Leaf properties estimation enhancement over heterogeneous vegetation by correcting for terrestrial laser scanning beam divergence effect

The need for an accurate description of forest structure is increased as it is a key for monitoring carbon storage, energy, and mass exchange, and different ecosystem functions. The leaf area index (LAI), the leaf area density (ul), and the leaf inclination distribution function (LIDF) are regarded as important and critical keys allowing the characterization of the forest structure. The dependency between these properties and the heterogeneity of the forest makes their estimation challenging and delicate. In this context, despite the expanding body of works reporting forest structure properties retrieval using infinitesimal footprint size terrestrial LiDAR system (TLS) data, there seem to be few works evaluating the influence of the TLS beam divergence effect (i.e. its size increase with distance from the sensor), on the estimation accuracy, even though the influence is not negligible. In this study, we aim to jointly estimate LAI/ul and LIDF using non-infinitesimal footprint size TLS data based on forward/inverse radiative transfer (RT) modeling. Our approach assumes a uniform distribution of azimuth angles enabling us to attain valuable insights into inclination angles and leaf area density while simplifying our computational efforts. The forward modeling allows an understanding of the interaction between vegetation structure properties and TLS light beams, while the inversion allows retrieving the properties given the TLS data. The inversion technique is based on the maximum likelihood estimator (MLE). Our problem turns out to be a non-linear and high-dimensional cost function to be optimized. To tackle this complexity, the global optimization technique, the shuffled complex evolution (SCE-UA), is adapted to find the globally optimal solution. Our developed approach is validated with simulated and actual forest TLS point clouds acquired from Estonian Pine, Birch, and Spruce stands. Our findings using simulated data prove that our estimates are in agreement with the actual ul and LIDF values with (MAEul is an element of [0.0012 0.0043]) and (RMSEul is an element of [0.0137 0.0224]). In the actual case, RMSELAI for Pine, Birch and Spruce stands are 0.1066, 0.014, and 0.070, respectively. In all cases, our approach outperforms state -of -the -art techniques.