Authors: Zachary Cleland*, , Diep Dao, University of Colorado Colorado Springs
Topics: Geographic Information Science and Systems
Keywords: Wildfire, Colorado, Datamining, GIScience,
Session Type: Paper
Start / End Time: 1:45 PM / 3:00 PM
Room: Director's Row I, Sheraton, Plaza Building, Lobby Level
Presentation File: No File Uploaded
The phenomenon of human-caused wildfire presents significant dilemmas for States like Colorado, especially given a growing population and large portions of forested mountain eco-regions. This study investigated the circumstances of human caused wildfire from 1992-2015 within Colorado’s Forested Mountain and North American Desert eco-regions using spatial association mining. This study extracted the associations amongst human caused wildfire variables by utilizing the Apriori Algorithm while allowing various spatial predicates to present complex iterative behaviors of variables across space. We also examined changes in the associations for different time periods and compared our findings with existing literature. This research leverages Colorado wildfire data to assess the inherent variable associations and whether it presents new knowledge or reflects existing wildfire variables found in previous literature. Existing research has suggested that human caused wildfires are spatially and temporally dependent. This case study found some variable associations that align with some previous wildfire literature regarding human population density. The population density variable stayed consistent over time. Other notable variables presented indications of change over time instead of consistency over the entire study period. The information extracted may prove useful for informing policy on land development, future risk analysis, and considerations for further human caused wildfire modeling studies within Colorado.