Leaf area index (LAI) is a critical indicator of canopy architecture and physiological performance, serving as a key parameter for crop growth monitoring and management. Although UAV multispectral imagery provides rich spectral and spatial information, the limitations of single texture features for LAI estimation still require further exploration. To address this issue, this study developed a multi-source feature fusion framework that integrates vegetation indices (VIs), texture features (TFs), and texture indices (TIs) within a stacked ensemble approach combining Partial Least Squares Regression (PLSR) with Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting Decision Tree (GBDT) algorithms to estimate maize LAI.A field experiment was conducted under three planting densities (42,000, 63,000, and 84,000 plants ha⁻¹) and four nitrogen rates (0, 80, 160, 240 kg N ha⁻¹) to assess the potential of UAV-based multispectral imagery for maize LAI estimation. The results show that when using partial least squares regression (PLSR) combined with RF, SVM and GBDT to estimate maize LAI, the R² values are 0.653, 0.697 and 0.634, and the RMSE is 0.650, 0.608 and 0.668, respectively, when only vegetation indices (VIs) is used as input. After texture features (TFs) incorporation, the R² increases to 0.717, 0.794, and 0.801, and the RMSE decreases to 0.587, 0.500, and 0.492. Further inclusion of the texture indices (TIs) raises the R² to 0.789, 0.804, and 0.844, with RMSE of 0.506, 0.489, and 0.436, respectively. Independent test set validation under contrasting conditions confirmed that our multi-model fusion framework (PLSR+GBDT) with multi-source feature fusion (VIs+TFs+TIs) effectively estimated LAI, achieving an R² of 0.859 and 0.794. These results demonstrate that multi-source feature integration via machine learning enables robust and accurate estimation of maize LAI, providing a valuable tool for precision agriculture and crop growth monitoring.

Hyperspectral remote sensing provides a powerful tool for crop nutrient monitoring and precision fertilization, yet its application is hindered by high-dimensional redundancy and inter-band collinearity. This study aimed to improve maize nitrogen estimation by constructing three types of two-dimensional full-band spectral indices—Difference Index (DI), Simple Ratio Index (SRI), and Normalized Difference Index (NDI)—combined with spectral preprocessing methods (raw spectra (RAW), first-order derivative (FD), and second-order derivative (SD)). To optimize feature selection, three strategies were evaluated: Grey Relational Analysis (GRA), Pearson Correlation Coefficient (PCC), and Variable Importance in Projection (VIP). These indices were then integrated into machine learning models, including Backpropagation Neural Network (BP), Random Forest (RF), and Support Vector Regression (SVR). Results revealed that spectral index optimization substantially enhanced model performance. NDI consistently demonstrated robustness, achieving the highest grey relational degree (0.9077) under second-derivative preprocessing and improving BP model predictions. PCC-selected features showed superior adaptability in the RF model, yielding the highest test accuracy under raw spectral input (R² = 0.769, RMSE = 0.0018). VIP proved most effective for SVR, with the optimal SD–VIP–SVR combination attaining the best predictive performance (test R² = 0.7593, RMSE = 0.0024). Compared with full-spectrum input, spectral index optimization effectively reduced collinearity and overfitting, improving both reliability and generalization. Spectral index optimization significantly improved inversion accuracy. Among the tested pipelines, RAW-PCC-RF demonstrated robust stability across datasets, while SD-VIP-SVR achieved the highest overall validation accuracy (R² = 0.7593, RMSE = 0.0024). These results highlight the complementary roles of stability and accuracy in defining the optimal pipeline for maize nitrogen inversion. This study highlights the pivotal role of spectral index optimization in hyperspectral inversion of maize nitrogen content. The proposed framework provides a reliable methodological basis for non-destructive nitrogen monitoring, with broad implications for precision agriculture and sustainable nutrient management.