Optimal IoT Sensor Deployment in the WUI: A Comparative Analysis of Strategies

Included here are individual burn maps used for evaluating algorithm results in the paper: Optimal IoT Sensor Deployment in the WUI: A Comparative Analysis of Strategies. This paper was accepted for presentation at IEEE HONET 2024, the 21st IEEE International Conference on Smart Communities. (For financial/travel reasons the paper has since been withdrawn)

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 optimized IoT sensor deployment strategies within the Wildland-Urban Interface (WUI), a key component of smart communities. It presents a comparative analysis of a novel dynamic grid approach against traditional random and greedy algorithms. By employing the Burn-P3+ simulator, detailed burn probability maps are generated for two Canadian geographically distinct areas: the Halifax Regional Municipality and Kelowna. Our analysis reveals that the dynamic grid method significantly enhances fire detection capabilities by strategically distributing IoT sensors in alignment with calculated burn probability. This approach shows a marked improvement of as much as 35% in burn detection over traditional deployment methods. The paper highlights the advantages of structured IoT sensor placement in supporting smart communities, offering more efficient and effective wildfire management strategies in the WUI through real-time data available to both fire mitigation teams and AI.

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