Volatile Fingerprinting and Interpretable Machine Learning for Quality Differentiation of Astragali Radix from Different Cultivation Patterns

Volatile fingerprints provide useful information for characterizing Astragali Radix (AR), a food–medicine homologous plant material, but differences among wild, wild-simulated, and cultivated samples remain unclear. In this study, headspace solid-phase microextraction coupled with gas chromatography–mass spectrometry (HS-SPME-GC–MS) and headspace gas chromatography–ion mobility spectrometry (HS-GC–IMS) were integrated with multivariate analysis and interpretable machine learning to characterize volatile profiles and identify candidate discriminatory compounds in 117 AR samples from different cultivation patterns. HS-SPME-GC–MS tentatively identified 29, 34, and 45 volatile compounds in wild, wild-simulated, and cultivated samples, respectively. Esters were the predominant class in all groups, although the relative abundance of esters and the overall chemical-class composition varied among cultivation patterns. HS-GC–IMS tentatively identified 57, 50, and 55 compounds, respectively, comprising mainly low-molecular-weight aldehydes, alcohols, and ketones and thereby providing complementary volatile fingerprint information. Partial least squares discriminant analysis (PLS-DA) showed that the volatile fingerprints captured cultivation-pattern-associated differences, with the HS-GC–IMS model showing clearer group separation. Random forest, support vector machine, and CatBoost models were further constructed using the HS-SPME-GC–MS profiling results. By integrating variable importance in projection (VIP) and SHapley Additive exPlanations (SHAP) values, γ-hexalactone, methyl eugenol, methyl (9Z,11E)-octadeca-9,11-dienoate, eugenol, and ethyl linoleate were selected as candidate discriminatory compounds. Based on the HS-GC–IMS results, 1-octen-3-one, pentyl acetate, (Z)-2-penten-1-ol, 2-heptanone, and the monomeric signal of 2-ethyl-6-methylpyrazine were also identified as candidate discriminatory compounds. These compounds may be related to fatty acid-derived metabolism, aromatic secondary metabolism, and terpenoid-related processes. The integration of two complementary volatile-analysis platforms with VIP- and SHAP-based interpretation provided broader coverage of volatile features and improved the interpretability of candidate-compound screening. These findings provide an interpretable analytical workflow and candidate discriminatory compounds that may support future rapid screening, cultivation-pattern authentication, and volatile-profile-based differentiation of AR, pending independent external validation.