A research team led by Prof. GAO Xiaoming from the Hefei Institutes of Physical Science of the Chinese Academy of Sciences has improved residual neural network to accurately classify and identify microplastics using low-quality Raman spectra, even under non-ideal experimental conditions.

"It detects and classifies microplastics when the data is cluttered with noise," said Prof. GAO, "and it does this without overloading computing power."

The research results were published in Talanta.

Microplastics—plastic particles smaller than five mm—are pervasive in the environment and pose significant risks to both ecosystems and human health. Rapid and precise identification of these pollutants is critical for effective pollution control. Raman spectroscopy, known for its non-destructive and high-resolution capabilities, is a promising tool for detection. However, accurately analyzing microplastics in challenging environments remains a technical hurdle.

To address this issue, the researchers introduced an improved residual network model that can classify microplastics based on Raman spectra collected under suboptimal conditions, such as insufficient laser power or short spectral acquisition times. 

Compared to traditional convolutional neural networks, the new model, equipped with a Squeeze-and-Excitation module, achieves higher accuracy in identifying microplastics even when faced with significant noise interference and low signal-to-noise ratios. Importantly, this advancement comes without a substantial increase in computational demands.

Additionally, Grad-CAM visualization, a kind of "AI X-ray vision," reflects the basis for spectral classification by machine learning.

This work demonstrates the capability of machine learning to analyze and process low-quality Raman spectra in more complex environments and under interference, according to the team.

The detected Raman spectra of microplastics enter into the neural network, which is trained to capture the features of different kinds of spectra for effective classification. SE block is used to enhance the performance of the network. Grad-CAM visualization reflects the basis for spectral classification by machine learning. (Image by CHEN Jiajin)