Improving the estimation accuracy of SPAD values for maize leaves by removing UAV hyperspectral image backgrounds

Hyperspectral images collected by unmanned aerial vehicles (UAVs) can provide fine, narrowband spectral information and help realize the accurate estimation of physiological and biochemical crop parameters at the plot scale. However, exposure to different backgrounds will negatively affect crop chlorophyll diagnosis. This research investigated the impact of the background and its degree of influence on the accuracy estimation of soil and plant analyser development (SPAD) values. UAV-based hyperspectral images of 498 maize inbred lines were obtained during the grain filling stage. Twenty vegetation indices (VIs) were calculated. VIs that were sensitive to the SPAD value were screened out by the Boruta algorithm. Estimation accuracies of the SPAD values before and after removing the background were compared and analysed. The results showed that Pearson's correlation coefficient (r) between VIs with background removal and the SPAD value was higher than that without background removal. The SPAD value estimated with sensitive VIs after removing the background was significantly closer to the measured value than that estimated before removing the background. The verification accuracy of the model with background removal was higher than that without background removal. With background removal, the coefficient of determination (R2), root mean square error (RMSE) and mean absolute error (MAE) increased by 60.87%, 48.39% and 40.89%, respectively. This study indicates that removal of the background improves the estimation accuracy of the SPAD value for maize leaves. Maize growth parameters could be quickly obtained from UAV hyperspectral images.