Estimation of Leaf Phosphorus Content in Cotton Using Fractional Order Differentially Optimized Spectral Indices.

The accurate and timely detection of leaf phosphorus content (LPC) is extremely important for the fertilization management of crop growth and yield. This study aimed to establish an estimating model of LPC in cotton based on hyperspectral data. Under field experimental conditions with different phosphorus treatments, the spectral data and LPC were measured. The spectral characteristics of different cotton cultivars and leaves with varying phosphorus content were analyzed. Optimized spectral indices most correlated to phosphorus were calculated with combinations of arbitrary bands using the Fractional Differential Order (FOD) transform. Then, the random forest-based(RF) estimation model for cotton LPC was established. The research results indicated that (1) the spectral changes of 24 cotton cultivars were basically consistent, and spectral differences between the cultivars became more obvious within the 760-960 nm spectral region; (2) in the visible region, the reflectance of cotton under different phosphorus treatments did not show obvious regularity, while in NIR, the reflectance of cotton increased with the increase in phosphorus content, showing a certain difference in phosphorus; (3) the RF model using a difference spectral index (DSI) had the best performance for LPC estimations in calibration (R = 0.78) and validation (R = 0.85), which was superior to the other models based on two spectral indices (the NDSI and RSI). This study provides technical support for the hyperspectral estimation of LPC in cotton.