Abstract
Accurate estimation of winter wheat canopy nitrogen concentration (CNC) supports crop diagnosis and precision nitrogen management, yet the relative value and redundancy of multispectral, structural, and chlorophyll-related variables remain unclear in small dat asets. Using 155 multi-temporal observations retained from the 2016–2017 and 2017–2018 growing seasons, seven prespecified feature combinations were evaluated with four traditional regression models under five-fold repeated season-stratified cross-validation. A stricter season-balanced, unit-level grouped five-fold cross-validation was added to prevent observations from the same field from occurring in both training and test partitions. Two fully connected neural networks were additionally assessed for the selected compact module. Spectral-only combinations yielded negative mean R2 values, whereas LAI, vegetation cover, and chlorophyll content achieved a mean R2 of 0.684. Combining these variables with four raw multispectral bands produced M5, which achieved mean RMSE, R2, and RPD values of 0.328, 0.782, and 2.147, respectively, with 36.4% fewer variables than the full module. RF provided the best numerical performance under repeated sample-level cross-validation (R2 = 0.796 ± 0.007), whereas M5 retained R2 values of 0.736–0.778 under unit-grouped validation, with SVR performing best in that stricter setting. Parameter-removal analysis showed the largest incremental contribution for vegetation cover and limited additional value from LAI. Bidirectional cross-season validation remained direction- and model-dependent. Overall, controlled low-redundancy feature fusion was more beneficial than increased model complexity, while field-level and cross-season tests indicated that the strong within-dataset results should not be interpreted as broad generalization capability.