甘草作為中藥方劑中「調和諸藥」的核心藥材，亦是製藥產業極為關鍵的原料藥材。本研究以「脹果甘草」作為研究對象，整合海拔、年平均氣溫及年降水量等八項關鍵環境因子作為自變數，並以甘草酸（Glycyrrhizic acid）含量作為依變數。 研究首先透過K-Means分群分析確認樣本分群，隨後採用多元線性回歸（MLR）之最小平方法（OLS）建構品質預測模型，並搭配「80/20驗證法則」以確保模型的泛化能力。此外，本研究進一步導入環境因子間的「交互作用分析」（如：氣溫與降水量的交互影響），以捕捉自然環境對甘草次級代謝產物累積所產生的複雜非線性影響。 研究結果證實，透過監控產地環境變因，能有效建立高品質甘草之預測模型。將此模型轉化為實務管理工具並應用於採購前置篩選，將能預先過濾並淘汰高風險樣本，顯著提升採購合格率。本研究不僅深化了環境因子對甘草品質影響的學術理解，更為製藥產業在精實物控管理與降低缺料風險上，提供了具備實證基礎的科學化與數據化的決策機制。;Licorice (Glycyrrhiza)， serving as the core medicinal material for "harmonizing various drugs" in traditional Chinese medicine prescriptions， is also a crucial raw material in the pharmaceutical industry. This study focused on Glycyrrhiza inflata as the research subject. Eight key environmental factors， including altitude， annual mean temperature， and annual precipitation， were integrated as independent variables， with the glycyrrhizic acid content set as the dependent variable. Initially， K-Means clustering analysis was employed to identify and confirm sample clusters.Subsequently， a quality prediction model was constructed using Ordinary Least Squares (OLS) based Multiple Linear Regression (MLR)， paired with the "80/20 validation rule" to ensure the model′s generalization capability.Furthermore， this study introduced "interaction analysis" among environmental factors (e.g.， the interactive effect between temperature and precipitation) to capture the complex， non-linear impacts of the natural environment on the accumulation of secondary metabolites in licorice. The results demonstrated that by monitoring the environmental variables of the origin， a highly effective prediction model for high-quality licorice can be established. Transforming this model into a practical management tool and applying it to pre-procurement screening can proactively filter and eliminate high-risk samples， significantly improving the procurement qualification rate. This study not only deepens the academic understanding of how environmental factors influence licorice quality but also provides an evidence-based， scientific， and data-driven decision-making mechanism for the pharmaceutical industry to streamline material control management and mitigate the risk of material shortages.
