Composition Identification and Analysis of Ancient Glass Artifacts Based on Statistical Methods and Machine Learning
Yan Liu, Haifan Xie, Aitong Jin, Zicong Yang, Jianyi Tan, Liyun Chen · 2024
Glass was introduced to China from West Asia and Egypt through the early Silk Road. Its primary raw material is quartz sand, which has a high melting point. Therefore, during refinement, a flux is added to lower the melting point. The performance of glass artifacts is influenced by different materials, making the analysis and identification of chemical composition crucial in the study of ancient Chinese glass. In this paper, non-parametric tests and machine learning techniques, including cluster analysis and KNN algorithm, are employed to analyze and identify a collection of ancient glass artifacts. This research investigated the relationship between the weathering condition of glass and its type, patterns, and colors, and predicted the chemical composition of these artifacts prior to weathering. Additionally, a detailed sub-classification and analysis of the chemical composition of glass artifacts is conducted to accurately identify different types of glass, focused on the classification patterns of two specific types of glass, namely high-potassium glass and lead-barium glass as well. Furthermore, the correlation between the chemical compositions of glass artifacts from different categories is also analyzed.