Related Experiment Video
Updated: Jan 7, 2026
09:10
Multimodal Analysis of Microplastics in Drinking Water using a Silicon Nanomembrane Analysis Pipeline
Published on: June 13, 2025
1.2K
Deep Learning-Powered Dark-Field Microscopy for Simultaneous Size and Concentration Analysis of Nanoplastics in Water
Yi Wang1, Cheng Ye Xi1, Jun Jie Yu1
1School of Chemistry & Molecular Engineering, East China University of Science and Technology, Shanghai 200237, China.
Analytical Chemistry
|December 25, 2025
Summary
This study introduces a new method using artificial intelligence and microscopy to measure nanoplastic size and concentration. This advance aids environmental and health assessments of these pervasive pollutants.
Area of Science:
- Environmental Science
- Analytical Chemistry
- Nanotechnology
Background:
- Nanoplastics pose significant environmental and health risks.
- Accurate analysis of nanoplastic size and concentration is crucial but challenging.
- Existing methods struggle with simultaneous size and concentration determination.
Purpose of the Study:
- To develop a novel method for concurrent size and concentration analysis of nanoplastics.
- To improve the accuracy and sensitivity of nanoplastic detection.
- To provide a reliable tool for environmental and biological monitoring.
Main Methods:
- Utilized dark-field microscopy (DFM) for nanoplastic imaging.
- Employed convolutional neural networks (CNNs) for data analysis.
- Combined contour recognition algorithms with VGGNet for image processing.
Main Results:
- Achieved high accuracy (over 0.99) and sensitivity (LOD: 1.7 ng mL⁻¹) for nanoplastics (150-600 nm).
- Demonstrated excellent spiked recovery rates (93.55-103.8%) for polystyrene nanoplastics.
- Successfully enabled simultaneous determination of nanoplastic size and concentration.
Conclusions:
- The developed CNN-powered DFM approach offers a reliable and visual method for nanoplastic analysis.
- This strategy has potential applications in environmental monitoring and toxicological studies.
- The method provides a significant advancement in quantifying nanoplastic pollution.
