Study on the LAI and FPAR inversion of maize from airborne LiDAR and hyperspectral data

Abstract

ABSTRACT Maize is an important cereal crop and plays an important role in agriculture. The leaf area index (LAI) and the fraction of absorbed photosynthetically active radiation (FPAR) are important vegetation canopy structure parameters that are closely related to crop photosynthesis, transpiration and respiration and are of great significance for crop yield estimation. Hyperspectral data can obtain the spectral characteristic parameters of crops, and LiDAR data can obtain the vertical structure index. The former focuses on horizontal characteristic information, and the latter focuses on vertical characteristic information. In this paper, random forest method is used to carry out the inversion modelling of maize LAI and FPAR, and the effects of hyperspectral data resolution, LiDAR data density and scanning angle on the inversion accuracy are tested and analysed. The results show that there is good accuracy and stability of the random forest inversion model (LAI: 0.53 <R2 < 0.78, 0.094 < RMSE < 0.158, 0.009 < MSE < 0.025, 0.074 < MAE < 0.136; FPAR: 0.323 < R2 < 0.594, 0.09 < RMSE < 0.261, 0.008 < MSE < 0.068, 0.068 < MAE < 0.212). When using Hyperspectral data to invert LAI, the accuracy is the highest when the resolution is 1 metre (R2 = 0.742, RMSE = 0.141, MSE = 0.02, MAE = 0.119). When using LiDAR data to invert LAI, the accuracy is the highest when the density is 30% (R2 = 0.78, RMSE = 0.115, MSE = 0.013, MAE = 0.094). When using Hyperspectral data to invert FPAR, the accuracy is the highest when the resolution is 0.128 metre(R2 = 0.594, RMSE = 0.09, MSE = 0.008, MAE = 0.068). When using LiDAR data to invert FPAR, the accuracy is the highest when the density is 20% (R2 = 0.525, RMSE = 0.141, MSE = 0.02, MAE = 0.113).