COMPARATIVE RESULTS OF USING DEEP LEARNING MODELS WITH ENSEMBLE METHODS FOR WILDFIRE ASSESSMENT
DOI:
https://doi.org/10.37943/23EUQO3546Keywords:
wildfire assessment, YOLO, SSD, deep learning, ensemble methods, false alarm reduction, machine learningAbstract
Wildfires are an increasingly transnational global environmental and socio-economic problem. In fact, their frequency, intensity and destructive power has grown drastically over the past decades largely driven by climate change, unsustainable land management and other human activities. Climate change has shown through rising global temperatures, longer and hotter droughts, and greater wind speeds, has fostered the perfect environment for fires to spark and sweep through the land. Kazakhstan is one of the Central Asian countries where the effects of climate change are making such disasters not only more frequent, but much worse. This vulnerability was tragically illustrated by the recent large-scale forest fire that swept across the Abay region, resulting in considerable ecological harm and exposing serious deficiencies in early detection and response capabilities. These advancements all point to an increasing, pressing need for more innovative, rapid, and dependable ways to evaluate, anticipate, and reduce wildfire risks. To address these issues, in this study we present a state-of-the-art ensemble-based deep learning approach to improve the accuracy and efficiency of wildfire detection. Our approach marries the strengths of two other state-of-the-art object detection algorithms, YOLO (You Only Look Once) and SSD (Single Shot Multibox Detector).By training this ensemble based model on a massive and varied dataset of landscape images and real-life wildfires, we’re able to get a general detection accuracy of 89%.This combined performance marks a striking advancement from when each model is used individually, especially in reducing false positives and providing more uniform and trustworthy results. Through fusing these models together and keeping them in one single unified framework there’s a notable boost in state-of-the-art detection accuracy as well as real-time image processing speed capabilities. This is a requirement for any real-time application. These results emphasize the value of using ensemble deep learning methods to enhance wildfire management and response strategies, eventually leading to more effective and proactive efforts.
References
TASS. (2024). Los Angeles wildfires cause economic losses exceeding $250 billion. Retrieved from https://tass.ru/proisshestviya/22870913
NIA. (2024). Massive wildfires in Canada and the Amazon intensify climate-related disasters. Retrieved from https://nia.eco/2024/08/14/88454/
KT.kz. (2024). Kazakhstan experiences 600 to 800 wildfires annually, highlighting urgent need for improved detection methods. Retrieved from https://www.kt.kz/rus/ecology/ot_600_do_800_lesnyh_pozharov_proishodit_ezhegodno_v_1377961025.html
Chaoxia C., Shang W. and Zhang F., “Information-Guided Flame Detection Based on Faster R-CNN” in IEEE Access, vol. 8, pp. 58923-58932, 2020, doi: 10.1109/ACCESS.2020.2982994.
Wenyang Y., Yesen W., Steven C. (2024). Deep Learning Method forReal-Time Fire Detection System for Urban Fire Monitoring and Control. International Journal of Computational Intelligence Systems. 17. 10.1007/s44196-024-00592-8.
Kyuchukova D., Hristov G., Raychev J., Zahariyev P. (2019). Early Forest Fire Detection Using Drones and Artificial Intelligence. 1060-1065. 10.23919/MIPRO.2019.8756696.
Xu R., Lin H., Lu K., Cao L., Liu Y. (2021). A Forest Fire Detection System Based on Ensemble Learning. Forests. 12. 217. 10.3390/f12020217.
Li Y., Shen Z., Li J., Xu Z. (2022). A Deep Learning Method based on SRN-YOLO for Forest Fire Detection. 1-6. 10.1109/ISAS55863.2022.9757300.
Jia, Y., Chen, W., Yang, M., Wang, L., Liu, D., & Zhang, Q. (2021). Video smoke detection with domain knowledge and transfer learning from deep convolutional neural networks. Optik, 240, 166947. doi:10.1016/j.ijleo.2021.166947.
Zhou, Yu-Cheng & Hu, Zhen-Zhong & Yan, Ke-Xiao & Lin, Jia-Rui. (2021). Deep Learning-Based Instance Segmentation for Indoor Fire Load Recognition. IEEE Access. 9. 148771-148782. 10.1109/ACCESS.2021.3124831.
Lin, Gaohua; Zhang, Yongming; Xu, Gao; Zhang, Qixing . (2019). Smoke Detection on Video Sequences Using 3D Convolutional Neural Networks. Fire Technology, (), –. doi:10.1007/s10694-019-00832-w
Vicente, J., Guillemant, P. (2002). An image processing technique for automatically detecting forest fire. International Journal of Thermal Sciences, 41(12), 1113–1120. doi:10.1016/s1290-0729(02)01397-2
Yaowen Hu, Jialei Zhan, Guoxiong Zhou, Aibin Chen, Weiwei Cai, Kun Guo, Yahui Hu, Liujun Li, Fast forest fire smoke detection using MVMNet, Knowledge-Based Systems, Volume 241, 2022, ISSN 0950-7051, https://doi.org/10.1016/j.knosys.2022.108219.
Mohnish S., Akshay P., Gokul S., Sarath A., Pavithra P., Ezhilarasi S. (2022). Deep Learning based Forest Fire Detection and Alert System. 1-5. 10.1109/IC3IOT53935.2022.9767911.
