Hyperspectral detection and monitoring of eggplant verticillium wilt in field conditions

Advancements in the ability to detect and monitor plant diseases are mandatory to improve crop yield, quality, and management practices. The present study shows the capability of hyperspectral reflectance $(400-2,400 \mathrm{~nm})$ to rapidly and non-destructively detect and monitor eggplant verticillium wilt in field conditions. Using a partial least squares regression approach, we constructed predictive models to concomitantly estimate from spectra leaf traits which are pivotal to investigate Verticillium/eggplant interaction, i.e., CO
2
assimilation rate, chlorophyll level and leaf water potential (goodness-of-fit model, $R^{2}: 0.72-0.86$; percentage of the root mean square error over the data range, % RMSE: 8-13). Furthermore, analyzing spectral signatures from asymptomatic leaves, disease conditions were accurately discriminated [accuracy: 0.79 and 0.84, at 10 and 20 days post inoculation (DPI), respectively]. Finally, variations of spectra-derived parameters highlighted a strong negative impact of V. dahliae infection on eggplant photosynthesis and water status, mostly at 20DPI, confirming what previously reported by standard measurements. The proposed approach could be used in precision agriculture, high-throughput plant phenotyping, and smart nursery management to enhance crop quality and yield.