Identifying the origins of Tianhuang stones based on Raman spectroscopy and pattern recognition algorithms

Abstract

Abstract In this paper, a non-destructive and efficient method for identifying gemstones of the same species based on Raman spectroscopy and pattern recognition algorithms was developed. Tianhuang stones from different origins (Shoushan (SS), Changhua (CH), and Laos (LA)) with similar composition and structure were investigated and analyzed. Raman spectra were collected by a self-developed portable Raman spectrometer. Combined with pattern recognition methods, the subtle differences between the three types of Tianhuang stones were comprehensively analyzed. Principal component analysis–latent Dirichlet allocation was used to predict the feasibility of distinguishing SS, CH, and LA Tianhuang stones by Raman spectra. Random forest analysis method was applied to establish SS/CH and SS/LA models to distinguish SS from CH and LA. The selection of characteristic variables and determination of the number of growing trees was discussed. Also, the accuracy, sensitivity, and specificity of the two models were calculated. The potential of this method for rapid and non-destructive identification of Tianhuang stones was proved. The feasibility and effectiveness of Raman spectroscopy combined with the pattern recognition method in identifying gemstones of the same species with similar composition were proved.