Evaluating Different Methods for Winter Wheat Water Content Estimation from Hyperspectral Remote Sensing Data.

Monitoring the water status of winter wheat under different nitrogen treatments is important for effective water management in precision agriculture. The hyperspectral data can

provide continuous spectral information and shows to be a promising tool for precisely describing canopy water content. In this study narrow-band spectral indices (calculated from all possible two band combinations), partial least square (PLS), artificial neural network model (ANN) and Support Vector Machine (SVM) were used to estimate winter wheat water content at canopy scale. The experiment was conducted on 72 winter wheat plots located at Texas A&M Brazos Farm, TX on four different varieties and four different nitrogen rates. Canopy spectra were measured by an ASD FieldSpec and the canopy water content of the related plots were also measured. Validation of the methods was based on the cross validation procedure and using three statistical indicators: R², RMSE and relative RMSE. The cross-validated results identified all models providing accurate estimates of canopy water content in winter wheat crop.