摘要：Chemometric techniques have seen wide application in biological and medical sciences, but they are still developing in the food sciences. This study illustrated the use of untargeted LC/MS chemometric methods to identify features (retention time_m/z) associated with food quality changes as products age (freshness). Extracts of three citrus fruit varietals aged over four time points that corresponded to noted changes in sensory attributes were chemically profiled and modeled by two discriminatory multivariate statistical techniques, projection partial least-squares discrimant analysis (PLS-DA) and machine learning random forest (RF). Age-associated compounds across the citrus platform were identified. Varietal was treated as a nuisance variable to emphasize aging chemistry, and further variable selection using age-related piecewise model generation and meta filtering to emphasize features associated with general aging chemistry common to all the citrus extracts. The identified features were further replicated in a validation study to illustrate the validity and persistence of these markers for applications in citrus food platforms.