Plot-level point clouds were processed using TLS2trees which is a set of Python command line tools & designed to be horizontally scalable, e.g., on a High Performance Computing (HPC) facility. Pipeline steps: 1) Point cloud re-processing, 2) semantic segmentation into wood & leaf point classes, 3) instance segmentation into sets of point clouds representing individual trees, 4) Quantitative structural models (QSMs) of individual tree point clouds, & 5) Plot biophysical & AGB estimates.