The vase life of cut flowers is determined by morphological and physiological attributes, which are shaped by the interaction of preharvest conditions and genetic traits. Water stress, ethylene damage, and gray mold disease (GMD) caused by Botrytis cinerea (B. cinerea) during postharvest storage and transportation are major factors that influence the vase life of cut roses. In this study, we developed a non-contact and rapid detection technique for the emergence of GMD and the potential vase life of cut roses using machine learning techniques based on hyperspectral image (HSI) data. Cut flowers of two rose cultivars (‘All For Love’ and ‘White Beauty’) underwent either dry transport (thus impaired cut flower hydration), ethylene exposure, or B. cinerea inoculation, to identify the characteristic light wavelengths that are closely correlated with plant physiological states based on HSI. The HSI results revealed that spectral reflectance between 470 to 680 nm was strongly correlated with GMD, whereas those between 700 to 900 nm were strongly correlated with flower wilting or vase life. To develop a YOLOv5 and random forest prediction model that can be used to anticipate flower longevity, the vase life of cut roses was classed into two categories as over 5 d (+5D) and under 5 d (-5D), based on scoring a grading standard on the flower quality. A total of 3000 images from HSI was forwarded to the YOLOv5 model for training and prediction of GMD and vase life of cut flowers. Validation of the prediction model using independent data showed high predictive accuracy in evaluating the vase life of both ‘All For Love’ (r2 = 0.86) and ‘White Beauty’ (r2 = 0.83) rose flowers. The YOLOv5 model also accurately detected and classified GMD in the cut rose flowers based on the image data. These results demonstrate that the combination of HSI and deep learning is a reliable method for detecting early GMD infection and evaluating the vase life of cut roses.