Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China; College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China.
Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China.
Chemosphere. 2022 Nov;307(Pt 4):136092. doi: 10.1016/j.chemosphere.2022.136092. Epub 2022 Aug 19.
Environmental pollution by microplastics (MPs) is a significant and complex global issue. Existing MPs identification methods have demonstrated significant limitations such as low resolution, long imaging time, and limited particle size analysis. New and improved methods for MPs identification are topical research areas, with machine learning (ML) algorithms proven highly useful in recent years. Critical literature reviews on the latest developments in this area are limited. This study closes this gap and summarizes the progress made over the last 10 years in using ML algorithms for identifying and quantifying MPs. We identified diverse combinations of ML methods and fundamental techniques for MPs identification, such as Fourier-transform infrared spectroscopy, Raman spectroscopy, and near-infrared spectroscopy. The most widely used ML model is the support vector machine, which effectively improves the conventional analysis method for spectral quality defects and improves detection accuracy. Artificial neural network models exhibit improved recognition effects, with shorter detection times and better MPs recognition efficiency. Our review demonstrates the potential of ML in improving the identification and quantification of MPs.
环境污染微塑料（MPs）是一个重大和复杂的全球性问题。现有的 MPs 识别方法已经证明存在明显的局限性，如低分辨率、长成像时间和有限的颗粒尺寸分析。新的和改进的 MPs 识别方法是当前的研究领域，机器学习（ML）算法近年来被证明非常有用。关于该领域最新进展的批判性文献综述有限。本研究弥补了这一空白，并总结了过去 10 年利用 ML 算法识别和量化 MPs 的进展。我们确定了用于识别和量化 MPs 的不同 ML 方法和基础技术的组合，例如傅里叶变换红外光谱、拉曼光谱和近红外光谱。最广泛使用的 ML 模型是支持向量机，它有效地改进了光谱质量缺陷的传统分析方法，并提高了检测精度。人工神经网络模型表现出改进的识别效果，具有更短的检测时间和更好的 MPs 识别效率。我们的综述表明了 ML 在提高 MPs 识别和量化方面的潜力。
