Department of Food Science, University of Otago, Dunedin, New Zealand.
Department of Physics, University of Auckland, Auckland, New Zealand.
J Sci Food Agric. 2023 Jul;103(9):4704-4718. doi: 10.1002/jsfa.12546. Epub 2023 Mar 25.
This study investigated the geographical origin classification of green coffee beans from continental to country and regional levels. An innovative approach combined stable isotope and trace element analyses with non-linear machine learning data analysis to improve coffee origin classification and marker selection. Specialty green coffee beans sourced from three continents, eight countries, and 22 regions were analyzed by measuring five isotope ratios (δ C, δ N, δ O, δ H, and δ S) and 41 trace elements. Partial least squares discriminant analysis (PLS-DA) was applied to the integrated dataset for origin classification.
Origins were predicted well at the country level and showed promise at the regional level, with discriminating marker selection at all levels. However, PLS-DA predicted origin poorly at the continental and Central American regional levels. Non-linear machine learning techniques improved predictions and enabled the identification of a higher number of origin markers, and those that were identified were more relevant. The best predictive accuracy was found using ensemble decision trees, random forest and extreme gradient boost, with accuracies of up to 0.94 and 0.89 for continental and Central American regional models, respectively.
The potential for advanced machine learning models to improve origin classification and the identification of relevant origin markers was demonstrated. The decision-tree-based models were superior with their embedded variable identification features and visual interpretation. © 2023 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.
本研究旨在对商业咖啡生豆进行从大陆到国家和地区水平的产地分类。本研究采用创新方法，结合稳定同位素和微量元素分析以及非线性机器学习数据分析，以提高咖啡产地分类和标志物选择。本研究分析了来自三大洲、八个国家和二十个地区的特种商用咖啡生豆，共测量了五个同位素比值（δ C、δ N、δ O、δ H 和 δ S）和 41 种微量元素。采用偏最小二乘判别分析（PLS-DA）对综合数据集进行产地分类。
在国家层面上，产地的预测效果良好，在地区层面上也有一定的预测潜力，在各个层面上都能进行标志物的选择。然而，PLS-DA 在大陆和中美洲地区层面上对产地的预测效果较差。非线性机器学习技术提高了预测能力，并能够识别出更多的产地标志物，而且所识别的标志物更具相关性。使用集成决策树、随机森林和极端梯度提升算法，获得了最佳的预测精度，大陆和中美洲地区模型的精度分别高达 0.94 和 0.89。
先进的机器学习模型在提高产地分类和识别相关产地标志物方面具有潜力。基于决策树的模型具有嵌入的变量识别功能和可视化解释功能，表现更为优越。
