在普洱茶产地溯源中化学计量学工具的应用研究

Application of Chemical metrology software of Pu-erh tea Geographical Origin Traceability

中文关键词:  普洱茶  微量元素  原产地  模型构建  化学计量学工具

英文关键词:Pu-erh tea  trace elements  place of origin  model building  Chemical metrology software  

中文摘要:

      目的 基于不同产地茶叶中微量元素差异应用化学计量学工具构建云南不同产地普洱茶产地溯源模型。方法 本文采用电感耦合等离子体质谱对两个主产区的普洱茶中21种微量元素和15种稀土元素进行检测,应用化学计量学工具对数据进行筛选、主成分分析和产地鉴别模型的构建,与常用Fisher判别方法(Fisher Linear Discriminant analysis, FLD)比较,对构建模型所采用的决策树算法C_5.0(Decision tree C5.0 ,C_5.0)、树扩展朴素贝叶斯算法(Tree augmented Bayes network,TAN)和反向传播人工神经网络算法(Back-propagation artificial neural network, BP-ANN)三种算法进行了评价。结果表明： C_5.0、TAN和BP-ANN三种算法构建的模型均适用于不同地域普洱茶的产地溯源。利用构建的模型经过外部样品预测集验证,以决策树算法C_5.0构建的普洱茶产地溯源模型判别率达83.33%。结论化学计量学工具构建的普洱茶产地溯源模型将为普洱茶溯源工作提供技术保障,从而促进普洱茶产业的健康发展。

英文摘要:

      Objective To identify the different regions of Pu-erh tea origin information of Yunnan through different elements of tea and Chemical metrology software establishing prediction model. Methods inductively coupled plasma-mass spectrometry (ICP-MS) was employed to measure the contents of 21 mineral elements and 15 rare earth elements in 107 tea samples from two origins. Chemical metrology software was used for data filtering, principal component analysis and origin identification model establishment. While the models for tea region authentication were established by Fisher linear discriminant analysis (FLD), decision tree 5.0(C_5.0), tree augmented bayes network (TAN) and back-propagation artificial neural network (BP-ANN) algorithms and they were evaluated by comparing the discriminant accuracy. The results showed that C_5.0 model , TAN model and BP-ANN model were applicated for geographical origin traceability of two Pu-erh tea regions. Application of external validation samples, C_5.0 model was suitable for geographical origin traceability of different regions, while the accuracy rats 83.33%. Results chemometric software determination model building of Pu-erh tea give support to identify Puer-tea of different origins.