Lecturer
Supervisor of Master's Candidates
Hits:
Impact Factor:7.2
DOI number:10.1016/j.jece.2026.122269
Affiliation of Author(s):长春工业大学
Journal:Journal of Environmental Chemical Engineering
Key Words:Microplastics Artificial intelligence Machine learning Detection Fate Ecological effects
Abstract:Microplastics (MPs) research faces critical challenges in detection, source identification, and risk assessment, where traditional methods are limited by efficiency and analytical capacity for complex systems. This review systematically evaluates the integration of artificial intelligence (AI) and machine learning (ML) across the entire MPs research chain. Key technological advances are examined, including computer vision for automated morphological analysis, deep learning for vibrational spectroscopy interpretation, and AI-assisted processing of Py-GC/MS data. Furthermore, the role of AI in integrating multi-source data for pollution source tracking, environmental fate prediction, and emerging risk dimensions is explored. Despite significant potential, widespread adoption remains constrained by data standardization issues, limited model generalizability, interpretability challenges, and insufficient integration with physical mechanisms. Future directions include developing standardized databases, domain-specific foundational models, explainable AI, physics-informed ML approaches, and intelligent decision support platforms. This review aims to provide a roadmap for advancing data-driven MPs research and informing precise pollution management strategies.
Indexed by:Journal paper
Volume:14
Issue:3
Page Number:122269
Translation or Not:no
Date of Publication:2026-03-01
Included Journals:SCI
Links to published journals:https://doi.org/10.1016/j.jece.2026.122269
