Document Type : Technical Paper

Authors

Department of Computer Engineering, Faculty of Engineering and Technology, University of Mazandaran, Babolsar, Iran.

10.22044/jadm.2025.15837.2699

Abstract

wildfires are among the most serious environmental and socio-economic threats worldwide, significantly impacting ecosystems and climate patterns. In recent years, deep learning-based methods, particularly Convolutional Neural Networks (CNNs), have played a crucial role in improving wildfire detection accuracy. This study presents an enhanced approach for identifying wildfire-affected areas using deep learning models. Specifically, three models—ResNet50, ResNet101, and EfficientNetB0—have been examined. To improve accuracy and reduce model complexity, the Flatten layer in all three architectures has been replaced with a Global Average Pooling (GAP) layer. This modification reduces the number of features and enhances the extraction of meaningful patterns from images. Additionally, a Dense layer with 128 neurons has been added after the GAP layer to enhance the learning and integration of the extracted features. To prevent overfitting, a Dropout layer with a rate of 0.5 has been incorporated. Finally, a Dense layer with 2 neurons serves as the output layer, responsible for the final classification. These optimizations have led to improved model accuracy and enhanced performance in wildfire detection. The dataset used consists of 42,850 satellite images, categorized into wildfire and nowildfire areas. Experimental results indicate that the ResNet101 model achieved the highest accuracy of 99.60%, while ResNet50 and EfficientNetB0 achieved accuracies of 99.35% and 99.10%, respectively. These results highlight the high potential of deep learning-based methods in improving wildfire detection accuracy and their role in environmental crisis management.

Keywords

Main Subjects

[1] P. Jain, S. C. P. Coogan, S. G. Subramanian, M. Crowley, S. Taylor, and M. D. Flannigan, "A review of machine learning applications in wildfire science and management", Environmental Reviews, vol. 28, no. 4, pp. 478-505, 2020. [Online]. Available: https://doi.org/10.1139/er-2020-0019. [Accessed: Feb. 22, 2025].
 
[2] T. Schoennagel, J. K. Balch, H. Brenkert-Smith, P. E. Dennison, B. J. Harvey, M. A. Krawchuk, N. Mietkiewicz, P. Morgan, M. A. Moritz, R. Rasker, M. G. Turner, and C. Whitlock, "Adapt to more wildfire in western North American forests as climate changes", Proceedings of the National Academy of Sciences, vol. 114, no. 18, pp. 4582-4590, 2017. [Online]. Available: https://doi.org/10.1073/pnas.1617464114. [Accessed: Feb. 22, 2025].
 
[3] G. Shi, H. Yan, W. Zhang, J. Dodson, H. Heijnis, and M. Burrows, "Rapid warming has resulted in more wildfires in northeastern Australia", Science of The Total Environment, vol. 771, p. 144888, 2021. [Online]. Available: https://doi.org/10.1016/j.scitotenv.2020.144888.[Accessed: Feb. 22, 2025].
 
[4] J. San-Miguel-Ayanz, T. Durrant, R. Boca, P. Maianti, G. Libertà, T. A. Vivancos, D. J. F. Oom, A. Branco, D. D. De Rigo, D. Ferrari, H. Pfeiffer, R. Grecchi, D. Nuijten, T. Leray, "Forest Fires in Europe, Middle East and North Africa 2019", Publications Office of the European Union, Luxembourg, Rep. KJ-NA-30402-EN-N, 2020.
 
[5]  J. S. S. Júnior, J. Pãulo, J. Mendes, D. Alves, and L. M. Ribeiro, "Automatic Calibration of Forest Fire Weather Index For Independent Customizable Regions Based on Historical Records", in Proceedings of the 2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE),1-8, 2020, Laguna Hills, CA, USA. Available: IEEE Xplore, https://doi.org/10.1109/AIKE48582.2020.00011. [Accessed: Feb. 22, 2025].
 
[6]  J. S. S. Júnior, J. R. Paulo, J. Mendes, D. Alves, L. M. Ribeiro, and C. Viegas, "Automatic forest fire danger rating calibration: Exploring clustering techniques for regionally customizable fire danger classification", Expert Systems with Applications, vol. 193, p. 116380, 2022. [Online]. Available: https://doi.org/10.1016/j.eswa.2021.116380.[Accessed: Feb. 22, 2025].
 
[7]  G. R. van der Werf, J. T. Randerson, L. Giglio, T. T. van Leeuwen, Y. Chen, B. M. Rogers, M. Mu, M. J. E. van Marle, D. C. Morton, G. J. Collatz, R. J. Yokelson, and P. S. Kasibhatla, " Global fire emissions estimates during 1997–2016", Earth System Science Data, vol. 9, no. 2, pp. 697-720, 2017. [Online]. Available: https://essd.copernicus.org/articles/9/697/2017/.[Accessed: Feb. 22, 2025].
 
[8] ‎F. N. Robinne and F. Secretariat, "Impacts of disasters on forests, in particular forest fires," UNFFS, 2021.
 
[9] L. Vilà-Vilardell, W. S. Keeton, D. Thom, C. Gyeltshen, K. Tshering, and G. Gratzer, "Climate change effects on wildfire hazards in the wildland-urban-interface – Blue pine forests of Bhutan", Forest Ecology and Management, vol. 461, p. 117927, 2020. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0378112719319024. [Accessed: Feb. 22, 2025].
 
[10] Aaba, A. “Wildfire Prediction Dataset (Satellite Images).
 
[11] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning", Nature, vol. 521, pp. 436–444, 2015. [Online]. Available: https://doi.org/10.1038/nature14539. [Accessed: Feb. 22, 2025].
 
