Chemical Fingerprints of New vs Weathered Plastics: A Machine Learning Approach.
5 affiliations
- 1Department of Chemistry and Biology, Toronto Metropolitan University, TorontoM5B 2K3, Canada.
- 2Department of Natural Science, Manchester Metropolitan University, ManchesterM1 5GD, U.K.
- 3Chemistry Matters Inc., CalgaryT2N 3P7, Canada.
- 4Department for Inorganic Environmental Chemistry, Helmholtz-Zentrum Hereon, Geesthacht21502, Germany.
- 5California State Water Resources Control Board, Sacramento, California95814, United States.
Abstract
Regulatory initiatives to mitigate plastic pollution face challenges in identifying microplastics and their sources. Recent advances in computational fingerprinting offer opportunities for the forensic investigation of plastic pollution sources. Here, we present an open-source computational workflow integrating multi-instrumental, nontargeted (organic and inorganic) data from three distinct mass spectrometry methods to evaluate two approaches for potential plastic pollution source tracking. The workflow includes a novel data imputation, normalization, and feature selection strategy with a Random Forest classifier applied to data sets of 42 pristine (store-bought) and 21 weathered (environmentally collected) plastics from U.S. retail products and California beaches. To develop a workflow for source identification, we first, evaluated an "Universal Fingerprint" approach, which tested whether chemical profiles from pristine, store-bought plastic products could be used to identify weathered environmental counterparts based on their chemical additive patterns. This approach yielded low classification accuracy due to high geographic and manufacturer-specific formulation variability for plastic products that the random forest model could not sufficiently resolve. Second, we evaluated a "Suspect-Source Comparison" approach that simulated a scenario where the chemical fingerprint of an environmentally sampled plastic was matched to the fingerprint of a suspect source. Under this paradigm, the workflow achieved a high classification accuracy across all platforms (up to 1.00 MCC for ICP-MS/MS and 0.79 for HPLC-QToF-MS). Additionally, we found that the different analytical techniques functioned best as complementary data sets to distinguish product categories, while combining all raw data sets prior to classification introduced excessive variability that hindered the classification. Our results demonstrate the feasibility of using relative chemical similarity to connect environmental plastics to potential local pollution sources. The presented workflow establishes a methodological foundation for localized source tracking, environmental litigation, and targeted regulatory monitoring.
Related
- Predicting Chemical Stressor Effects on Conjugative Plasmid Transfer Rates Using Machine Learning.
- Combined reinforcement mechanism of TEOS-barium oxalate-phosphate composite on weathered sandstone
- Additive topology governs structural degradation of weathered plastic
- Editorial: Biodegradation of plastics and their additives
- SCREEN-LCA: Ex-ante prioritization of bio-based pathways for chemicals and plastics under a climate-mitigation objective
BibTeX
@article{nguyen2026chemical,
title = {{Chemical Fingerprints of New vs Weathered Plastics: A Machine Learning Approach.}},
author = {Huy Nguyen and Eric Fries and David Jones and David Megson and Alexa Zonderman and Lars Hildebrandt and Scott Coffin and Daniel Pröfrock and Roxana Sühring},
journal = {Environmental science \& technology},
year = {2026},
month = sep,
doi = {10.1021/acs.est.6c03575},
url = {https://europepmc.org/article/MED/42916225},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Chemical Fingerprints of New vs Weathered Plastics: A Machine Learning Approach.
AU - Huy Nguyen
AU - Eric Fries
AU - David Jones
AU - David Megson
AU - Alexa Zonderman
AU - Lars Hildebrandt
AU - Scott Coffin
AU - Daniel Pröfrock
AU - Roxana Sühring
PY - 2026
DA - 2026/09/01
JO - Environmental science & technology
DO - 10.1021/acs.est.6c03575
UR - https://europepmc.org/article/MED/42916225
AB - Regulatory initiatives to mitigate plastic pollution face challenges in identifying microplastics and their sources. Recent advances in computational fingerprinting offer opportunities for the forensic investigation of plastic pollution sources. Here, we present an open-source computational workflow integrating multi-instrumental, nontargeted (organic and inorganic) data from three distinct mass spectrometry methods to evaluate two approaches for potential plastic pollution source tracking. The workflow includes a novel data imputation, normalization, and feature selection strategy with a Random Forest classifier applied to data sets of 42 pristine (store-bought) and 21 weathered (environmentally collected) plastics from U.S. retail products and California beaches. To develop a workflow for source identification, we first, evaluated an "Universal Fingerprint" approach, which tested whether chemical profiles from pristine, store-bought plastic products could be used to identify weathered environmental counterparts based on their chemical additive patterns. This approach yielded low classification accuracy due to high geographic and manufacturer-specific formulation variability for plastic products that the random forest model could not sufficiently resolve. Second, we evaluated a "Suspect-Source Comparison" approach that simulated a scenario where the chemical fingerprint of an environmentally sampled plastic was matched to the fingerprint of a suspect source. Under this paradigm, the workflow achieved a high classification accuracy across all platforms (up to 1.00 MCC for ICP-MS/MS and 0.79 for HPLC-QToF-MS). Additionally, we found that the different analytical techniques functioned best as complementary data sets to distinguish product categories, while combining all raw data sets prior to classification introduced excessive variability that hindered the classification. Our results demonstrate the feasibility of using relative chemical similarity to connect environmental plastics to potential local pollution sources. The presented workflow establishes a methodological foundation for localized source tracking, environmental litigation, and targeted regulatory monitoring.
SN - 0013-936X
SN - 1520-5851
ER -