IoT Sensor Deployment in the Wildland Urban Interface: Leveraging Fire Risk Analysis

Included here are individual burn maps used for evaluating algorithm results in the paper: IoT Sensor Deployment in the Wildland Urban Interface: Leveraging Fire Risk Analysis. This paper will be presented at the IEEE World Forum on Internet of Things in November 2024 and available on IEEE Xplore after that.

Also included are maps of fuel load and elevation (geotifs) and the daily weather (in .csv format) for the region of interest used in the burn probability simulator Burn-P3+ to generate the individual burn maps.

This paper investigates various algorithms for distributing Internet of Things sensors within the Wildland-Urban Interface to enhance early wildland fire detection. Utilizing geospatial data analysis and a validated wildland fire growth model burn maps were generated to guide sensor placement strategies across a defined region of interest. The algorithms evaluated include an even grid distribution, random distributions, and genetic algorithm-based methods. Each algorithm was tested against 50,000 selected burn maps to assess detection rates, with sensor counts ranging from 50 to 800 across 500 experimental runs. Results indicate that while the even grid distribution yielded the highest detection rates, the practicality of such a method in real-world applications is limited. Genetic algorithms showed promise, but require further exploration to more accurately simulate random distribution used in field deployment. Surprisingly, weighting sensor placement based on wildland fire growth risk did not significantly impact detection effectiveness, suggesting the need for additional research into the representativeness of selected burn maps.

Partial code for the sensor deployment algorithms discussed in the above mentioned paper is available on GitHub.