[12] ‎ S. Maggioros and N. Tsalkitzis, "Wildfire danger prediction optimization with transfer learning," arXiv, 2024, [online]. Available: https://arxiv.org/abs/2403.12871. [Accessed: Feb. 22, 2025].
 
[13]  R. Xu, H. Lin, K. Lu, L. Cao, and Y. Liu, "A forest fire detection system based on ensemble learning", Forests, vol. 12, no. 2, p. 217, 2021. [Online]. Available: https://doi.org/10.3390/f12020217. [Accessed: Feb. 22, 2025].
 
[14]  Z. Jiao, Y. Zhang, L. Mu, J. Xin, S. Jiao, H. Liu, and D. Liu, "A YOLOv3-based Learning Strategy for Real-time UAV-based Forest Fire Detection", in Proceedings of the 2020 Chinese Control and Decision Conference (CCDC), 4963-4967, 2020, Hefei, China. Available: IEEE Xplore, https://doi.org/10.1109/CCDC49329.2020.9163816. [Accessed: Feb. 22, 2025].
 
[15] M. Rahul, S. S. Karnekanti, S. Attili, and S. N. Nenavath, "Early Detection of Forest Fire using Deep Learning", in Proceedings of the 2020 IEEE REGION 10 CONFERENCE (TENCON), 1136-1140, 2020, Osaka, Japan. Available: IEEE Xplore, https://doi.org/10.1109/TENCON50793.2020.9293722. [Accessed: 22 Feb. 2025].
 
[16] A. Namburu, P. Selvaraj, S. Mohan, S. Ragavanantham, and E. Tag Eldin, "Forest Fire Identification in UAV Imagery Using X-MobileNet," Electronics, vol. 12, no. 3, art. no. 733, Feb. 2023.[Online].Available:  https://doi.org/10.3390/electronics12030733[Accessed: Feb. 22, 2025].
 
[17] S. A. Sifat, S. A. Shoukat, et al., "PyroVision: A deep learning based model for wildfire detection in satellite imagery," in Proc. 6th Int. Conf. Electr. Eng. Inf. Commun. Technol. (ICEEICT), IEEE, 2024, pp. 705–710. [Online]. Available: https://doi.org/10.1109/ICEEICT62016.2024.10534576. [Accessed: Feb. 22, 2025].
 
[18] Z. Wu, C. Shen, and A. van den Hengel, "Wider or deeper: Revisiting the ResNet model for visual recognition", Pattern Recognition, vol. 90, pp. 119-133, 2019. [Online]. Available: https://doi.org/10.1016/j.patcog.2019.01.006.[Accessed: Feb. 22, 2025].
 
[19] F. Salimian Najafabadi and M. T. Sadeghi, "AgriNet: a New Classifying Convolutional Neural Network for Detecting Agricultural Products’ Diseases," Journal of Artificial Intelligence and Data Mining (JAIDM), vol. 10, no. 2, pp. 285–302, 2022. [Online]. Available: http://jad.shahroodut.ac.ir/article_2431_10ea85357f4b93525c9f43aa020d424a.pdf. [Accessed: Aug. 18, 2025].
 
[20] A. Narin, C. Kaya, and Z. Pamuk, "Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks", Pattern Analysis and Applications, vol. 24, no. 3, pp. 1207-1220, 2021. [Online]. Available: https://doi.org/10.1007/s10044-021-00984-y. [Accessed: Feb. 22, 2025].
 
[21] A. A. Farhat, M. M. Darwish, and T. M. El-Gindy, "Resnet50 and logistic Gaussian map-based zero-watermarking algorithm for medical color images", Neural Computing and Applications, vol. 36, no. 31, pp. 19707–19727, 2024. [Online]. Available: https://doi.org/10.1007/s00521-024-101215. [Accessed: Feb. 22, 2025].
 
[22] A. Manzoor, W. Ahmad, M. Ehatisham-ul-Haq, A. Hannan, M. A. Khan, M. U. Ashraf, A. M. Alghamdi, and A. S. Alfakeeh, "Inferring emotion tags from object images using convolutional neural network", Applied Sciences, vol. 10, no. 15, p. 5333, 2020. [Online]. Available: https://doi.org/10.3390/app10155333. [Accessed: Feb. 22, 2025].
 
[23] M. Tan and Q. V. Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks", in Proceedings of the 36th International Conference on Machine Learning (ICML 2019), 6105-6114, 2019, Long Beach, CA, USA. [Online].  Available: PMLR http://proceedings.mlr.press/v97/tan19a.html.[Accessed: 22 Feb. 2025].
 
[24]  A. Iqbal, M. A. Jaffar, and R. Jahangir, "Enhancing brain tumour multi-classification using Efficient-Net B0-based intelligent diagnosis for Internet of Medical Things (IoMT) applications", Information, vol. 15, no. 8, p. 489, 2024. [Online]. Available: https://doi.org/10.3390/info15080489. [Accessed: Feb. 22, 2025].
 
[25]  R. Sonavane, P. Ghonge, S. U. Patil, K. S. Sagale, and A. A. Maha, "Exploring ResNet101, InceptionV3, and Xception for Modi Script Character Classification", International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 17, pp. 117–124, 2024. [Online]. Available: https://ijisae.org/index.php/IJISAE/article/view/4841. [Accessed: Feb. 22, 2025].
 
[26] A. Khan, M. A. Khan, M. Y. Javed, M. Alhaisoni, U. Tariq, S. Kadry, J.-I. Choi, and Y. Nam, "Human Gait Recognition Using Deep Learning and Improved Ant Colony Optimization", Computers, Materials & Continua, vol. 70, no. 2, pp. 2113–2130, 2022. [Online]. Available: https://doi.org/10.32604/cmc.2022.018270. [Accessed: Feb. 22, 2025].