Three dimensional fluorescence spectroscopy has become increasingly useful in the detection of organic pollutants. However, this approach is limited by decreased accuracy in identifying low concentration pollutants. In this research, a new identification method for organic pollutants in drinking water is accordingly proposed using three-dimensional fluorescence spectroscopy data and a deep learning algorithm. A novel application of a convolutional autoencoder was designed to process high-dimensional fluorescence data and extract multi-scale features from the spectrum of drinking water samples containing organic pollutants. Extreme Gradient Boosting (XGBoost), an implementation of gradient-boosted decision trees, was used to identify the organic pollutants based on the obtained features. Method identification performance was validated on three typical organic pollutants in different concentrations for the scenario of accidental pollution. Results showed that the proposed method achieved increasing accuracy, in the case of both high-(>10 $\mathsf{\mu }$g/L) and low-(≤10 $\mathsf{\mu }$g/L) concentration pollutant samples. Compared to traditional spectrum processing techniques, the convolutional autoencoder-based approach enabled obtaining features of enhanced detail from fluorescence spectral data. Moreover, evidence indicated that the proposed method maintained the detection ability in conditions whereby the background water changes. It can effectively reduce the rate of misjudgments associated with the fluctuation of drinking water quality. This study demonstrates the possibility of using deep learning algorithms for spectral processing and contamination detection in drinking water.

This paper proposes a morphological grayscale reconstruction method combined with an alternating trilinear decomposition (ATLD) and threshold method based on 3D fluorescence spectroscopy to detect pollutants present at low concentrations in drinking water. First, the morphological grayscale reconstruction method was used to locate the fluorescence peaks of pollutants by comparing the original and reconstructed spectra obtained through expansion. The signal in the characteristic spectral region was then enhanced using an amplification factor. Feature extraction was subsequently performed by ATLD, and the threshold method was used to qualitatively distinguish water quality. By comparing the proposed method with the direct use of the ATLD and threshold method—which is a commonly used feature-extraction method—this study found that the application of the morphological grayscale reconstruction method can extrude characteristics of 3D fluorescence spectra. Given the typical spectral characteristics of phenol, salicylic acid, and rhodamine B, they were selected as experimental organic pollutants. Results illustrated that the morphological grayscale reconstruction with ATLD improved the spectral signal-to-noise ratio of pollutants and can effectively identify organic pollutants, especially those present at low concentrations.