Estimation of potato canopy leaf water content in various growth stages using UAV hyperspectral remote sensing and machine learning

To ensure national food security amidst severe water shortages, agricultural irrigation must be reduced through scientific innovation and technological progress. Efficient monitoring is essential for achieving water-saving irrigation and ensuring the sustainable development of agriculture. UAV hyperspectral remote sensing has demonstrated significant potential in monitoring large-scale crop leaf water content (LWC). In this study, hyperspectral and LWC data were collected for potatoes (Solanum tuberosum) during the tuber formation, growth, and starch accumulation stage in both 2021 and 2022. The hyperspectral data underwent mathematical transformation by multivariate scatter correction (MSC) and standard normal transformation (SNV). Next, feature spectral bands of LWC were selected using Competitive Adaptive Reweighted Sampling (CARS) and Random Frog (RF). For comparison, both the full-band and feature band were utilized to establish the estimation models of LWC. Modeling methods included partial least squares regression (PLSR), support vector regression (SVR), and BP neural network regression (BP). Results demonstrate that MSC and SNV significantly enhance the correlation between spectral data and LWC. The efficacy of estimation models varied across different growth stages, with optimal models identified as MSC-CARS-SVR (R2 = 0.81, RMSE = 0.51) for tuber formation, SNV-CARS-PLSR (R2 = 0.85, RMSE = 0.42) for tuber growth, and MSC-RF-PLSR (R2 = 0.81, RMSE = 0.55) for starch accumulation. The RPD values of the three optimal models all exceed 2, indicating their excellent predictive performance. Utilizing these optimal models, a spatial distribution map of LWC across the entire potato canopy was generated, offering valuable insights for precise potato irrigation.