Related Experiment Video
Updated: May 5, 2026
Protocol for Microplastics Sampling on the Sea Surface and Sample Analysis
Published on: December 16, 2016
Deep Learning-Based Shape Classification for Hyperspectral-Imaged Microplastics
Yuanli Liu1,2,3, Guohan Zhao3,4, Fan Liu3
1College of Environmental and Biological Engineering, Fujian Provincial Key Laboratory of Ecological Impacts and Treatment Technologies for Emerging Contaminants, Putian University, Putian 351100, China.
Deep learning automates microplastic (MP) shape classification from hyperspectral images, offering faster and more accurate results than manual methods. Convolutional Neural Networks (CNNs), particularly MobileNet, show superior performance, highlighting the importance of model architecture and data quality.
Area of Science:
- Environmental Science
- Analytical Chemistry
- Computer Science
Background:
- Microplastic (MP) shape classification is crucial but traditionally labor-intensive and prone to bias.
- Automating MP shape analysis is needed for efficient environmental monitoring.
Purpose of the Study:
- To investigate deep learning models for automated microplastic shape classification using hyperspectral imaging.
- To compare the performance of various deep learning architectures on diverse datasets.
Main Methods:
- Tested nine deep learning architectures (NNs, CNNs, transfer learning models) on 11,042 MP hyperspectral images.
- Utilized micro-Fourier transform infrared spectroscopy across seven environmental matrices.
- Evaluated models on original, augmented, refined, and augmented refined datasets.
Main Results:
- Convolutional Neural Networks (CNNs) outperformed Neural Networks (NNs), and transfer learning models surpassed non-transfer learning models.
- MobileNet achieved the highest accuracy (0.93 validation, 1.00 test).
- Model architecture and data quality significantly impact classification accuracy; complex models showed robustness.
Conclusions:
- Deep learning provides an efficient, automated alternative to manual MP shape classification.
- Model selection and high-quality data are critical for optimal performance.
- Further research into robust model designs is needed for advanced MP analysis.
