Sample Generation Method Based on Variational Modal Decomposition and Generative Adversarial Network (VMD-GAN) for Chemical Oxygen Demand (COD) Detection Using Ultraviolet Visible Spectroscopy.

Abstract

Ultraviolet visible spectroscopy can realize the detection of chemical oxygen demand (COD), especially for low concentration levels due to its high sensitivity, but the issue of insufficient real water sample data has always been a challenge owing to the low probability of occurrence of actual water pollution events. However, in existing methods, generated absorption spectra do not conform to actual situations as the former neglect the actual spectral characteristics. On the other hand, the diversity and complexity are restricted because the information in one-dimensional data is not enough for direct spectral generation. This study proposed a spectral sample generation method based on the variational modal decomposition and generative adversarial network (VMD-GAN). First, the VMD algorithm was utilized to separate principal components and residuals of absorption spectra. Among them, the GAN was used to generate new principal components to ensure that the major spectral characteristics of actual water samples are not lost. The corresponding residuals were then obtained by adjusting the parameters of a three-order Gaussian fitting function, which is more beneficial than the direct use of GAN in the aspect of diversity and complexity. Based on the spectral reconstruction with new principal components and residuals, various absorption spectra were generated more coincident with actual situations. Finally, the effectiveness of this method was evaluated by establishing regression models and predicting COD for actual water samples. In all, the insufficient water sample data can be expanded for a better performance in modeling and analysis of water pollution using the proposed method.