This study is based on the rank difference of the nitrogenous nutrition level by the man made style through two years rice farm experiment about the difference of the nitrogenous nitrition level. Using linear and non linear and stepwise multiple regression methods

the estimation models about LAI of rice have been built on the basis of the experimental data in 1999 which where evaluatde and validated with experimental data of the year 2000 as training samples. The results show that there are the ralationships between the characteristic variables of hyperspectra and LAI . From the results of precision analysis

the models that the vegetation indices variables of sum of the 1st derivative value within red edge （ SDr） and the blue edge （ SDb） are the best one of estimating LAI of Rice by hyperspectral remote sensing data.