Replication Data for: Integrating C-H Information to Improve Machine Learning Classification Models for Microplastic Identification from Raman Spectra
Bibliographic record
Abstract
The development of uniform, consistent spectroscopic databases of Raman spectra is important for the community to maximize the value of emerging machine learning techniques. This dataset contains processed and augmented Raman spectra acquired on a variety of common plastics, with variations in manufacturer and properties such as plastic color. The Raman spectra span the frequency window from 300 to 3900 cm-1, were collected using variations in instrumentation settings, were interpolated to 1 cm-1 wavenumber spacing to ensure compatibility, and were augmented 5X by random scaling and artificial noise introduction. Three different versions of the data are provided, each enabling exploration of a different strategy for training machine learning classification models. This data was used to train microplastic classification models using K-nearest neighbor algorithm of the sklearn package in python, as published in the associated manuscript. Python pickle files are included in the dataset, which contain the optimized models and supporting information for the models. The data are being posted in support of this research. The data was created by the authors.
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.005 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.022 | 0.050 |
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".