Estimation of potato leaf area index based on spectral information and Haralick textures from UAV hyperspectral...

The Leaf Area Index (LAI) is a crucial parameter for evaluating crop growth and informing fertilization management in agricultural fields. Compared to traditional methods, UAV-based hyperspectral imaging technology offers significant advantages for non-destructive, rapid monitoring of crop LAI by simultaneously capturing both spectral information and two-dimensional images of the crop canopy, which reflect changes in its structure. While numerous studies have demonstrated that various texture features, such as the Gray-Level Co-occurrence Matrix (GLCM), can be used independently or in combination with crop canopy spectral data for LAI estimation, limited research exists on the application of Haralick textures for evaluating crop LAI across multiple growth stages. In this study, experiments were conducted on two early-maturing potato varieties, subjected to different treatments (e.g., planting density and nitrogen levels) at the Xiaotangshan base in Beijing, during three key growth stages. Crop canopy spectral reflectance and Haralick textures were extracted from ultra-low-altitude UAV hyperspectral imagery, while LAI was measured using ground-based methods. Three types of spectral data-original spectral reflectance (OSR), first-order differential spectral reflectance (FDSR), and vegetation indices (VIs)-along with three types of Haralick textures-simple, advanced, and higher-order-were analyzed for their correlation with LAI across multiple growth stages. A model for LAI estimation in potato at multiple growth stages based on spectral and textural features screened by the successive projection algorithm (SPA) was constructed using partial least squares regression (PLSR), random forest regression (RFR) and gaussian process regression (GPR) machine learning methods. The results indicated that: (1) Spectral data demonstrate greater sensitivity to LAI than Haralick textures, with sensitivity decreasing in the order of VIs, FDSR and OSR; (2) spectral data alone provide more accurate LAI estimates than Haralick textures, with VIs achieving an accuracy of R² = 0.63, RMSE = 0.38, NRMSE = 28.36%; and (3) although Haralick textures alone were not effective for LAI estimation, they can enhance LAI prediction when combined with spectral data, with the GPR method achieving R² = 0.70, RMSE = 0.30, NRMSE = 20.28%. These findings offer a valuable reference for large-scale, accurate monitoring of potato LAI.