Large-Scale Coastal Marine Wildlife Monitoring with Aerial Imagery

Abstract

Monitoring coastal marine wildlife is crucial for biodiversity conservation, environmentalmanagement, and sustainable utilization of tourism-related natural assets.Conducting in situ censuses and population studies in extensive and remote marine habitatsoften faces logistical constraints, necessitating the adoption of advanced technologiesto enhance the efficiency and accuracy of monitoring efforts. This study investigates theutilization of aerial imagery and deep learning methodologies for the automated detection,classification, and enumeration of marine-coastal species. A comprehensive datasetof high-resolution images, captured by drones and aircrafts over southern elephant seal(Mirounga leonina) and South American sea lion (Otaria flavescens) colonies in the ValdésPeninsula, Patagonia, Argentina, was curated and annotated. Using this annotated dataset,a deep learning framework was developed and trained to identify and classify individualanimals. The resulting model may help produce automated, accurate population metricsthat support the analysis of ecological dynamics. The resulting model achieved F1 scoresof between 0.7 and 0.9, depending on the type of individual. Among its contributions,this methodology provided essential insights into the impacts of emergent threats, such asthe outbreak of the highly pathogenic avian influenza virus H5N1 during the 2023 australspring season, which caused significant mortality in these species.