Advancing microplastic analysis in the era of artificial intelligence: From current applications to the promise of generative AI

The proliferation of microplastics (MPs) in aquatic and terrestrial environments poses significant threats to ecosystems and human health. Over the past 20 years, significant efforts have been dedicated to understanding the distribution, sources, and impacts of MPs. However, traditional methods for the detection and analysis of MPs rely on labor-intensive and time-consuming techniques, often lacking the needed precision. Recently, artificial intelligence (AI) has emerged as a transformative tool in environmental science, offering innovative solutions to enhance the efficiency and accuracy of MP analysis. Despite significant scientific advancements, there is a lack of critical review that consolidates the key applications of AI in MP analysis, synthesizes knowledge gained, and navigates for future research directions. This review is the first to thoroughly explore the exciting role of AI across the entire life cycle of MP analysis—from collection to characterization, dynamic modeling, impact assessment, and management of MP pollution. Specifically, AI-driven autonomous drones and robotics have emerged as promising solutions to revolutionize MP collection practices. Computer vision systems provide robust solutions for the identification and quantification of MPs in diverse environmental matrices. Additionally, data-driven modeling using machine-learning and deep-learning techniques facilitates accurate evaluation of MP pollution levels and their impacts, facilitating the design of effective management strategies. Despite these advancements, several knowledge gaps remain, including data scarcity and quality issues; the readiness of the AI models; and model interpretability, transparency, and reproducibility issues. Addressing these gaps requires the development of standardized protocols for improved data infrastructure, the adoption of more advanced and groundbreaking AI tools (such as generative AI), and the encouraging of multidisciplinary collaborations. Through these efforts, AI has the potential to revolutionize MP research, leading to a more comprehensive and effective response to MP pollution.