Defense Presentation Title: Estimating and Modeling Structural Characteristics of Trees Within Aerial LiDAR Data

Co-Advisors: Dr. Perver Baran, faculty fellow and teaching professor, Center for Geospatial Analytics; Dr. Laura Tateosian, faculty fellow and associate teaching professor, Center for Geospatial Analytics

Abstract: The transparency and shape of tree crowns in urban areas play a critical role in applications such as solar energy potential estimation, urban microclimate modeling, and urban landscape planning and architecture. Data-driven approaches model tree crown attributes using point cloud data, but high-density point clouds are cost-prohibitive. To improve modeling capabilities of widely available medium-resolution aerial LiDAR, this dissertation explores techniques for urban tree modeling, including accounting for seasonal variations in crown transparency, using deep learning to select the crown shape of a tree based on its point cloud, and comparing the performance of algorithms for tree crown delineation.