1. Industrial wastewater source tracing: The initiative of SERS spectral signature aided by a one-dimensional convolutional neural network.
- Author
-
Huang, Yuting, Yuan, Bingxue, Wang, Xueqing, Dai, Yongsheng, Wang, Dongmei, Gong, Zhengjun, Chen, Junmin, Shen, Li, Fan, Meikun, and Li, Zhilin
- Subjects
- *
INDUSTRIAL wastes , *SEWAGE , *CONVOLUTIONAL neural networks , *SERS spectroscopy , *CHEMICAL fingerprinting - Abstract
• Industrial wastewater sourcing was first realized with multi-wavelength SERS. • The superiority of SERS in wastewater information capturing was confirmed by PCA. • 1D-CNN shows excellent performance in SERS signature extraction for sourcing. • The wastewater can be identified from unknown samples with 97.33% accuracy. The spectral fingerprint is a significant concept in nontarget screening of environmental samples to direct identification efforts to relevant and important features. Surface-enhanced Raman scattering (SERS) has long been recognized as an optical method that can provide fingerprint-like chemical information at the single-molecule level. Here, the advanced one-dimensional convolutional neural network (1D-CNN) approach was applied to accurately identify the SERS spectral signature of industrial wastewaters for source tracing. A total of 66,000 SERS spectra were acquired from wastewaters of 22 factories across 10 industrial categories at three excitation wavelengths after data augmentation. The dataset was used to train a 1D-CNN model consisting of three convolutional layers to achieve adequate feature extraction of SERS spectra. As a proof-of-concept, multimixed wastewater samples were used to simulate practical pollution scenarios and evaluate the application potential of the model. The SERS-1D-CNN platform can identify the amount and factory information of wastewaters in multimixed samples, which achieves a recognition accuracy rate of 97.33%. The results suggest that even in a complex and unknown water environment, the 1D-CNN model can accurately identify industrial wastewaters in precollected datasets, exhibiting excellent potential in pollution source tracing. [Display omitted] [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF