The comparison of two inversion methods for Jun jujube leaf area index based on hyper spectral remote sensing

In this study, the different hype rspectral inversion methods for jun jujube leaf area index was constructed to improve the accuracy and adaptability of simulation model. We Choose Alaer in Xinjiang as the study area, collect jun jujube leaves there back to the laboratory, and scan them by ASD FieldSpec HH portable object spectrometer to get the reflectance spectrum data and calculated LAI values. And establish jun jujube LAI inversion model by using the methods of regression analysis and BP neural network, Then, analysis and evaluate the inversion precision of two different methods. The results show that BP neural network inversion method can build a much better LAI inversion for jun jujube than the regression analysis method. Among them, the BP neural network inversion model has the highest R2 (0.950) and least RMSE (0.156). So the BP neural network method is used to establish the inversion model is better for jun jujube LAI inversion.