Date of Award

5-2026

Degree Name

Master of Science

Department

Geography

First Advisor

Nicholas L. Padilla, Ph.D.

Second Advisor

Julio Pedrassoli, Ph.D.

Third Advisor

Rudy Bartels, Ph.D.

Access Setting

Masters Thesis-Open Access

Abstract

Local climatic zone (LCZ) classifications are traditionally done using reflectance, population data, and often climatic data. The goal of this research is to utilize Google’s new “Open Buildings Temporal v1” building data set as well as “spectral unmixing”. With the objective of testing, assessing, and implementing this data set into the workflow of LCZ mapping. After testing the quality of the data against a validated LiDAR data set from the same year as a given “Open Buildings Temporal v1” band, I implemented it into the Random Forest machine learning process. Secondly, I justified the use of spectral unmixing as a variable in classification. Finally, I assessed the impact of building height values and unmixed bands as variables in the model in the form of “variable importance”. Those results show that these two variables combined were 22.6% of the importance for the final model. While the final map showed an overall accuracy of 75.67%.

Share

COinS