Automatic Identification and Classification of Marine Microplastic Pollution Based on Deep Learning and Spectral Imaging Technology
Bibliographic record
Abstract
Marine microplastics pose a significant ecological and health risk due to their widespread sources and distribution.As a result, the rapid and accurate identification and classification of microplastics have become critical for marine environmental protection.Currently, traditional visual and microscope detection methods are inefficient and subjective.Some image-based recognition methods suffer from insufficient feature extraction capabilities, resulting in limited accuracy, while spectral-based techniques fail to effectively address data redundancy and noise, leading to poor classification performance in complex environments.To address these challenges, this study focuses on the development of an automatic recognition and classification technology for marine microplastic pollution using deep learning combined with spectral images.The research includes: proposing a feature extraction method for marine microplastics from multispectral images based on the ReliefF algorithm, which effectively selects features and removes redundant information; and developing a Conv-ReliefF-based recognition method for marine microplastics, integrating the feature learning ability of Convolutional Neural Networks (CNNs) with the feature selection advantages of the ReliefF algorithm.The innovation of this study lies in precisely extracting key features from multispectral images using the ReliefF algorithm to solve the problems of redundancy and noise interference in traditional feature extraction.By combining CNNs with the ReliefF algorithm, the Conv-ReliefF method balances feature learning depth and selective screening, thereby improving the accuracy and efficiency of microplastic recognition in complex marine environments.This approach provides technical support for large-scale marine 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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".