来自加拿大的研究人员提出了一种基于高频超声与深度学习相结合的微塑料识别与粒径估计方法。

当前微塑料检测主要依赖光谱和显微方法，存在成本高、效率低及难以实现原位快速检测等问题。研究人员通过构建超声回波信号分析框架，结合峰值提取算法、特征工程以及深度学习模型，对不同材料和粒径的微塑料颗粒开展系统实验研究。实验结果表明，该方法可实现约96%的颗粒信号识别准确率，并在材料分类与粒径估计中表现出较高精度，其中卷积神经网络模型在分类任务中准确率超过94%。同时，不同材料在频谱特征上表现出显著差异，使得模型能够有效区分多种微塑料类型。研究表明，高频超声结合数据驱动模型能够实现对微塑料的高效识别与定量分析，为复杂环境中微塑料监测提供了新的技术路径。

此篇名为《High-frequency ultrasound combined with deep learning enables identification and size estimation of microplastics》的文章被发表在2026年3月的《npj Emerging Contaminants》期刊。

Researchers from Canada proposed a microplastic identification and particle size estimation method based on the combination of high-frequency ultrasound and deep learning.

The abstract is as follows:

Microplastics are widespread in aquatic and terrestrial environments, yet standard identification techniques remain slow, labor-intensive, and unsuitable for large-scale or in situ monitoring. In this work, we investigate high-frequency ultrasound as a fast, non-destructive alternative for microplastic detection, material identification, and size estimation. A peak-based extraction method isolated particle-specific echoes, from which temporal and spectral features were computed. We evaluated several machine learning methods and introduced a one-dimensional convolutional neural network (1D-CNN) to classify material types. The proposed 1D-CNN achieved 97.14% accuracy, outperforming traditional models. Particle size was further estimated using material-specific multilayer perceptrons, which classified microspheres into four size ranges with an average accuracy of 99.93%. These results show that high-frequency ultrasound encodes discriminative scattering patterns that can be learned directly from raw acoustic signals, offering a fast and scalable framework for microplastic characterization with potential for future real-time or in situ applications.

https://www.nature.com/articles/s44454-026-00029-1#citeas