Abstract:Aiming to obtain the leaf area index (LAI) of largescale summer maize in a highefficiency, nondestructive and largescale manner, and provide a technical reference for remote sensing monitoring of summer maize growth. The research was based on the fieldcollected summer maize LAI and maize height, as well as combined with multispectral data of the same period, eight vegetation indexes and height with strong correlation with summer maize LAI were selected as the input variables of gradient boosting decision tree (GBDT) algorithm model for LAI inversion. The support vector machine (SVM) model and the random forest (RF) model were taken as the reference models, which were used to compare the accuracy of prediction. The results showed that the GBDT algorithm model prediction consequence were better than the other two models among the three sample groups. R2 of prediction value and measured LAI values of the sample groups 1, 2 and 3 were 0.5710, 0.7558 and 0.6441, respectively, which were higher than those of the SVM models (0.5472, 0.6791, 0.6168) and RF models (0.5505, 0.6973, 0.6295), corresponding root mean square error (RMSE) values were 0.0027, 0.0015 and 0.0016, which were lower than those of the SVM model (0.2117, 0.1523 and 0.1597) and RF model (0.2447, 0.2147 and 0.2080). The research result provided a technical method for fast and accurate monitoring of summer maize LAI remote sensing in the field.