WOOD-LEAF UNSUPERVISED CLASSIFICATION OF SILVER BIRCH TREES FOR BIOMASS ASSESSMENT USING OBLIQUE POINT CLOUDS

Forests play a fundamental role in carbon stocking since about a third of the carbon dioxide produced by activities of human origin is absorbed by forests. Forest biomass is an essential indicator of carbon dioxide absorption, enabling an understanding the interaction between forest dynamics and climate change effects. However, biomass and wood material changes are challenging to quantify in forest stands. Nowadays, recent 3D remote sensing technologies, such as laser scanning systems, have allowed accurate measures of single trees. This study evaluates three approaches to classify wood and non-wood materials and quantify biomass based on LiDAR data, aiming at biomass change detection. Specifically, we propose an automated methodology for estimating the single tree-level biomass of a portion of forest monitored through a LiDAR oblique acquisition. The classification of wood and foliage points was performed with machine learning algorithms, while the tree modelling was conducted rigorously through a Quantitative Structure Model (QSM). The purpose of this study is to evaluate (1) two different unsupervised and one semi-supervised classification approaches for wood and foliage separation and (2) the accuracy of the biomass assessment performed on a QSM-based approach on innovative LiDAR acquisitions. The results are promising; the wood-leaf classification performs effectively in all 20 silver birches considered; as regards the biomass, when the noise is limited, it is estimated in a manner consistent with the reference values calculated using an appropriate allometric equation. Higher values are found mainly in dense undergrowth, which negatively affects the modelling of the tree. The research is ongoing, and further tests will be performed to generalize the methodology on different tree species, deepen the multitemporal variability, and improve the accuracy of the assessment.