Chemical Fingerprints of New vs Weathered Plastics: A Machine Learning Approach
Huy Nguyen, Eric Fries, David Jones, David Megson, Alexa Zonderman, Lars Hildebrandt, Scott Coffin, Daniel Pröfrock, Roxana Sühring · 2026
Read Chemical Fingerprints of New vs Weathered Plastics: A Machine Learning Approach by Huy Nguyen, Eric Fries, David Jones, David Megson, Alexa Zonderman, Lars Hildebrandt, Scott Coffin, Daniel Pröfrock, Roxana Sühring (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13614197.txt.
Description
Huy Nguyen and co-authors published this 2026 study on identifying plastic pollution by its chemical fingerprint. Regulators chasing microplastics need to know not just what a fragment is but where it came from. The team built an open-source workflow fusing data from three mass spectrometry methods, organic and inorganic, and trained a random forest to read the combined signature.
Forty-two store-bought plastics and twenty-one weathered ones from California beaches supplied the test. A universal fingerprint, matching beach fragments to retail products by additive patterns, classified poorly: recipes vary too much by maker and place. A suspect-source comparison, checking a fragment against a known candidate source, worked better. The authors conclude plastic forensics is viable case by case, not as a universal lookup, a useful limit for enforcement hopes.
Catalog record
| CREATOR | Huy Nguyen, Eric Fries, David Jones, David Megson, Alexa Zonderman, Lars Hildebrandt, Scott Coffin, Daniel Pröfrock, Roxana Sühring |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 53 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |