Fluorescence Hyperspectral Imaging for Early Diagnosis of Heat-Stressed Ginseng Plants

Ginseng is a perennial herbaceous plant that has been widely consumed for medicinal and dietary purposes since ancient times. plants require shade cool temperatures better growth; climate warming rising heat waves have negative impact on the plants’ productivity yield quality. Since Republic of Korea’s temperature increasing beyond normal expectations seriously threatening ginseng plants, an early-stage non-destructive diagnosis stressed essential before symptomatic manifestation to produce high-quality roots. This study demonstrated potential fluorescence hyperspectral imaging achieve early high-throughput detection prediction chlorophyll composition in four varieties heat-stressed plants: Chunpoong, Jakyeong, Sunil, Sunmyoung. Hyperspectral data 80 from these (temperature-sensitive temperature-resistant) were acquired after exposing stress. Additionally, SPAD-502 meter was used measurement greenness level. In accordance, mean spectral each leaf extracted region interest (ROI). Analysis variance (ANOVA) applied discrimination which performed with 96% accuracy. Accordingly, develop partial least squares regression (PLSR) model combined multiple preprocessing techniques predicting significantly correlates concentration. The results obtained PLSR analysis higher determination coefficients R2val = 0.90, root square error (RMSE) 3.59%. Furthermore, five proposed bands (683 nm, 688 703 731 745 nm) by stepwise (SR) developed into model, create greenness-level concentration images showed differences between control all varieties.