Usage
  • 83 views
  • 105 downloads

Wildland-Urban Interface Fire Exposure Assessment Using Remote-Sensing Framework

  • Author / Creator
    Afaghi, Mohammad
  • Wildfires occurring in proximity to urban areas pose a potential risk to the safety and wellbeing of the population, while also carrying the potential for substantial economic damage through the destruction of infrastructure and private property. Canada, given its unique geographical and climatic conditions, is among the countries facing significant wildfire challenges. Alberta, in particular, has recorded the highest number of wildfires compared to other Canadian provinces, making it increasingly susceptible to fires in Wildland Urban Interface (WUI) regions. These are regions where natural vegetation intersects or mixes with structures, and where the population is growing. Due to the vastness of human settlements and infrastructure needed to be monitored, the precision of fire risk assessment plays a crucial role in effective fire management. It is therefore necessary to advance a framework to determine fire behaviour in WUI. In this study I focus on fire exposure within the WUI, and a building in the City of Edmonton serves as a case study. Studies suggest that the characteristics of a small portion of the WUI, known as the Home Ignition Zone (HIZ), are a significant factor in determining the level of exposure in wildfire ignition. The primary goal of this study is to develop an automated method that aligns with national guidelines for characterizing vegetation land cover as various fuel types. This method employs convolutional neural networks and incorporates topographical factors, including the identification of ignition zones near buildings and accounting for slope effects. These parameters are valuable for pinpointing potentially high-risk individual HIZ or clusters of HIZ in a neighborhood. Summertime RGB satellite imagery is utilized to detect and categorize tree canopies and grass-covered areas, while wintertime satellite imagery is employed to address the challenge of distinguishing between conifer and deciduous trees, two fuel types with differing fire behaviours. The methods described in this study can be combined with in situ data collection and extended for use in different regions to inform hazard mitigation plans.

  • Subjects / Keywords
  • Graduation date
    Spring 2024
  • Type of Item
    Thesis
  • Degree
    Master of Science
  • DOI
    https://doi.org/10.7939/r3-rw08-sj62
  • License
    This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.