Estimation of rice plant potassium accumulation based on non-negative matrix factorization using hyperspectral reflectance

Rapid and accurate estimation of plant potassium accumulation (PKA) using hyperspectral remote sensing is of significance for the precise management of crop K fertilizer. This study focused on the separation of non-negative matrix factorization (NMF) for hyperspectral reflectance from the ground and unmanned aerial vehicle (UAV) platforms and its mitigation effect on the water and soil background. Pure vegetation spectra were extracted from the canopy mixed spectra using NMF, and then a partial least-squares regression (PLSR) model was established based on the extracted vegetation spectra and rice PKA to construct an estimation model of rice PKA. The results showed that the green light and red edge bands contributed significantly to the rice PKA estimation. NMF could effectively extract pure vegetation and water and soil spectra from mixed spectra, and enhance the green peak, red valley, and red edge information of the extracted vegetation spectra. Compared with spectral indices, the PLSR performed best for ground and UAV data. Besides, the R-2 of the PLSR model based on NMF-extracted vegetation spectra increased by 15.15% to 0.76%, and the verified RMSE and RE decreased by 16.93% and 16.77% to 3.19 g m(-2) and 45.07%, respectively. Hyperspectral dataset testing from different years, growth stages and varieties, and UAV platforms showed that NMF could improve the estimation accuracy of rice PKA. This study showed that NMF could be applied to both ground and UAV hyperspectral platforms to improve the estimation accuracy of rice K nutrition.

Automated summary

This study focused on extracting pure vegetation spectra using non-negative matrix factorization (NMF) from hyperspectral reflectance, establishing a model for estimating rice potassium accumulation (PKA). Results showed that NMF effectively extracted pure vegetation and water and soil spectra, enhancing vegetation spectral information. The partial least-squares regression (PLSR) model based on NMF-extracted vegetation spectra performed best for ground and UAV data, with improved accuracy in estimating rice PKA.