A new method for voxel-based modelling of three-dimensional forest scenes with integration of terrestrial and airborne LiDAR data

<ol><li>Simulating realistic three-dimensional (3D) forest scenes is useful in understanding the links between forest structure and ecosystem functions (e.g. radiative transfer). Light detection and ranging (LiDAR) technology provides useful 3D data for forest reconstructions since it can characterise 3D structures of individual trees and canopies. High-density terrestrial LiDAR (terrestrial laser scanning, TLS) is suitable for fine-scale reconstructions but is limited to smaller forest plots; low-density airborne LiDAR (airborne laser scanning, ALS) can cover larger areas but is only suitable for coarse-scale reconstructions. How to take advantage of TLS and ALS to enable fine-scale forest simulations in large areas needs to be studied.</li><li>We propose a new voxel-based method for forest simulations using the integration of TLS and ALS data. TLS data of representative reference trees are used to approximate the detailed architectures of the whole forest scene, with structural information on each individual tree extracted from ALS data. The high-density point cloud data derived from TLS and ALS data are voxelised using high resolution solid voxels for scene representation. We tested the proposed method using two virtual forests (108 m x 108 m) and a real forest (300 m x 300 m) with conifer and broadleaf species. The physically based ray tracer (PBRT) was used to visualise the true virtual forest scenes, whereas voxel-based radiative transfer (VBRT) was used to visualise the modelled forest scenes from LiDAR data. For the real forest scene, simulated and real ALS data were compared.</li><li>Our results demonstrate that the images simulated by VBRT and PBRT are similar in the virtual forest scenes, with average radiance values of 1.02 and 1.72, respectively. In the real forest scene, the distributions of points and individual tree attributes (tree height, crown radius, and tree volume) derived from real and simulated ALS also match well, with Kullback-Leibler divergence ranging from 0.006 to 0.06.</li><li>We conclude that the new method is capable of modelling fine-scale 3D forests in large areas (over 1 ha) when TLS and ALS data are available, and it has good potential in studying the process of radiative transfer in conifer and broadleaf forests.</li> </ol>