A Hybrid Model for Forest Fire Prediction Based on Cellular Automata and Advanced Machine Learning

International Journal of Emerging Research in Science, Engineering, and Management
Vol. 2, Issue 3, pp. 65-72, March 2026.

https://doi.org/10.58482/ijersem.v2i3.9

This work is licensed under a Creative Commons Attribution 4.0 International License.

Full Text PDF

A Hybrid Model for Forest Fire Prediction Based on Cellular Automata and Advanced Machine Learning

K Hema

G Hari Priya

R Bhaskar

M Ganesh Babu

M Harish Sai

Department of CSE, Siddharth Institute of Engineering & Technology, Puttur, India.

Abstract: Forest fires are becoming more common and more dangerous because of climate change, causing serious harm to forests, wildlife, and nearby communities. Detecting fires early and predicting where they might happen is essential to reducing damage and responding quickly. In this work, a machine learning–based system was developed that predicts forest fire risk using simple environmental factors like temperature, humidity, rainfall, and wind speed. Tested different algorithms, such as Random Forest, SVM, and Logistic Regression, to find which one can best identify conditions that may lead to a fire. Using publicly available datasets, the models performed with high accuracy and proved reliable in spotting fire-prone situations. Analyzed which features contribute the most to fire risk, helping us understand the conditions that matter most. The proposed approach can be easily connected to IoT sensors or satellite data to monitor forests in real time and send early alerts. Overall, the study shows that machine learning can be a powerful, affordable, and scalable tool for improving forest fire prevention and early warning systems.

Keywords: Forest Fire Prediction, Random Forest, Logistic Regression, Fire Risk Assessment, Climate Change.

References: 

  1.  Alonso-Betanzos et al., “An intelligent system for forest fire risk prediction and fire fighting management in Galicia,” Expert Systems With Applications, vol. 25, no. 4, pp. 545–554, Jun. 2003, doi: 10.1016/s0957-4174(03)00095-2.
  2.  Abdalhaq, A. Cortés, T. Margalef, and E. Luque, “Enhancing wildland fire prediction on cluster systems applying evolutionary optimization techniques,” Future Generation Computer Systems, vol. 21, no. 1, pp. 61–67, Nov. 2004, doi: 10.1016/j.future.2004.09.013.
  3.  G. Bianchini, M. Denham, A. Cortés, T. Margalef, and E. Luque, “Improving forest-fire prediction by applying a statistical approach,” Forest Ecology and Management, vol. 234, p. S210, Oct. 2006, doi: 10.1016/j.foreco.2006.08.237.
  4. Y. Liu, R. A. Kahn, A. Chaloulakou, and P. Koutrakis, “Analysis of the impact of the forest fires in August 2007 on air quality of Athens using multi-sensor aerosol remote sensing data, meteorology and surface observations,” Atmospheric Environment, vol. 43, no. 21, pp. 3310–3318, Apr. 2009, doi: 10.1016/j.atmosenv.2009.04.010.
  5. Monod, A. Collin, G. Parent, and P. Boulet, “Infrared radiative properties of vegetation involved in forest fires,” Fire Safety Journal, vol. 44, no. 1, pp. 88–95, May 2008, doi: 10.1016/j.firesaf.2008.03.009.
  6. H. B. Singh et al., “Pollution influences on atmospheric composition and chemistry at high northern latitudes: Boreal and California forest fire emissions,” Atmospheric Environment, vol. 44, no. 36, pp. 4553–4564, Aug. 2010, doi: 10.1016/j.atmosenv.2010.08.026.
  7. M. Denham, K. Wendt, G. Bianchini, A. Cortés, and T. Margalef, “Dynamic Data-Driven Genetic Algorithm for forest fire spread prediction,” Journal of Computational Science, vol. 3, no. 5, pp. 398–404, Jun. 2012, doi: 10.1016/j.jocs.2012.06.002.
  8. G. Sanjuan, C. Brun, T. Margalef, and A. Cortés, “Wind field uncertainty in forest fire propagation prediction,” Procedia Computer Science, vol. 29, pp. 1535–1545, Jan. 2014, doi: 10.1016/j.procs.2014.05.139.
  9. Carrillo, T. Artés, A. Cortés, and T. Margalef, “Error function impact in dynamic data-driven framework applied to forest fire spread prediction,” Procedia Computer Science, vol. 80, pp. 418–427, Jan. 2016, doi: 10.1016/j.procs.2016.05.342.
  10. H. Lin, X. Liu, X. Wang, and Y. Liu, “A fuzzy inference and big data analysis algorithm for the prediction of forest fire based on rechargeable wireless sensor networks,” Sustainable Computing Informatics and Systems, vol. 18, pp. 101–111, May 2017, doi: 10.1016/j.suscom.2017.05.004.
  11. V. Sevinc, O. Kucuk, and M. Goltas, “A Bayesian network model for prediction and analysis of possible forest fire causes,” Forest Ecology and Management, vol. 457, p. 117723, Nov. 2019, doi: 10.1016/j.foreco.2019.117723.
  12. L. Si et al., “Study on forest fire danger prediction in plateau mountainous forest area,” Natural Hazards Research, vol. 2, no. 1, pp. 25–32, Jan. 2022, doi: 10.1016/j.nhres.2022.01.002.
  13. K. M. Freitas, R. S. Juvanhol, C. J. G. Pinheiro, and A. A. De Moura Meneses, “Prediction of forest fire susceptibility using machine learning tools in the Triunfo do Xingu Environmental Protection Area, Amazon, Brazil,” Journal of South American Earth Sciences, vol. 153, p. 105366, Jan. 2025, doi: 10.1016/j.jsames.2025.105366.
  14. C. Maffei, R. Lindenbergh, and M. Menenti, “Probabilistic approaches for the prediction of forest fire danger using optical and thermal satellite data,” in Elsevier eBooks, 2025, pp. 285–327. doi: 10.1016/b978-0-443-40296-8.00010-0.
  15. Alexandridis, D. Vakalis, C. I. Siettos, and G. V. Bafas, “A cellular automata model for forest fire spread prediction: The case of the wildfire that swept through Spetses Island in 1990,” Applied Mathematics and Computation, vol. 204, no. 1, pp. 191–201, Jun. 2008, doi: 10.1016/j.amc.2008.06.046.
Download PDF

This article is part of Volume 2, Issue 3 (March 2026)