Prediction of soybean fatty-acid composition from hyperspectral imaging with spectral feature processing and structured tabular modeling.

Soybean fatty-acid composition is a key determinant of nutritional quality and industrial value, but conventional gas chromatography is destructive, labor-intensive, and time-consuming. This study combined hyperspectral imaging, which enables rapid and nondestructive acquisition of seed-surface spectral information, with the Tabular Prior-data Fitted Network (TabPFN) to predict the relative proportions of five major soybean fatty acids: palmitic, stearic, oleic, linoleic, and linolenic acids. Mean seed reflectance spectra extracted using three region-of-interest (ROI) strategies were subjected to preprocessing, comparison across representative models and feature-reduction strategies, and SHapley Additive exPlanations (SHAP) analysis to identify wavelength regions associated with fatty-acid variation. TabPFN achieved the best regression performance under partial least squares (PLS) reduction, with an overall R2 of 0.9750, while all four classification metrics exceeded 0.93 under linear discriminant analysis (LDA). These results demonstrate an accurate, interpretable, and nondestructive framework for rapid prediction of soybean fatty-acid composition and quality evaluation.