Iguanas from above: Citizen scientists provide reliable counts of endangered Galapagos marine iguanas from drone imagery

Abstract

Population surveys are vital for wildlife management, yet traditional methods often demand excessive time and resources, leading to data gaps for many species. Modern technologies such as drones can facilitate field surveys but may also increase data analysis challenges. Citizen Science (CS) can address this issue by engaging non-specialists for data collection and analysis. We evaluated CS for population monitoring using the endangered Galapagos marine iguana as a case study, assessing online volunteers ability to detect and count animals in aerial images. Comparing against a Gold Standard dataset of expert counts in 4345 images, we explored optimal aggregation methods from CS inputs, considering image quality and filtering data from infrequent and anonymous participants. During three phases of our project -- hosted on the Zooniverse platform -- over 13,000 volunteers made 1,375,201 classifications from 57,838 aerial images; each being independently classified 20 (phases 1 & 2) or 30 (phase 3) times. Volunteers achieved 68% to 94% accuracy in detecting iguanas, with more false negatives than false positives. Image quality strongly influenced accuracy; by excluding data from suboptimal pilot-phase images, volunteers counted with 90% to 92% of accuracy. For detecting presence or absence of iguanas, the commonly used majority vote aggregation approach (where the answer selected is that given by the majority of individual inputs) produced less accurate results than when a minimum threshold of five (from the 20/30 independent classifications) was used. For counting iguanas, HDBSCAN clustering yielded the best results. Excluding inputs from anonymous and inexperienced volunteers decreased accuracy. We conclude that online volunteers can accurately identify and count marine iguanas from drone images, though a tendency to underestimate warrants further consideration. CS-based data analysis is faster than manual counting but still resource-intensive, underscoring the need to develop a Machine Learning approach.