Prediction of brown tide algae using improved Gramian angular field and deep learning based on laser-induced fluorescence spectrum

Abstract

The frequent occurrence of algal blooms has seriously affected the marine environment and human production activities. Therefore, it is crucial to monitor the phytoplankton concentration in water bodies. In this study, a prediction method for brown tide algae using improved Gramian angular field (IGAF) and deep learning based on the laser-induced fluorescence spectrum was proposed. The method combined one-dimensional(1D) fluorescence spectrum with improved Gramian angular field (IGAF) for image coding. The internal normalizing approach of the original Gramian angle field algorithm was upgraded from local to global, which can increase the difference between samples with various concentrations. Then, we established a novel technique that fully takes into account the Gramian angular difference field (GADF) and Gramian angular summation field (GASF) features, allowing it to control the main and sub-diagonal features and successfully convert 1D sequences into images by adding various weight factors. Using depthwise separable convolutional neural network (DSC) to extract image features helps reduce model training parameters, paired with long short-term memory network (LSTM) to rapidly predict the concentration of brown tide. To confirm the actual performance of the given approach, ablation and contrast experiments were carried out, and the results showed that the method's regression accuracy, R2 was 97.8%, with the lowest MSE and MAE. This study investigated the transformation of 1D spectra into images using IGAF, which not only explored the application of the fluorescence spectrum image coding method for algal regression but also enabled the introduction of the potent benefits of deep learning image processing into the field of spectral analysis.