Soluble solid content (SSC) and acidity (pH) are two important factors indicating the fruit quality of pears and can be measured by near-infrared spectroscopy (NIRS). However, the robustness of these measurements as affected by different origins of pears remains largely unknown. In this study, we developed an NIRS method to measure ‘Dangshan’ pear (Pyrus spp.) SSC and pH and evaluated the robustness of this non-destructive detection method by examining the effects of pears from three different origins in 2019 and 2020. First, the Kennard–Stone method was used to divide the calibration set of the 2020 pear samples from different orchards. The partial least squares (PLS) model was used to establish the local origin and hybrid origin models to predict the pears’ SSC and pH. Second, a combination of competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), and uninformative variable elimination (UVE) was implemented to construct spectral prediction models based on effective variables for assessing the pears’ SSC and pH from local and hybrid origins. The results showed that the local origin detection model produced large errors in predicting the SSC and pH of pears from different origins, and the model, established based on the pear samples of three origins, performed better than the local origin and other hybrid origin models. Finally, the model could be effectively simplified using 70 and 52 characteristic variables selected by the CARS method. Pear samples harvested from three different orchards in 2019 were used as an independent set to verify the validity of the selected characteristic variables. The results showed that the predicted R²_p for the SSC and pH measurements of pears of three different origins were more than 0.9 and 0.85, respectively. This finding indicates that the difference in the origin of pears has an important influence on the quantitative inversion of pear SSC and pH measurements, and the combination of the hybrid origin model constructed based on the characteristic variables can improve the prediction accuracy. These findings provide an important theoretical basis for the development of rapid detection devices for the measurements of pears’ SSC and pH.

Paddy rice grain variety classification is essential for quality control, as different rice varieties exhibit significant variations in quality attributes, affecting both food security and market value. The integration of hyperspectral imaging with machine learning presents a promising approach for precise classification, though challenges remain in managing the high dimensionality and variability of spectral data, along with the need for model interpretability. To address these challenges, this study employs a CNN-Transformer model that incorporates Standard Normal Variate (SNV) preprocessing, Competitive Adaptive Reweighted Sampling (CARS) for feature wavelength selection, and interpretability analysis to optimize the classification of hybrid indica paddy rice grain varieties. The results show that the CNN-Transformer model outperforms baseline models, achieving an accuracy of 95.33% and an F1-score of 95.40%. Interpretability analysis reveals that the model’s ability to learn from key wavelength features is significantly stronger than that of the comparison models. The key spectral bands identified for hybrid indica paddy rice grain variety classification lie within the 400–440 nm, 580–700 nm, and 880–960 nm ranges. This study demonstrates the potential of hyperspectral imaging combined with machine learning to advance rice variety classification, providing a powerful and interpretable tool for automated rice quality control in agricultural practices.