A Method for Non-destructive Detection of Moisture Content in Oilseed Rape Leaves Using Hyperspectral Imaging Technology

This study assessed the viability of using hyperspectral imaging (HSI) technology for nondestructive detection of moisture content in oilseed rape leaves. Besides, a method (IVISSA-iPLS) coupling interval variable iterative space shrinkage approach (IVISSA) with interval partial least square (iPLS) was introduced to identify characteristic wavelengths. The IVISSA-iPLS algorithm changed the selection target from wavelength points to spectral intervals, reducing the computational burden while increasing the continuity between the selected wavelengths. Subsequently, the characteristic wavelengths selected by the IVISSA-iPLS were used as the input of the least square support vector regression (LSSVR) model to predict the moisture content of oilseed rape leaves. Additionally, the competitive adaptive reweighted sampling (CARS), the successive projections algorithm (SPA), the IVISSA, and the iPLS were investigated as wavelength selection algorithms for comparison. The results indicated that the LSSVR models based on the characteristic wavelengths acquired from the IVISSA-iPLS using divided wavelength intervals of 30, demonstrated the highest performance, with \({{\text{R}}}_{{\text{p}}}^{2}\) ${\text{R}}_{\text{p}}^2$ of 0.9555, RMSEP of 0.0065, and \({\text{RPD}}\) $\text{RPD}$ of 4.715. Finally, the optimal prediction model was used to visualize the moisture content of oilseed rape leaves, which offered a more intuitive and effective method for the evaluation of moisture content. The results ascertained the significant possibility of combining HSI with combinatorial algorithms in detecting, quantifying, and visualizing the moisture content of oilseed rape leaves.