Estimation of Potato Canopy Nitrogen Content Based on Hyperspectral Index Optimization

Abstract

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