Harnessing Artificial Intelligence for Microplastic Pollution Control in Lakes: Detection, Prediction and Removal

Abstract

Microplastic (MP) contamination in freshwater systems has become a pressing global concern. Lakes, as relatively closed aquatic environments, act as long-term sinks for microplastics and serve as critical indicators of human-induced environmental change. Traditional monitoring and removal methods are limited by labor intensity, cost, and the inability to provide real-time data. Recent advancements in artificial intelligence (AI) are revolutionizing how microplastic pollution in lakes is detected, modeled, and mitigated. AI enables automated identification, classification, and prediction of microplastic behavior using tools such as computer vision, remote sensing, and machine learning algorithms. This review synthesizes current research on AI’s role in addressing lake-based microplastic pollution, including detection and characterization methods, predictive modeling of microplastic fate and transport, and AI-assisted removal systems. It also identifies challenges, such as data scarcity, model generalization, and hardware efficiency, and outlines future directions for integrating AI-driven solutions into environmental monitoring frameworks. The findings highlight AI’s transformative potential for achieving sustainable microplastic management in freshwater ecosystems