Effects of Plant and Scene Modeling on Canopy NDVI Simulation: A Case Study on Phragmites Australis and Spartina Alterniflora

Plant and scene three-dimensional (3-D) modeling, combined with radiative transfer (RT) modeling, are of great importance for mastering canopy reflectance characteristics and further developing target recognition and parameter retrieval in remote sensing images. However, 3-D RT simulation of large, complex landscapes is generally too demanding in terms of computing time and memory space. Simplifying plant models can significantly reduce the computational load, but with the accuracy reducing in radiation simulations. It is necessary to balance the complexity of plant models and the efficiency of 3-D RT simulation while maintaining high simulation accuracy. We investigated this issue for the vegetation of the Yangtze River estuary in eastern China. First, we used a series of created 3-D models of two species (Phragmites australis and Spartina alterniflora) to simulate canopy reflectance with the discrete anisotropic radiative transfer (DART) model. Then, we investigated how the simulated plant model complexity, plant density, and scene unit scale influence the accuracy and computation time of canopy normalized difference vegetation index (NDVI) simulation. The comparison of different parameterization simulations leads to three major conclusions. It is not necessary to simulate the actual vegetation density exactly, given the simplifications and approximations inherent in simulations. A specific 3-D model per species is needed for simulation since plants’ morphological structures different. Simplifying plant 3-D models and using a coarser DART scale of analysis shortens simulation time, but decreases the accuracy of the simulated canopy NDVI to varying degrees. Based on these results, we propose a universal optimization scheme that balances the accuracy and computation time of canopy NDVI simulation.