Rapid identification of marine microplastics by laser-induced fluorescence technique based on PCA combined with SVM and KNN algorithm

The laser-induced fluorescence technique has the advantage of fast and non-destructive detection and can be used to classify types of marine microplastics. However, spectral overlap poses a challenge for qualitative and quantitative analysis by conventional fluorescence spectroscopy. In this paper, a 405 nm excitation laser source was used to irradiate 4 types of microplastic samples with different concentrations, and a total of 1600 sets of fluorescence spectral data were obtained. The 726 data points contained in each sample spectrum were first analyzed by PCA, and the 4 microplastics were differentiated by their position in the PCA score plot. The classification and identification are then performed by SVM, KNN, PCA-SVM and PCA-KNN algorithms respectively. The classification accuracy of microplastics in seawater using SVM and KNN algorithms is higher than 86%. The classification accuracy can be increased to 100% by PCA combined with SVM and KNN algorithm. Concentration inversion was conducted by SVM and KNN algorithms after classification. The correlation coefficients between the predicted values and the actual values were higher than 0.8, and the RMSE was less than 0.47%, which indicated that both algorithms had good prediction results. These machine learning methods provide accurate and reliable identification results in the rapid identification of microplastic types and their concentrations without complex spectral data preprocessing and fluorescence background removal algorithms.