Composition Analysis and Category Prediction Model of Ancient Glass Based on Decision Tree

Abstract

Ancient glass is easily affected by environmental factors, which cause chemical changes between glass composition and environmental substances and leads to weathering. It is important to analyze the chemical composition of ancient glass for the study of the Silk Road. To study the composition of glass cultural relics, the relationship between surface weathering and glass type, ornamentation and colour was analyzed first, and then qualitative analysis was carried out through a frequency distribution map, and grouping was carried out according to glass type and surface weathering type, the statistical distribution law of each chemical composition was studied, and the loss of chemical composition with or without weathering was analyzed; Finally, the chemical composition content of the weathered sample before weathering is predicted according to the chemical composition ratio of the weathered and non-weathered cultural relics. The experimental results show that the model has good robustness and can be used to prepare and quickly predict the composition and classification of ancient glasses.