Passive acoustic monitoring paired with machine learning outperforms playback surveys for a rare and cryptic species, the Black-billed Cuckoo (Coccyzus erythropthalmus)

Monitoring rare and cryptic species presents unique challenges and is of high importance for conservation practitioners. In this study, we evaluate the use of in-person playback surveys and passive acoustic monitoring for a rare and cryptic avian species, the Black-billed Cuckoo (Coccyzus erythropthalmus). We compared the two methods in terms of detection probability from one survey season and estimated monitoring costs over a 3-year project period and found that passive acoustic monitoring delivers higher detection probability for lower costs than playback surveys. These results are driven by our efficient use of a machine learning classifier to extract acoustic signals of our target species and the remote nature of our study system. As practitioners look to scale up monitoring efforts for rare and cryptic species to meet today's conservation challenges, our study presents an informative comparison of two commonly applied monitoring methods within contexts shared by many geographic areas and taxa.