Wildfire Spread Modeling in Pau Furado State Park Using Cellular Automata and Genetic Algorithms

• Maria Eugênia A. Ferreira UFU
• Danielli A. Lima IFMT
• Luiz Gustavo A. Martins UFU

DOI: https://doi.org/10.5753/wcama.2025.8942

Resumo

Wildfire spread has intensified in Brazil, particularly in biomes such as the Cerrado, due to climate change and environmental degradation. This study proposes a heterogeneous wildfire spread model based on cellular automata (CA), optimized using genetic algorithms (GA), to simulate fire propagation in areas with different vegetation types, such as Pau Furado State Park. The model accounts for the interaction between wind, vegetation, and soil conditions, and employs the GA to adjust parameters such as fire intensity and wind direction, aiming to align the simulations with reference data. The results showed that the model accurately reproduced fire spread dynamics, demonstrating the effectiveness of GA in parameter optimization.

Referências

Alexandridis, A., Vakalis, D., Siettos, C. I., and Bafas, G. V. (2008). A cellular automata model for forest fire spread prediction: The case of the wildfire that swept through spetses island in 1990. Appl. Mathematics and Computation.

Brasiel, H. and Lima, D. (2024). Parameter analysis in probabilistic cellular automaton model for fire spread simulation in sete cidades national park. In Anais do XV Workshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais, pages 101–110, Porto Alegre, RS, Brasil. SBC.

Ferreira, M. E. A., Lima, D. A., Martins, L. G. A., and Oliveira, G. M. B. (2022a). Refining a parameter setting evolutionary approach for fire spreading models based on cellular automata. In 2022 International Conference on Computational Science and Computational Intelligence (CSCI), pages 480–486.

Ferreira, M. E. A., Quinta, A. L. M. P., Lima, D. A., Martins, L. G. A., and Oliveira, G. M. B. (2022b). Automatic evolutionary adjustment of cellular automata model for forest fire propagation. In ACRI.

Fraga, L. M., Oliveira, G. M. B., and Martins, L. G. A. (2021). Multistage evolutionary strategies for adjusting a cellular automata-based epidemiological model. In IEEE CEC.

Martins, L. G., Franca, T. P., and de Oliveira, G. M. (2019). Bio-inspired algorithms for many-objective discrete optimization. In 2019 8th Brazilian Conference on Intelligent Systems (BRACIS), pages 515–520. IEEE.

Monteiro, L., Fanti, V., and Tessaro, A. (2020). On the spread of sars-cov-2 under quarantine: A study based on probabilistic cellular automaton. Ecological Complexity, 44:100879.

Mota, P. H. S., da Rocha, S. J. S. S., de Castro, N. L. M., Marcatti, G. E., de Jesus França, L. C., Schettini, B. L. S., Villanova, P. H., dos Santos, H. T., and dos Santos, A. R. (2019). Forest fire hazard zoning in mato grosso state, brazil. Land use policy, 88:104206.

Murilo, L. V., Oliveira, G. M. B., and Martins, L. G. A. (2025). Evolutionary adjustment of a cellular automata-based model for wildfire spreading. In Intelligent Systems, pages 260–275, Cham. Springer Nature Switzerland.

Oliveira, G. M. B., De Oliveira, P., and Omar, N. (2001). Improving genetic search for one-dimensional cellular automata, using heuristics related to their dynamic behavior forecast. In IEEE CEC.

Ramos-Neto, M. B. and Pivello, V. R. (2000). Lightning fires in a brazilian savanna national park: rethinking management strategies. Environmental management, 26(6):675–684.

Tinoco, C. R., Lima, D. A., and Oliveira, G. M. (2019). An improved model for swarm robotics in surveillance based on cellular automata and repulsive pheromone with discrete diffusion. Int. Journal of Parallel, Emergent and Distributed Systems, 34(1).