Rapid detection of colored and colorless macro- and micro-plastics in complex environment via near-infrared spectroscopy and machine learning

• Published in: Journal of environmental sciences (China) 2025-01, Vol.147, p.512-522
• Main Authors: Zou, Hui-Huang, He, Pin-Jing, Peng, Wei, Lan, Dong-Ying, Xian, Hao-Yang, Lü, Fan, Zhang, Hua
• Format: Article
• Language: English
• Subjects: Color; Colorless microplastics; Discriminant Analysis; Environmental Monitoring - methods; Least-Squares Analysis; Machine Learning; Near-infrared hyperspectral imaging; Partial least squares discriminant analysis; Plastic identification; Plastics - analysis; Spectroscopy, Near-Infrared - methods
• ISSN: 1001-0742
• DOI: 10.1016/j.jes.2023.12.004

•PLS-DA model showed the potential to monitor colorless and colored microplastics.•The color had limited influence on plastic classification except for black sample.•Two-stage detection of colorless plastic in org-&inorganic background was proposed.•Colorless PP, PET and PS with thickness of 30–76µm were successfully identified. To better understand the migration behavior of plastic fragments in the environment, development of rapid non-destructive methods for in-situ identification and characterization of plastic fragments is necessary. However, most of the studies had focused only on colored plastic fragments, ignoring colorless plastic fragments and the effects of different environmental media (backgrounds), thus underestimating their abundance. To address this issue, the present study used near-infrared spectroscopy to compare the identification of colored and colorless plastic fragments based on partial least squares-discriminant analysis (PLS-DA), extreme gradient boost, support vector machine and random forest classifier. The effects of polymer color, type, thickness, and background on the plastic fragments classification were evaluated. PLS-DA presented the best and most stable outcome, with higher robustness and lower misclassification rate. All models frequently misinterpreted colorless plastic fragments and its background when the fragment thickness was less than 0.1mm. A two-stage modeling method, which first distinguishes the plastic types and then identifies colorless plastic fragments that had been misclassified as background, was proposed. The method presented an accuracy higher than 99% in different backgrounds. In summary, this study developed a novel method for rapid and synchronous identification of colored and colorless plastic fragments under complex environmental backgrounds. [Display omitted]