Automating parcel classification for land management

Authors: Xinyue Ye*, New Jersey Institute of Technology, Kelly Turner, University of California Los Angeles, Bing She, University of Michigan
Topics: Geographic Information Science and Systems, Land Use, Urban and Regional Planning
Keywords: Land management, land parcel classification, open source, neighborhood-scale urban analysis
Session Type: Paper
Day: 4/4/2019
Start / End Time: 8:00 AM / 9:40 AM
Room: Congressional B, Omni, West
Presentation File: No File Uploaded


Homeowners’ Associations (HOAs) dictate landscape structure and management through legally enforceable land covenants at the neighborhood scale in the USA. Determining the location and spatial extent of HOAs is critical for examining its influence. However, such analysis is confounded by the lack of spatial data at the appropriate unit for such analysis. The purpose of this paper is to develop and realize an open source implementation to automate land parcel classification, which is an initial step towards the goal of determining the impact of HOAs on urban land management. Using Maricopa County, Arizona as a testbed, we found that parcel merging processes reduce the number of subdivisions from 26,042 to 17,269, such that boundaries better align with neighborhood units to which rule sets like land covenants apply. Moreover, after an initial training period, this process was completed in just over 7 hours. This research is an important first step in enabling a number of analysis including determining the location and spatial extent of HOAs regionally and, eventually, nationally and determining proposed links between HOAs and land management outcomes.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login