Related Experiment Video
Updated: Jun 20, 2026
Protocol for Microplastics Sampling on the Sea Surface and Sample Analysis
Published on: December 16, 2016
Rapid Identification of Marine Plastic Debris via Spectroscopic Techniques and Machine Learning Classifiers
Anna P M Michel1, Alexandra E Morrison1, Victoria L Preston1,2
1Department of Applied Ocean Physics and Engineering, Woods Hole Oceanographic Institution, Woods Hole, Massachusetts 02543, United States.
Accurate identification of plastic types is crucial for understanding environmental plastic pollution. Attenuated total reflectance-Fourier transform infrared spectroscopy (ATR-FTIR), near-infrared (NIR) reflectance spectroscopy, and laser-induced breakdown spectroscopy (LIBS) show high success rates when combined with machine learning.
Area of Science:
- Environmental Science
- Analytical Chemistry
- Materials Science
Background:
- Macro- and micro-plastic debris pose significant environmental challenges.
- Effective in situ identification and characterization methods are needed for plastic debris analysis.
- Understanding plastic fate and transport requires reliable analytical techniques.
Purpose of the Study:
- To compare the accuracy of four spectroscopic techniques for plastic identification.
- To evaluate the performance of machine learning classifiers in plastic analysis.
- To assess methods for both consumer plastics and marine plastic debris (MPD).
Main Methods:
- Comparison of Attenuated Total Reflectance-Fourier Transform Infrared Spectroscopy (ATR-FTIR), Near-Infrared (NIR) reflectance spectroscopy, Laser-Induced Breakdown Spectroscopy (LIBS), and X-ray Fluorescence (XRF) spectroscopy.
- Coupling spectroscopic techniques with seven classification methods, including machine learning algorithms.
- Testing accuracy on both standard consumer plastics and environmentally weathered marine plastic debris.
Main Results:
- High success rates for consumer plastic identification using machine learning: ATR-FTIR (99%), LIBS (97%), NIR (91%), XRF (70%).
- Similar or slightly lower success rates for marine plastic debris: ATR-FTIR (99%), NIR (81%), LIBS (76%), XRF (66%).
- Environmental weathering impacts the accuracy of plastic identification, particularly for LIBS and XRF.
Conclusions:
- ATR-FTIR, NIR reflectance spectroscopy, and LIBS, when coupled with machine learning, are effective for identifying both consumer and environmental plastic types.
- These methods provide robust analytical approaches for plastic debris characterization.
- Further research may be needed to optimize techniques for weathered MPD.