Deng Li, Tan Yang, Zhou Jin, Wu Si-qi, Liu Quan-yi, YOLOv8-EMSC: A lightweight fire recognition algorithm for large spaces, Journal of Safety Science and Resilience, Volume 5, Issue 4, 2024, Pages 422-431, ISSN 2666-4496, https://doi.org/10.1016/j.jnlssr.2024.06.003.
Abdusalomov, A. B., Islam, B. M. S., Nasimov, R., Mukhiddinov, M., & Whangbo, T. K. (2023). An Improved Forest Fire Detection Method Based on the Detectron2 Model and a Deep Learning Approach. Sensors, 23(3), 1512. https://doi.org/10.3390/s23031512.
Mesfer Al Duhayyim, Majdy M. Eltahir, Ola Abdelgney Omer Ali, Amani Abdulrahman Albraikan, Fahd N. Al-Wesabi, Anwer Mustafa Hilal, Manar Ahmed Hamza, Mohammed Rizwanullah, Fusion-Based Deep Learning Model for Automated Forest Fire Detection, Computers, Materials and Continua, Volume 77, Issue 1, 2023, Pages 1355-1371, ISSN 1546-2218, https://doi.org/10.32604/cmc.2023.024198.
Zhang, Jianmei & Zhu, Hongqing & Wang, Pengyu & Ling, Xiaofeng. (2021). ATT Squeeze U-Net: A Lightweight Network for Forest Fire Detection and Recognition. IEEE Access. PP. 1-1. 10.1109/ACCESS.2021.3050628.
Jadouli, Ayoub & El Amrani, Chaker. (2024). Enhancing Wildfire Forecasting Through Multisource Spatio-Temporal Data, Deep Learning, Ensemble Models and Transfer Learning. 10.48550/arXiv.2407.15878.
H. Cao, J. Xu, Y. Zheng, and Z. Zhou, “Forest Fire Detection Method Based on Improved YOLOv5,” Fire Ecology, 2024. doi: 10.1007/s44267-024-00053-y.
H. Zhou, X. Li, et al., “YOLOv8n-SMMP: A Lightweight Deep Learning Model for Real-Time Forest Fire Smoke Detection,” Fire, vol. 8, no. 5, p. 183, 2025. doi: 10.3390/fire8050183.
W. Ming, Y. Peng, J. Liangcun, Y. Dayu, T. Tianyu, L. Jian. (2024). An open flame and smoke detection dataset for deep learning in remote sensing based fire detection. Geo-spatial Information Science. 1-16. 10.1080/10095020.2024.2347922.
Y. Bahhar, A. Abdellaoui, and M. Benjelloun, “Wildfire and Smoke Detection Using Staged YOLO Model and Ensemble CNN,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 11, 2023. doi: 10.14569/IJACSA.2023.0141122.
Deng, L., Yang, T., Jin, Z., Wu, S., Liu, Q. (2024). YOLOv8-EMSC: A lightweight fire recognition algorithm for large spaces. Journal of Safety Science and Resilience, 5(4), 422–431. https://doi.org/10.1016/j.jnlssr.2024.06.003
Liau, J., Lin, C.-H., & Kuo, S.-Y. (2018). Fire SSD: A lightweight convolutional neural network for real-time fire detection. In 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (pp. 1982–1987). IEEE. https://doi.org/10.1109/SMC.2018.00336
Suo, X., Xu, Y., Yang, J., & Zhang, M. (2023). E³-UAV: Energy-efficient ensemble deep learning for real-time wildfire detection on unmanned aerial vehicles. Sensors, 23(5), 2761. https://doi.org/10.3390/s23052761
Xu, R., Lin, H., Lu, K., Cao, L., Liu, Y. (2021). A Forest Fire Detection System Based on Ensemble Learning. Forests, 12(2), 217. https://doi.org/10.3390/f12020217
Nguyen, Q. T., Kim, H., Lee, J., & Han, Y. (2023). Challenges in Deep Learning-Based Fire Detection: A Comprehensive Review. Fire Technology, 59, 1123–1152. https://doi.org/10.1007/s10694-022-01254-5
Peruzzi, M., Bucci, A., Manzoni, G., Zoppi, M., & Caiti, A. (2023). A LoRa-based wildfire surveillance unit: System design and deployment results. Sensors, 23(4), 2021. https://doi.org/10.3390/s23042021
Vázquez, D., García, A., Ramírez, J., & Molina, J. (2025). Generalization of wildfire detection systems using transfer learning and multispectral data. Applied Sciences, 15(1), 89. https://doi.org/10.3390/app15010089
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Articles are open access under the Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Authors who publish a manuscript in this journal agree to the following terms:
- The authors reserve the right to authorship of their work and transfer to the journal the right of first publication under the terms of the Creative Commons Attribution License, which allows others to freely distribute the published work with a mandatory link to the the original work and the first publication of the work in this journal.
- Authors have the right to conclude independent additional agreements that relate to the non-exclusive distribution of the work in the form in which it was published by this journal (for example, to post the work in the electronic repository of the institution or publish as part of a monograph), providing the link to the first publication of the work in this journal.
- Other terms stated in the Copyright Agreement.