Machine learning-integrated droplet microfluidic system for accurate quantification and classification of microplastics.
Journal:
Water research
PMID:
39842213
Abstract
Microplastic (MP) pollution poses serious environmental and public health concerns, requiring efficient detection methods. Conventional techniques have the limitations of labor-intensive workflows and complex instrumentation, hindering rapid on-site field analysis. Here, we present the Machine learning (ML)-Integrated Droplet-based REal-time Analysis of MP (MiDREAM) system. Utilizing a compact peristaltic pump, the system achieved high-throughput droplet generation (> 200 Hz) while encapsulating MPs in uniform droplets (142 ± 8 μm). A high-resolution complementary metal oxide semiconductor (CMOS) sensor combined with an optimized YOLO v8 ML model was employed for real-time analysis, achieving a mean average precision (mAP) of 0.982 and an area under the curve (AUC) of 97.64 %. Comparative analysis with hemocytometer counting and surface-enhanced Raman spectroscopy (SERS) demonstrated the superior performance of the system, demonstrating high correlation (R² = 0.9965) and minimal deviation (6.36 %) from theoretical values. The system accurately classified MPs of different sizes, achieving accuracies of 95.4 %, 87.9 %, 95.3 %, 85.3 %, and 92.5 % for 3, 5, 10, 30, and 50 μm particles, respectively. Validation with real-world water samples confirmed the system adaptability, while maintaining high detection accuracy (> 90 %). The on-site field tests of MiDREAM system also demonstrated its robust performance for environmental monitoring in a variety of environments. Therefore, our portable and integrated MiDREAM system offers a promising solution for real-time environmental monitoring applications.