University of North Texas
Urban Tree Biomass Estimation Using Airborne LiDAR Data: A Case Study of the University of North Texas Campus
Abstract
dc:descriptionAccurate Aboveground Biomass (AGB) estimation plays an important role in effective forest management and monitoring tree health. The research estimates individual tree-level AGB on University of North Texas (UNT) main campus by integrating 2020 airborne LiDAR data with field inventory data. Methodologically, a Canopy Height Model derived from LiDAR points was used to detect the 1,792 treetops and delineate individual crowns. The treetops and tree crowns were further used to extract tree height, crown area and crown volume of individual tree. LiDAR points were used to determine the vertical structure metrics including Canopy Height Ranges and Canopy Skewness. The study compared four biomass estimation models (Linear Regression, Ridge Regression, Random Forest and Extreme Gradient Boosting) to determine the most effective method for urban context. Correlation Analysis concluded the tree metrics Tree Crown Area (r=0.73), and Crown Volume (0.66) were the strongest predictors for AGB estimation. The Ridge Regression model outperformed other models achieving a test R² of 0.454 and an overall R² of 0.574. The machine learning models (Random Forest and Extreme Gradient Boosting) underperformed compared with other models, likely due to the limited dataset size for training these complex algorithms. The findings demonstrated the utility of airborne LiDAR for estimating AGB at the individual tree level in heterogeneous landscape.
Degree
thesis:*- Grantor dc:publisher
- University of North Texas
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Thakuri, Suman Singh
- Contributors dc:contributor
-
- Rege, Rajshree
- Dong, Pinliang
- Jung, Jihoon
Subjects
dc:subject × 6Rights
dc:rights- Statement dc:rights
-
- Public
- Thakuri, Suman Singh
- Copyright
- Copyright is held by the author, unless otherwise noted. All rights Reserved.
- Language dc:language
- English
Identifiers
dc:identifier.*- Identifier
-
local-cont-no: submission_4508
https://digital.library.unt.edu/ark:/67531/metadc2482610/
ark: ark:/67531/metadc2482610