Non-destructive hyperspectral imaging and machine learning for detection of pea seed-borne mosaic virus in faba bean seeds

Pea seed-borne mosaic virus (PSbMV) is an important seed-transmitted pathogen of pulse crops that can reduce yield and seed quality while remaining difficult to detect using visual inspection. Conventional diagnostic methods are accurate, but destructive, labor-intensive, and unsuitable for large-scale seed screening. In this study, we evaluated hyperspectral imaging (HSI) as a non-destructive approach for detecting PSbMV infection in faba bean ( Vicia faba ) seeds. Individual seeds were imaged using visible-near-infrared (Vis–NIR) and shortwave-infrared (SWIR) hyperspectral systems (400–1700 nm), and directional reflectance spectra were extracted after reflectance calibration and preprocessing. Principal Component Analysis (PCA) revealed subtle but consistent spectral differences between infected and healthy seeds. Among the evaluated models and preprocessing methods, a support vector machine combined with standard normal variate preprocessing achieved the best performance, with a mean fivefold cross-validation accuracy of 97.2% and an independent holdout accuracy of 98.3% (ROC-AUC = 0.994). Competitive adaptive reweighted sampling identified a reduced set of informative wavelengths distributed across the visible, near-infrared, and shortwave-infrared regions. The reduced model retained strong discrimination, achieving cross-validation and holdout accuracies of 96.2% and 90.8%, respectively, with a holdout ROC-AUC of 0.974. To support biological interpretation, seed moisture content was quantified, and proton nuclear magnetic resonance ( 1 H NMR) metabolite profiling was performed, revealing increased phenolic signals in virus-infected seeds. Together, these results demonstrate that PSbMV infection induces detectable optical and compositional changes in faba bean seeds that can be captured using hyperspectral imaging. This work provides a foundation for developing rapid, non-destructive screening tools for single seed health assessment and virus management in pulse crops.