Forest Fire Detection Leveraging Hybrid Convolutional-Recurrent Models
Abstract
Forest fires pose serious environmental and economic risks across tropical, temperate, and boreal regions. Traditional detection methods are often limited in accuracy and adaptability, motivating the use of deep learning for automated solutions. While Convolutional Neural Networks (CNNs) have shown promise, fewer studies have systematically examined hybrid models combining CNN feature extraction with recurrent layers such as Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU). This study compares CNN-MLP, CNN-RNN, CNN-LSTM, and CNN-GRU architectures on a public forest fire dataset, evaluating classification performance and computational efficiency. Results show that CNN-GRU offers the best trade-off, closely matching CNN-MLP in accuracy while requiring fewer resources. CNN-LSTM provides stable performance, whereas CNN-RNN underperforms and needs refinement. Computational analysis further indicates that CNN-MLP is the the most resource intensive models with over 1 millions parameter. These findings highlight CNN-GRU as a strong candidate for real-time forest fire detection, balancing accuracy and efficiency, and suggest future exploration of adaptive thresholds and transformer-based approaches.
References
V. Ferna ́ndez-Garc ́ıa, E. Marcos, J. M. Ferna ́ndez-Guisuraga, A. Taboada, S. Suarez-Seoane, and L. Calvo, “Impact of burn severity on soil properties in a Pinus pinaster ecosystem
immediately after fire,” Int. J. Wildland Fire, v
A. Bento-Gonc ̧alves, A. Vieira, X. U ́ beda, and D. Martin, “Fire and soils: key concepts and recent advances,” Geoderma, vol. 191, pp. 3–13, Jan. 2012.
A. A. Agbeshie, S. Abugre, T. Atta-Darkwa, et al., “A review of the effects of forest fire on soil properties,” J. For. Res., vol. 33, pp. 1419–1441, 2022. [Online]. Available: https://doi.org/10.1007/s11676-022-01475-4
M. D. Flannigan, B. J. Stocks, and B. M. Wotton, “Climate change and forest fires,” Sci. Total Environ., vol. 262, no. 3, pp. 221–229, 2000. [Online]. Available: https://doi.org/10.1016/S0048-9697(00)00524-6
A. Mohapatra and T. Trinh, “Early wildfire detection technologies in practice—a review,” Sustainability, vol. 14, no. 19, p. 12270, 2022. [Online]. Available: https://doi.org/10.3390/su141912270
V. Cuomo, R. Lasaponara, and V. Tramutoli, “Evaluation of a new satellite-based method for forest fire detection,” Int. J. Remote Sens., vol. 22, no. 9, pp. 1799–1826, 2001. [Online]. Available: https://doi.org/10.1080/01431160120827
M. Hefeeda and M. Bagheri, “Forest fire modeling and early detection using wireless sensor networks,” Ad Hoc Sensor Wireless Netw., vol. 7, no. 3–4, pp. 169–224, 2009.
M. Bahrepour, N. Meratnia, and P. Havinga, “Automatic fire detection: A survey from wireless sensor network perspective,” Centre Telematics Inf. Technol., Univ. Twente, Enschede, The Netherlands, Tech. Rep. TR-CTIT-08-73, 2008. ISSN 1381- 3625.
Y. E. Asian, I. Korpeoglu, and O. Ulusoy, “A framework for use of wireless sensor networks in forest fire detection and monitoring,” Comput., Environ. Urban Syst., vol. 36, no. 6, pp. 614–625, 2012. [Online]. Available: https://doi.org/10.1016/j.compenvurbsys.2012.03.003
K. Bouabdellah, H. Noureddine, and S. Larbi, “Using wireless sensor networks for reliable forest fires detection,” Procedia Comput. Sci., vol. 19, pp. 794–801, 2013. [Online]. Available: https://doi.org/10.1016/j.procs.2013.06.110
Z. Jiao, et al., “A deep learning based forest fire detection approach using UAV and YOLOv3,” in Proc. 1st Int. Conf. Ind. Artif. Intell. (IAI), Shenyang, China, 2019, pp. 1–5, doi: 10.1109/ICIAI.2019.8850815.
