Contrasting the efficiency of imaging systems for mesozooplankton indicators across Pacific and Atlantic coastal ecosystems

Mesozooplankton have a pivotal role in marine food webs, linking primary producers to higher trophic levels. Their abundance and traits serve as key indicators of ecosystem structure and function, making them essential components of long-term ocean monitoring. However, the need to monitor biodiversity and functional traits, combined with their pronounced spatial and temporal variability, requires extensive sampling and presents significant laboratory bottlenecks and cost-related challenges. Imaging instruments, combined with automated image classifiers such as Ecotaxa, offer a promising solution by enabling high-throughput, cost-effective processing of large numbers of samples, while also providing highly precise trait measurements previously unattainable with traditional methods. In this study, we compare the performance of human-sorted microscopy, human-sorted images and computer-sorted images across three contrasting coastal ecosystems on Canada's Pacific and Atlantic coasts. First, we demonstrated that upfront investment in identifying a larger number of images contributed to the development of robust regional image libraries, which significantly enhanced the performance of automated classifiers (e.g., mean F1 score = 0.54 with up to 200 images per taxon and 0.68 with up to 5000 images per taxon). Results showed that automated image classification performance varies with specimen characteristics such as symmetry, geodesic thickness, and taxa richness. We then assessed how each method captures local mesozooplankton diversity and altered key ecological indicators. Based on observed ecosystem-specific differences, we provide recommendations for optimizing classification workflows in relation to local diversity patterns. This study provides large-scale empirical evidence that investing in the development of regional image libraries enhances the scalability and accuracy of coastal ecological assessments. These emerging digital assets have the potential to significantly advance ecosystem monitoring and management.