Retrieval of biophysical vegetation parameters using simultaneous inversion of high resolution remote sensing imagery constrained by a vegetation index

摘要

This study proposes a new method for inverting radiative transfer models (RTM) to retrieve canopybiophysical parameters using remote sensing imagery. The inversion procedure is improved with respect to standardinversion, and achieves simultaneous inversion of leaf area index (LAI), soil reflectance (ρsoil), chlorophyll content(Ca+b) and average leaf angle (ALA). In this approach, LAI is used to constrain modelling conditions during theinversion process, providing information about the phenological state of each plot under study. Due to the small areaof the vegetation plots used for the inversion procedure and in order to avoid redundant information and improvecomputation efficiency, existing plot segmentation was used. All retrieved biophysical parameters, except LAI, wereassumed to be invariant within each plot. The proposed methodology, based on the combination of PROSPECT andSAILH models, was tested over 16 cereal fields and 51 plots, on two dates, which were chosen to ensure cropassessment at different phenological stages. Plots were selected to provide a wide range of LAI between 0 and 6.Field measurements of LAI, ALA and Ca+b were conducted and used as ground truth for validation of the proposedmodel-inversion methodology. The approach was applied to very high spatial resolution (VHR) remote sensing datafrom the QuickBird 2 satellite. The inversion procedure was successfully applied to the imagery and retrieved LAIwith R2=0.83 and RMSE=0.63 when compared to LAI2000 ground measurements. Separate inversions for barleyand wheat yielded R2=0.89 (RMSE=0.64) and R2=0.56 (RMSE=0.61), respectively.