shortwave@npr.org.
Listen to every episode of Short Wave sponsor-free and support our work at NPR by signing up for Short Wave+ at plus.npr.org/shortwave.
Listen to Short Wave on Spotify and Apple Podcasts.
This episode was produced by Hannah Chinn. It was edited by Rebecca Ramirez and fact-checked by Nathan Rott and Tyler Jones. Robert Rodriguez was the audio engineer.
Copyright 2025 NPR
