Use of Artificial Intelligence (AI) in Meso - zooplankton (Copepod) research: Applications, advances and future perspectives

Abstract

Copepods dominate meso-zooplankton communities in marine and freshwater systems and form a critical trophic bridge between primary producers and higher consumers, thereby regulating secondary production, carbon flux, and nutrient cycling. Escalating marine pollution, including microplastics, petroleum hydrocarbons, heavy metals, and eutrophication-driven harmful algal blooms and their byproducts, threatens these keystone organisms by impairing feeding, reproduction, and survival, with cascading effects on ecosystem stability and fisheries resources. Yet, conventional monitoring based on net sampling, microscopy, and expert taxonomy remains laborintensive, time-consuming, and insufficient for resolving large-scale, long-term pollution impacts. Artificial intelligence (AI) has emerged as a transformative solution, enabling rapid, automated, and scalable assessment of copepod communities and their environmental drivers. This review synthesizes recent advances in machine learning and deep learning for automated species identification, image-based classification, ecological modeling, and distribution forecasting, alongside AI-powered spatiotemporal imputation and prediction of chlorophyll-a and water-quality indicators to diagnose habitat quality and pollution stress. Approaches such as convolutional neural networks, ensemble learning, generative models, and real-time imaging systems substantially improve detection accuracy, data completeness, and predictive performance. Despite challenges related to training data, sensor integration, and model generalization, AI-driven frameworks offer unprecedented capacity for continuous monitoring and early warning. Integrating these technologies into marine pollution management will strengthen biodiversity conservation, ecosystem resilience, and evidence-based coastal governance.