Department of Civil Urban Earth and Environmental Engineering, Ulsan National Institute of Science and Technology (UNIST), UNIST-gil 50, Ulsan, 44919, Republic of Korea.
Department of Environmental Science and Technology, University of Maryland, College Park, MD, 20742, United States.
Water Res. 2023 Nov 1;246:120710. doi: 10.1016/j.watres.2023.120710. Epub 2023 Oct 8.
Several preprocessing procedures are required for the classification of microplastics (MPs) in aquatic systems using spectroscopic analysis. Procedures such as oxidation, which are employed to remove natural organic matter (NOM) from MPs, can be time- and cost-intensive. Furthermore, the identification process is prone to errors due to the subjective judgment of the operators. Therefore, in this study, deep learning (DL) was applied to improve the classification accuracies for mixtures of microplastic and natural organic matter (MP-NOM). A convolutional neural network (CNN)-based DL model with a spatial attention mechanism was adopted to classify substances from their Raman spectra. Subsequently, the classification results were compared with those obtained using conventional Raman spectral library software to evaluate the applicability of the model. Additionally, the crucial spectral band for training the DL model was investigated by applying gradient-weighted class activation mapping (Grad-CAM) as a post-processing technique. The model achieved an accuracy of 99.54%, which is much higher than the 31.44% achieved by the Raman spectral library. The Grad-CAM approach confirmed that the DL model can effectively identify MPs based on their visually prominent peaks in the Raman spectra. Furthermore, by tracking distinctive spectra without relying solely on visually prominent peaks, we can accurately classify MPs with less prominent peaks, which are characterized by a high standard deviation of intensity. These findings demonstrate the potential for automated and objective classification of MPs without the need for NOM preprocessing, indicating a promising direction for future research in microplastic classification.
在使用光谱分析对水生系统中的微塑料 (MPs) 进行分类时，需要进行几种预处理程序。例如，为了从 MPs 中去除天然有机物 (NOM) 而采用的氧化程序可能既耗时又费成本。此外，由于操作人员的主观判断，鉴定过程容易出错。因此，在本研究中，应用深度学习 (DL) 来提高微塑料-天然有机物 (MP-NOM) 混合物的分类准确性。采用基于卷积神经网络 (CNN) 的具有空间注意力机制的 DL 模型来对物质从其拉曼光谱进行分类。随后，将分类结果与使用常规拉曼光谱库软件获得的结果进行比较，以评估模型的适用性。此外，通过应用梯度加权类激活映射 (Grad-CAM) 作为后处理技术，研究了用于训练 DL 模型的关键光谱带。该模型的准确率达到 99.54%，远高于拉曼光谱库的 31.44%。Grad-CAM 方法证实，DL 模型可以根据拉曼光谱中视觉上突出的峰有效地识别 MPs。此外，通过跟踪不依赖于视觉上突出峰的独特光谱，我们可以准确地对具有较低突出峰的 MPs 进行分类，这些峰的强度标准差较高。这些发现表明，无需 NOM 预处理即可实现 MPs 的自动化和客观分类，为未来的微塑料分类研究指明了一个有前途的方向。
