Modeling urban leaf area index with AISA+ hyperspectral data

This study used simple multiple regression to model urban leaf area index (LAI) in Terre Haute, Indiana, USA as a function of AISA+ hyperspectral radiance and its derivative features. Regression R2 values ranging from 0.27 to 0.73 were obtained from the various models. Features appearing most frequently in the models included radiance at 0.727, 0.753, 0.848, 0.870, 0.900 and 0.917 μm. The best single predictor of LAI was the absolute difference in radiance between 0.777 and 0.673 μm. The best models performed well at low and intermediate LAI levels, but were less accurate with LAI values between 5.0 and 8.0.