This research uses LiDAR and individual tree segmentation to replace traditional polygon-based forest inventories with precise, tree-level data. By modelling the growth and interactions of individual trees, it enables more accurate forest management, improving timber planning, ecosystem resilience, and climate adaptation while supporting sustainable forestry across British Columbia.

This study evaluated a PointNet++ deep learning model for binary classification of Pinus sylvestris and Quercus pyrenaica using only LiDAR 3D point clouds. A balanced dataset of 160 trees achieved 91% accuracy, showing that geometric features alone can effectively discriminate species, highlighting the potential of lightweight AI models for forest inventories.

This research develops new height–diameter models for key Spanish tree species to improve forest management planning. While initial models fit data visually, statistical performance remains weaker than current equations. Future work will incorporate stand-level variables such as basal area and dominant height to enhance accuracy and reduce estimation errors.