Microplastics Detection Using Deep Learning Ensemble with Vision Language Models
Bibliographic record
Abstract
Microplastics pollution poses a significant environmental threat requiring accurate and efficient detection methods. This paper presents a novel ensemble approach combining deep learning models with Vision Language Models (VLMs) and traditional machine learning algorithms for microplastics classification, achieving unprecedented accuracy rates across multiple datasets. Our methodology integrates state-of-the-art Vision Transformers (EVA02-Large, ViT-Large, Swin-Large, BEiTLarge), advanced CNNs (EfficientNet-B7, ConvNeXt-XLarge), and traditional ML baselines (SVM, Random Forest, XGBoost) with comprehensive data augmentation, test-time augmentation (TTA), and stratified cross-validation strategies. We evaluated our hybrid approach on three comprehensive datasets: holographic imaging dataset, microplastic imaging dataset, and PS-PMMA comprehensive dataset. The Vision Language Model ensemble consistently outperformed traditional approaches, the complete hybrid ensemble with TTA achieved a an accuracy of 99.21% across all datasets. Our results demonstrate the superiority of Vision Transformers over conventional CNNs for microplastics detection, establishing new benchmarks for automated environmental monitoring systems.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".