Open Collections

Seely, Harry

Harry Seely was a semi-finalist in the 2024 UBC Three Minute Thesis (3MT) competition. Harry presented their research, "Applying Deep Learning to Optimize Lidar-Based Forest Carbon Models." They hope to enhance aboveground tree biomass estimation using deep neural network models, contributing to improved forest management and carbon accounting. Airborne laser scanning (ALS) data has been widely used for total aboveground tree biomass (AGB) modelling, however, there is less research focusing on estimating specific tree biomass components (wood, branches, bark, and foliage). Knowledge about these biomass components is essential for carbon accounting, understanding forest nutrient cycling, and other applications. In this study, Harry performs AGB estimation using deep neural network (DNN) and random forest (RF) models. They utilise two point cloud DNNs: point-based Dynamic Graph Convolutional Neural Network (DGCNN) and Octree-based Convolutional Neural Network (OCNN). Harry Seely is completing their PhD in Forestry in the Department of Forest and Conservation Sciences under the supervision of Dr. Nicholas Coops.

Moving Image; Text

Three Minute Thesis (3MT)

Vancouver : University of British Columbia Library

10.14288/1.0447813

Forestry, Faculty of

Graduate

DSpace