Optimizing Leaf Nitrogen Estimation Using Hyperspectral Sensing and Machine Learning With Band Selection Techniques
Integrating hyperspectral sensing with machine learning (ML) enables efficient monitoring of crop health, improved fertilization management, and data-driven precision agriculture. This study proposes a framework for leaf-level nitrogen estimation using full-range visible, near-infrared, and short-wave infrared hyperspectral reflectance data combined with advanced ML models and band selection (BS) strategies. Seven regression models, including linear, kernel-based, and neural-network approaches, were benchmarked using both full-spectrum data and reduced bands subsets. BS was addressed through variable importance in projection (VIP), a constrained genetic algorithm (GA) specifically designed to enforce fixed subset cardinality, and by introducing a two-step hybrid VIP–GA (HVG) strategy, in which VIP was first applied as a coarse filtering step followed by GA-based refinement, thus combining computational efficiency with refined combinatorial optimization. Experiments were conducted on a large public leaf-level spectral dataset using both repeated random subsampling and leave-one-group-out (LOGO) validation to assess robustness to training set size and transferability under heterogeneous conditions. Results showed that regularized linear models achieved, on these data, performance comparable to or better than more complex nonlinear approaches, with ridge regression yielding the lowest $\text{NRMSE}{{\mathrm{P}}_{\text{IQR}}}$ values, ranging between 0.27 and 0.30 across different BS scenarios. LOGO experiments indicated moderate transferability across heterogeneous conditions, although performance remained dependent on group-specific characteristics. Overall, BS considerably reduced spectral dimensionality and computational cost while preserving predictive performance, with the HVG approach providing an effective tradeoff between accuracy, efficiency, and interpretability. These findings highlight the potential of combining ML and BS for efficient leaf-level nutrient monitoring and for providing a priori spectral insights for future hyperspectral sensing studies.