V. E. Sathishkumar, J. Cho, M. Subramanian, et al., “Forest fire and smoke detection using deep learning-based learning without forgetting,” Fire Ecol., vol. 19, p. 9, 2023. [Online]. Available: https://doi.org/10.1186/s42408-022-00165-0
S. T. Seydi, V. Saeidi, B. Kalantar, N. Ueda, and A. A. Halin, “Fire-Net: A deep learning framework for active forest fire detection,” J. Sensors, vol. 2022, no. 1, p. 8044390, 2022. [Online]. Available: https://doi.org/10.1155/2022/8044390
J. San-Miguel-Ayanz, J. M. Moreno, and A. Camia, “Analysis of large fires in European Mediterranean landscapes: lessons learned and perspectives,” For. Ecol. Manage., vol. 294, no. 1–3, pp. 11–22, 2005. [Online]. Available: https://doi.org/10.1016/j.foreco.2004.10.050
Y. Cui, H. Zhang, Y. Wang, and X. Li, “An intelligent smoke detection system for forest fire prevention using multi-sensor data fusion,” Sensors, vol. 24, no. 2, p. 567, 2024. [Online]. Available: https://doi.org/10.3390/s24020567
A. Gaur, B. Singh, and P. Kumar, “Wireless sensor network: An approach for early forest fire detection,” Int. J. Adv. Res. Comput. Sci., vol. 10, no. 5, pp. 57–61, 2019. [Online]. Available: https://doi.org/10.26483/ijarcs.v10i5.6473
L. Yao, Z. Wang, and X. Chen, “A review of smoke detection technologies in wildland fire monitoring,” Fire, vol. 6, no. 1, p. 25, 2023. [Online]. Available: https://doi.org/10.3390/fire6010025
B. J. Meacham, “Fire detection technologies and applications: A review,” Fire Technol., vol. 29, no. 1, pp. 5–29, 1993. [Online]. Available: https://doi.org/10.1007/BF01040264
Y. Long, X. Wei, and H. Wang, “Flame detection based on image processing and support vector machines,” Fire Saf. J., vol. 62, pp. 186–195, 2013. [Online]. Available: https://doi.org/10.1016/j.firesaf.2013.09.009
C. C. Tsai and C. H. Huang, “A novel flame detection technique for video-based surveillance systems,” Fire Saf. J., vol. 41, no. 6, pp. 512–522, 2006. [Online]. Available: https://doi.org/10.1016/j.firesaf.2006.05.001
S. Bordbar, M. Ghasemi, and A. H. Sadeghi, “Outdoor flame detection in forest environments using infrared and ultraviolet sensors,” Sensors, vol. 22, no. 14, p. 5280, 2022. [Online]. Available: https://doi.org/10.3390/s22145280
Y. Pauchard, J. C. Borel, and J. L. Mermier, “Fire detection in natural environments using UV sensors,” Fire Saf. J., vol. 34, no. 4, pp. 307–318, 2000. [Online]. Available: https://doi.org/10.1016/S0379-7112(99)00048-2
X. Li, J. Zhao, and K. Wang, “Performance of aspirating smoke detectors in different environmental conditions,” Fire Saf. J., vol. 120, p. 103087, 2021. [Online]. Available: https://doi.org/10.1016/j.firesaf.2021.103087
H. Lee, D. Kim, and J. Park, “Application of aspirating smoke detection system in large open spaces,” J. Fire Prot. Eng., vol. 32, no. 4, pp. 289–302, 2022. [Online]. Available: https://doi.org/10.1177/10423915221083742
H. Visak and R. Sharma, “Review on aspirating smoke detection systems for fire safety,” Int. J. Eng. Adv. Tech- nol., vol. 10, no. 6, pp. 142–147, 2021. [Online]. Available: https://doi.org/10.35940/ijeat.F3250.089621
X. Deng, Y. Sun, and M. Zhou, “Challenges and perspectives of fire detection technologies in wildland environments: A comprehensive review,” Fire Technol., vol. 61, pp. 1123–1156, 2025. [Online]. Available: https://doi.org/10.1007/s10694-025-01321-9
S. B. Kukuk and Z. H. Kilimci, “Comprehensive analysis of forest fire detection using deep learning models and con- ventional machine learning algorithms,” Int. J. Comput. Exp. Sci. Eng., vol. 7, no. 2, pp. 84–94, 2021. [Online]. Available: https://doi.org/10.22399/ijcesen.950045
A. Secilmis, N. Aksu, F. A. Dael, I. Shayea, and A. A. El-Saleh, “Machine learning-based fire detection: A comprehensive review and evaluation of classification models,”JOIV: Int. J. Informatics Vis., vol. 7, no. 3–2, pp. 1982–1988, 2023.
