The integration of hyperspectral imaging with machine learning algorithms has presented a promising strategy for the non-invasive and rapid detection of plant metabolites. For this study, we developed prediction models using partial least squares regression (PLSR) and boosting algo-rithms (such as AdaBoost, XGBoost, and LightGBM) for five metabolites in Brassica juncea leaves: total chlorophyll, phenolics, flavonoids, glucosinolates, and anthocyanins. To enhance the model performance, we employed several spectral data preprocessing methods and feature-selection al-gorithms. Our results showed that the boosting algorithms generally outperformed the PLSR models in terms of prediction accuracy. In particular, the LightGBM model for chlorophyll and the AdaBoost model for flavonoids improved the prediction performance, with R2p = 0.71–0.74, com-pared to the PLSR models (R2p = 0.53–0.58). The final models for the glucosinolates and anthocya-nins performed sufficiently for practical uses such as screening, with R2p = 0.82–0.85 and RPD = 2.4–2.6. Our findings indicate that the application of a single preprocessing method is more effective than utilizing multiple techniques. Additionally, the boosting algorithms with feature selection ex-hibited superior performance compared to the PLSR models in the majority of cases. These results highlight the potential of hyperspectral imaging and machine learning algorithms for the non-destructive and rapid detection of plant metabolites, which could have significant implications for the field of smart agriculture.

Among abiotic stresses, both drought and UV-B radiation effectively trigger the accumulation of secondary metabolites, and can be widely applied in plant factories. The objectives of this study were to investigate antioxidant accumulation under drought stress alone, or in combination with UV-B radiation near harvest, and to determine an optimal treatment time for maximum antioxidant production. Kale (Brassica oleracea L. var. acephala) plants were grown in a plant factory and harvested at 42 days after transplanting. The single and combination treatments lasted for 7 to 1 days and 4 to 2 days before harvest, respectively. The results of both F_v/F_m (maximal photochemical efficiency in photosystem II) and leaf water potential could ensure the function of photosynthesis and maintain normal leaf moisture in single drought treatments of less than 4 days. The total phenolic and flavonoid contents and antioxidant activities were significantly increased in both single and combination treatments for 3 to 4 days, compared to other treatments. The supplementary UV-B treatments showed no extra formation of antioxidants compared to the single drought treatments. As a result, drought for 3 days before harvest could achieve the highest potential value of kale as a source of natural antioxidants.