Landscape and Impervious Surface Mapping in the Twin Cities Metropolitan Area using Feature Recognition and Decision Tree techniques
Land Use and Land Cover (LULC) and Impervious Surface Area (ISA) are important parameters for many environmental studies, and serve as an essential tool for decision makers and stakeholders in Urban & Regional planning. Newly available high spatial resolution aerial ortho-imagery and LiDAR data, in combination with specialized, object-oriented and decision-tree classification techniques, allow for accurate mapping of these features. In this study, a method was developed to first classify LULC using an object-based classifier, and then use the resulting map as input for a decision-tree model to classify ISA in the Twin Cities Metropolitan Area in Minnesota. It was found that vegetation cover classes were the most prevalent in the study area, making up over half of the land area. Water was the smallest class, followed by urban land cover, which made up 11%. Impervious surface was determined to make up 14% of the TCMA area.Overall classification accuracy for LULC cover was estimated to be 74%, and 95% for the ISA classification.
Date of Degree
Master of Science (MS)
Social and Behavioral Sciences
Nagel, P. (2014). Landscape and Impervious Surface Mapping in the Twin Cities Metropolitan Area using Feature Recognition and Decision Tree techniques [Master’s thesis, Minnesota State University, Mankato]. Cornerstone: A Collection of Scholarly and Creative Works for Minnesota State University, Mankato. https://cornerstone.lib.mnsu.edu/etds/309/
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License