Linear and nonlinear classification models for tea grade identification based on the elemental profile

The content of mineral elements in tea is an important quality indicator that determines the quality and grade of tea to a certain extent. However, there are almost no studies using mineral element information to identify tea grade. To this end, the contents of 18 mineral elements from three tea grades were determined using inductively coupled plasma mass spectrometry (ICP-MS), and a few exploratory analysis methods were adopted to preliminarily analyse the dataset structure before modelling. Then the feasibility of combining elemental profiles and the two classification models partial least squares discriminant analysis (PLS-DA) and counter propagation artificial neural networks (CP-ANNs) to identify tea grade was evaluated. By comparing the performance of the PLS-DA and CP-ANNs models, better results were obtained from the PLS-DA classification model with an accuracy of 0.900, a specificity of 0.960 and a sensitivity of 0.923. The results demonstrate that it is feasible to identify tea grades using the elemental profile along with chemometric methods. Moreover, this study also provides a new perspective on the content of mineral elements as an identifier of tea grade.