Short-wave infrared hyperspectral imaging of microplastics: Effects of chemical and physical processes on spectral signatures and detection capabilities
Bibliographic record
Abstract
This study investigated the performance of hyperspectral imaging (HSI) in the short-wave infrared (SWIR) band (900–1620 nm) coupled with perClass Mira software for rapid detection and polymer identification of microplastics (MPs). Various physical and chemical agents were applied to simulate MPs in environmental samples and test the limits and capabilities of SWIR-HSI under challenging conditions. Spectral signatures of seven different MP polymers (polypropylene, polystyrene, high-density polyethylene, low-density polyethylene, acrylonitrile butadiene styrene, thermoplastic elastomer, and thermoplastic polyurethane) were analyzed before and after treatment with physical and chemical agents (KOH, HNO 3 , SDS, NaOH, H 2 O 2 , Fenton's reagent, coating with oil and water, and heating to 100°C). Six different MP colours and two different size ranges (1–5 mm, 300–500 µm) were also included in the testing. Results showed that the degree of spectral alteration depended on size and polymer type. Appearance of a distinct peak near 1400 nm was observed on exposure to chemical agents (NaOH, Fenton's reagent, and H 2 O 2 ), likely attributed to the hydroxyl group. Polypropylene and polyethylene exhibited fewer spectral alterations compared to polystyrene and thermoplastics. Additionally, MPs in the smaller size ranges were more susceptible to chemical and physical agents, necessitating the inclusion of these variations in the training set. The visualization feature in perClass Mira shows immense promise in enhancing the classification algorithm, achieving an overall accuracy of 94.4 % in post-treatment samples. This study aims to establish a groundwork for rapid and efficient MP classification in environmental samples using SWIR-HSI technology. • MP detection and identification were studied with hyperspectral imaging. • Seven polymers in two size ranges were exposed to physical and chemical agents. • Spectral changes varied by polymer type, with PP and PE showing minimal effect • Higher spectral distortions in smaller size ranges highlight their role in training • PerClass Mira's visualization feature enhanced MP detection and identification
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".