Simulated fire observables as indicators for optimizing wireless sensor networks in wildfire risk monitoring

J.L. Gómez, E. Marcoulaki, A. Cantizano, M. Konstantinidou, R. Caro, M. Castro

Ecological Indicators Vol. 175, pp. 113509-1 - 113509-15

Summary:

Uncontrolled wildfires cause significant damage and economic costs. Wireless Sensor Networks (WSNs) can mitigate these impacts by detecting fires early across extensive wildland areas. This work presents a simulation-driven optimization framework for localizing WSNs to enhance early wildfire detection and minimize potential damage. Formulated as a Multi-Objective Optimization Problem (MOOP) and solved using the Non-dominated Sorting Genetic Algorithm II (NSGA-II), the method utilizes dynamic wildfire simulations and considers stochastic variables such as ignition likelihood and weather conditions. The methodology is general and independent of the simulation model or the studied region. The framework supports decision-making under uncertainty, ensuring the designed networks remain effective across varying conditions. A practical case study with validated fire behaviour demonstrates the robustness of the approach to identify the most efficient and cost-effective sensor locations. Results show significantly better performance compared to uniform sensor grids and WSNs designed for fixed-weather scenarios, highlighting the benefits of this approach for wildfire management.

Spanish layman's summary:

Esta investigación propone usar simulaciones de incendios para optimizar el diseño de redes de sensores inalámbricos en entornos vulnerables frente a incendios forestales. La metodología es flexible respecto al simulador e incorpora incertidumbre meteorológica para producir soluciones robustas.

English layman's summary:

This study presents a simulation-driven approach to optimize the placement of wireless sensor networks for early wildfire detection. By leveraging fire behavior models, the method identifies sensor configurations that maximize detection performance while minimizing deployment costs. The research highlights how strategically located sensors can not only detect ignitions promptly but also anticipate fire spread, aiding in evacuation planning and protection of critical assets. These findings lay the groundwork for more effective, scalable wildfire monitoring systems in high-risk areas. This methodology is flexible regarding the simulated wildfire observable – e.g. smoke dispersion, concentration of combustion gases, heat from the fire perimeter—and incorporates uncertainty in the meteorological scenarios, ensuring the solutions are robust against weather variability.

Keywords: Wildfire simulation; Optimization; Early wildfire detection system; Wireless sensor network; NSGA-II

JCR Impact Factor and WoS quartile: 7,000 - Q1 (2023)

DOI reference: https://doi.org/10.1016/j.ecolind.2025.113509

Published on paper: June 2025.

Published on-line: May 2025.

Citation:
J.L. Gómez, E. Marcoulaki, A. Cantizano, M. Konstantinidou, R. Caro, M. Castro, Simulated fire observables as indicators for optimizing wireless sensor networks in wildfire risk monitoring. Ecological Indicators. Vol. 175, pp. 113509-1 - 113509-15, June 2025. [Online: May 2025]