Fast identification of fluorescent components in three-dimensional excitation-emission matrix fluorescence spectra via deep learning

Abstract

Three-dimensional excitation-emission matrix (3D-EEM) fluorescence spectroscopy has been widely applied to detect the fluorescent components in samples from natural water bodies to wastewater treatment processes. Data interpretation methods such as parallel factor analysis (PARAFAC) are required to decompose the overlapped fluorescent signals in the 3D-EEM spectra. However, strict requirements of data and complicated procedures of the PARAFAC limit the online monitoring and analysis of samples. Here we develop a fast fluorescent identification network (FFI-Net) model based on the deep learning approach to fast predict the numbers and maps of fluorescent components by simply inputting a single 3D-EEM spectrum. Two types of convolutional neural networks (CNN) are trained to classify the numbers of fluorescent components with an accuracy of 0.956 and predict the maps of fluorescent components with the min mean absolute error of 8.9 × 10-4. We demonstrate that the accuracy of the FFI-Net model will be further improved when more 3D-EEM data are available as a training dataset. Meanwhile, a user-friendly interface is designed to facilitate practical applications. Our approach gives a robust way to overcome the shortage of the PARAFAC and provides a new platform for online analysis of the fluorescent components in water samples.