Estimation of Rice Protein Content Based on Unmanned Aerial Vehicle Hyperspectral Imaging

Identification of nutritious rice varieties through non-destructive detection technology is important for high-quality seed production. With the development of technology, rapid and non-destructive identification methods based on unmanned aerial vehicle (UAV) remote sensing technology are increasingly gaining attention in the scientific community. This study utilized hyperspectral imaging technology to acquire spectral reflectance data from the rice canopy during the grain filling stage. Different models (stepwise multiple linear regression (SMLR) and the Back Propagation Neural Network (BPNN)) for estimating rice protein content based on canopy spectral information were constructed using both multiple stepwise regression and BP neural networks. The results showed that the model based on BPNN estimation performed best for predicting grain protein content, with an R2 = 0.9516 and RMSE = 0.3492, indicating high accuracy and stability in the model. Overall, hyperspectral imaging technology combined with various models could significantly help to identify rice varieties. Further, the current findings provide a technical reference for the selection of high-quality rice varieties in a non-destructive manner.