Guidelines for the use of acoustic indices in environmental research

Ecoacoustics, the study of environmental sound, is a growing field with great potential for biodiversity monitoring. Audio recordings could provide a rapid, cost-effective monitoring tool offering novel insights into ecosystem dynamics. More than 60 acoustic indices have been developed to date, which reflect distinct attributes of the soundscape, (i.e. the total acoustic energy at a given location, including noise produced by animals, machinery, wind and rain). However, reported patterns in acoustic indices have been contradictory, possibly because there is no accepted best practice for the collection and analysis of audio recordings. Here, we propose: (a) guidelines for designing studies using audio recordings for the rapid assessment of multiple sites; and (b) a workflow for comparing recordings with seven of the most commonly used indices, permitting discrimination among habitat-specific soundscapes. We collected and analysed over 26,000 hr of recordings from 117 sites across a range of habitats in a human-modified tropical landscape in central Panama; an order of magnitude more recordings than used in previously published studies. We demonstrate that: (a) Standard error variance of indices stabilizes within 120 hr of recordings from a single location. (b) Continuous recording should be used rather than subsample recording on a schedule; sub sampling is a common practice but delays capture of site variability and maximizing total duration of recording should be prioritized. (c) Use of multiple indices to describe soundscape patterns reveals distinct diel and seasonal soundscape patterns among habitats. We advocate collecting at least 120 hr of continuous recordings per site, and using a range of acoustic indices to categorize the soundscape, including the Acoustic Complexity Index, Acoustic Evenness Index, Acoustic Entropy Index and the Normalized Difference Soundscape Index. Differences among habitat types can be captured if multiple indices are used, and magnitude of variance is often more important than mean values. The workflow we provide will enable successful use of ecoacoustic techniques for environmental monitoring.