Inferring bird communities on remote freshwater lakes through time-lapse imagery

Assessing bird diversity and associated ecological patterns in remote freshwater lakes presents challenges that require innovative approaches. Here, we evaluated the utility of time-lapse images from camera traps for this purpose using two lakes in Haida Gwaii, British Columbia, Canada. We consider four key factors: (1) manual versus automated image processing, (2) data validation through in-person observations, (3) the ability of time-lapse data to capture known ecological patterns, and (4) variation in sampling effort. We find that (1) MegaDetector, a common AI approach, is not effective at detecting birds from time-lapse images —necessitating manual screening, (2) relative bird abundances were correlated between time-lapse and in-person observer data, (3) time-lapse data capture previously documented ecological variation in space and time, and (4) sampling effort per camera trap can be, under certain scenarios, scaled down, but camera trap position and time-lapse frequency greatly influence bird detectability. Our research builds on the few previous studies that use time-lapse imagery to detect birds, and our work is the first to focus on detecting ecological patterns on freshwater lakes in remote landscapes. Camera trap technologies can shed light on avifauna in remote freshwater lakes, but additional developments are needed to maximize utility of such applications.