Estimation of Potato Canopy Nitrogen Content Based on Hyperspectral Index Optimization

Potato canopy nitrogen content (CNC) is an imperative metric for assessing potato growth status and guiding field management. While the spectral index can be utilized to estimate CNC, its efficacy influenced by environment crop type. To address this issue, we hyperspectral indices (HIs) optimization CNC estimation. Using inverse first-order differential (FD) transformations of original data (OD), HIs comprising two-band combinations in 400–1000 nm, such as RSI, DSI, NDSI, SASI, PSI, were constructed analyze correlation between HIs. Based on analysis, prediction models created using most optimal The results showed that FD transformation significantly improved correlations HIs, among which FD−PSI(R654, R565) had highest with CNC. We further employed variables establish univariate multivariate regression Among models, accuracy OD−DSI model was highest, R2 0.79 RMSE 0.22. Meanwhile, FD−MLR demonstrated compared other 0.84, 0.20 during validation, a greater than model. used map distribution monitored planting plots guide precision fertilization.