Scientific American Machine-learning algorithms can quickly process thousands of hours of natural soundscapes Advertisement We can learn a lot from nature if we listen to it more—and scientists around the world are trying to do just that. From mountain peaks to ocean depths, biologists are increasingly planting audio recorders to unobtrusively eavesdrop on the groans, shrieks, whistles and songs of whales, elephants, bats and especially birds. This summer, for example, more than 2,000 electronic ears will record the soundscape of California’s Sierra Nevada mountain range, generating nearly a million hours of audio. To avoid spending multiple human lifetimes decoding it, researchers are relying on artificial intelligence.