Field-Deployable Plasmonic Sensing and Machine Learning Classification of Microplastics Using Peptide–AuNP Conjugates
Bibliographic record
Abstract
Microplastic (MP) debris ($1 \mu \mathrm{m}-5 \text{mm}$) is now widely found in oceans, rivers, and even municipal tap water, yet routine monitoring remains limited due to the high cost and time demands of laboratory-based FTIR or Raman spectroscopy. We introduce a peptide-gold nanoparticle (AuNP) assay that converts polymer-specific interactions into a rapid plasmonic colorimetric response, further analyzed through machine learning (ML)-based classification. Cysteineterminated peptides with affinity toward polystyrene (PS) and polypropylene (PP) were immobilized on 20 nm AuNPs. Upon exposure to the target microplastics, peptide-driven aggregation was triggered, producing a red-shift of the localized surface plasmon resonance (LSPR) band from 533 nm within five minutes. Spectral parameters obtained from UV-Vis analysis, together with dynamic light scattering (DLS) measurements, provided features such as$\lambda \max, \Delta \lambda$, full width at half maximum (FWHM), integrated absorbance, and Z-average hydrodynamic size. Random Forest, K-nearest neighbors (KNN), and Hierarchical Clustering were employed to classify MPs across six size ranges ($100 \text{nm}-250 \mu \mathrm{m}$) and four concentration tiers$\left(0.1-5 \mu \mathrm{g} \text{mL}^{-1}\right)$, successfully assigning blind samples to the correct size-concentration cluster. The assay functions effectively in tap water, achieving a limit of detection of$0.1 \mu \mathrm{g} \text{mL}^{-1}$and a linear detection range up to$10 \mu \mathrm{g} \text{mL}^{-1}$comparable to electrochemical platforms but without the need for a potentiostat or extended incubations. By integrating nanoscale molecular recognition with spectrum-based ML, this method offers a field-deployable, chemically specific solution for real-time microplastic monitoring.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".