A. Khan, B. Hassan, S. Khan, R. Ahmed, and A. Abuassba, “DeepFire: A novel dataset and deep transfer learning benchmark for forest fire detection,” Mobile Inf. Syst., vol. 2022, no. 1, p. 5358359, 2022. [Online]. Available: https://doi.org/10.1155/2022/5358359
A. B. Abdusalomov, B. M. S. Islam, R. Nasimov, M. Mukhiddinov, and T. K. Whangbo, “An improved forest fire detection method based on the detectron2 model and a deep learning approach,” Sensors, vol. 23, no. 3, p. 1512, 2023. [Online]. Available: https://doi.org/10.3390/s23031512
D. Shen, X. Chen, M. Nguyen, and W. Q. Yan, “Flame detection using deep learning,” in Proc. 4th Int. Conf. Control, Autom. Robot. (ICCAR), pp. 416–420, 2018. [Online]. Available: https://doi.org/10.1109/ICCAR.2018.8384711
J. Alves, C. Soares, J. M. Torres, P. Sobral, and R. S. Moreira, “Automatic forest fire detection based on a machine learning and image analysis pipeline,” in A ́ . Rocha, H. Adeli, L. Reis, and S. Costanzo (eds.), New Knowledge in Information Systems and Technologies (WorldCIST’19), pp. 259–269. Springer, 2019. [Online]. Available: https://doi.org/10.1007/978-3-030-16184-2 24
A. Rafi, S. A. Tanim, T. Biswas, F. Mridha, M. Safran, S. Alfarhood, and D. Che, “Fire and non-fire forest dataset,” Mendeley Data, V2, 2025. [Online]. Available: https://doi.org/10.17632/5vb2kds993.2
Z. J. Wang, R. Turko, O. Shaikh, H. Park, N. Das, F. Hohman, M. Kahng, and D. H. Polo Chau, “CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization,” IEEE Transactions on Visualization and Computer Graphics, vol. 27, no. 2, pp. 1396–1406, Feb. 2021. [Online]. Available: https://doi.org/10.1109/TVCG.2020.3030418
J. L. Elman, “Finding structure in time,” Cogn. Sci., vol. 14, no. 2, pp. 179–211, 1990. [Online]. Available: https://doi.org/10.1016/0364-0213(90)90002-E
S. Hochreiter and J. Schmidhuber,“Long short-term memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, 1997.
K. Cho, B. Van Merrie ̈nboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using RNN encoder-decoder for statistical machine translation,” arXiv preprint arXiv:1406.1078, 2014.
X. Ye,“calflops: a FLOPs and Params calculate tool for neural networks in PyTorch framework,” GitHub, 2023. [Online]. Available: https://github.com/MrYxJ/calculate-flops.pytorch
Z. Li and D. Hoiem, “Learning without forgetting,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 12, pp. 2935–2947, 2017.
