Research Article
BibTex RIS Cite

Orman Yangınlarının Sınıflandırılması için Derin Sinir Ağlarının Performans Değerlendirmesi

Year 2025, Volume: 10 Issue: 2, 31 - 45, 29.10.2025
https://doi.org/10.57120/yalvac.1799284

Abstract

Orman yangınları, geniş ormanlık alanları yok etmekle kalmayıp biyolojik çeşitliliği tehdit eden, hava kalitesini bozan, tarım arazilerine zarar veren ve iklim değişikliğini hızlandıran yıkıcı doğal afetlerdir. Küresel sıcaklıkların yükselmesi, uzun süreli kuraklıklar ve insan kaynaklı faktörler nedeniyle, orman yangınlarının sıklığı ve şiddeti her geçen yıl artmaktadır. Sonuç olarak, orman yangınlarının erken tespiti ve hızlı sınıflandırılması, can ve mal kaybını önlemek ve afet müdahale süreçlerinin etkin bir şekilde yönetilmesini sağlamak için kritik öneme sahiptir. Bu çalışma, orman yangınlarının erken tespiti ve sınıflandırılması için derin öğrenme tabanlı bir yaklaşım sunmayı amaçlamaktadır. Bu bağlamda, son yıllarda görüntü sınıflandırma görevlerinde olağanüstü başarı gösteren dört gelişmiş evrişimli sinir ağı (CNN) mimarisi (Xception, InceptionV3, DenseNet121 ve EfficientNetV2), orman yangını görüntülerinin sınıflandırılması için karşılaştırmalı olarak değerlendirilmiştir. Eğitim ve test prosedürleri, yangın ve yangın olmayan sınıflarından oluşan Orman Yangını Görüntüleri veri seti kullanılarak gerçekleştirilmiştir. Deney sonuçları, tüm modellerin orman yangını sınıflandırmasında iyi performans gösterdiğini ortaya koymuştur; ancak Xception modeli, diğerlerinden daha yüksek doğruluk sergileyerek üstün performans göstermiştir. Bu sonuçlar, derin öğrenme mimarilerinin orman yangınlarının hızlı ve doğru sınıflandırılması için etkili araçlar olduğunu vurgulamakta ve böylece orman yangını izleme ve yönetim stratejilerine önemli katkılar sağlamaktadır.

References

  • [1] D. Bowman et al., “Fire in the Earth System,” Science, vol. 324, pp. 481–484, May 2009, doi: 10.1126/science.1163886.
  • [2] B. Calda, N. An, M. T. Turp, and L. Kurnaz, “İklim Değişikliğinin Akdeniz Havzasındaki Orman Yangınlarına Etkisi,” International Journal of Advances in Engineering and Pure Sciences, vol. 32, no. 1, pp. 15–32, 2020, doi: 10.7240/jeps.571001.
  • [3] CTIF, “World Fire Statistics | CTIF - International Association of Fire Services for Safer Citizens through Skilled Firefighters.” Accessed: Aug. 14, 2025. [Online]. Available: https://www.ctif.org/world-fire-statistics
  • [4] R. N. Vasconcelos et al., “Fire Detection with Deep Learning: A Comprehensive Review,” Land (Basel), vol. 13, no. 10, 2024, doi: 10.3390/land13101696.
  • [5] A. Saleh, M. A. Zulkifley, H. H. Harun, F. Gaudreault, I. Davison, and M. Spraggon, “Forest fire surveillance systems: A review of deep learning methods,” Heliyon, vol. 10, no. 1, p. e23127, 2024, doi: https://doi.org/10.1016/j.heliyon.2023.e23127.
  • [6] NASA VIIRS Land Team, “NASA VIIRS Active Fire Product,” 2025. [Online]. Available: https://viirsland.gsfc.nasa.gov/Products/NASA/FireESDR.html
  • [7] K. Govil, M. L. Welch, J. T. Ball, and C. R. Pennypacker, “Preliminary Results from a Wildfire Detection System Using Deep Learning on Remote Camera Images,” Remote Sens (Basel), vol. 12, no. 1, 2020, doi: 10.3390/rs12010166.
  • [8] M. Mukhiddinov, A. B. Abdusalomov, and J. Cho, “A Wildfire Smoke Detection System Using Unmanned Aerial Vehicle Images Based on the Optimized YOLOv5,” Sensors, vol. 22, no. 23, 2022, doi: 10.3390/s22239384.
  • [9] J. Feng, D. Zhu, and  L., “A Novel Method for Forest Fire Detection Based on Convolutional Neural Network,” 2018. doi: 10.18178/wcse.2018.06.047.
  • [10] S. B. KUKUK and Z. H. Kilimci, “Comprehensive Analysis of Forest Fire Detection Using Deep Learning Models and Conventional Machine Learning Algorithms,” 2021. doi: 10.22399/ijcesen.950045.
  • [11] S. T. Seydi, V. Saeidi, B. Kalantar, N. Ueda, and A. A. Halin, “Fire-Net: A Deep Learning Framework for Active Forest Fire Detection,” 2022. doi: 10.1155/2022/8044390.
  • [12] Y. Xu, J. Li, L. Zhang, H. Liu, and F. Zhang, “CNTCB-YOLOv7: An Effective Forest Fire Detection Model Based on ConvNeXtV2 and CBAM,” 2024. doi: 10.3390/fire7020054.
  • [13] Y. Wang, L. M. Dang, and J. Ren, “Forest Fire Image Recognition Based on Convolutional Neural Network,” 2019. doi: 10.1177/1748302619887689.
  • [14] K. YÜKSEL, “Yanan Orman Alani Tespi̇ti̇nde Farkli Uzaktan Algilama İndi̇sleri̇ni̇n Değerlendi̇ri̇lmesi̇: 2022 Yili Mersi̇n (Gülnar) Orman Yangini Örneği̇,” 2022. doi: 10.57165/artgrid.1179074.
  • [15] P. L. Kumari, Z. Abid, A. Abid, and G. D. Saxena, “Robust Forest Fire Detection Using Deep Convolutional Neural Networks,” vol. 01, no. 01, pp. 49–57, 2024, doi: 10.58599/ijsmcse.2024.1111.
  • [16] B. Aksoy, K. Korucu, Ö. Çalışkan, Ş. Osmanbey, and H. D. Halis, “İnsansız Hava Aracı ile Görüntü İşleme ve Yapay Zekâ Teknikleri Kullanılarak Yangın Tespiti: Örnek Bir Uygulama,” Duzce University Journal of Science and Technology, vol. 9, no. 6, pp. 112–122, 2021, doi: 10.29130/dubited.1016195.
  • [17] Prasad Mohnish Sai, “Forest Fire Images,” 2022, Kaggle. [Online]. Available: https://www.kaggle.com/datasets/mohnishsaiprasad/forest-fire-images
  • [18] D. H. Hubel and T. N. Wiesel, “Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex,” J Physiol, vol. 160, no. 1, pp. 106–154, Jan. 1962, doi: https://doi.org/10.1113/jphysiol.1962.sp006837.
  • [19] D. H. Hubel and T. N. Wiesel, “Receptive fields of single neurones in the cat’s striate cortex,” J Physiol, vol. 148, no. 3, pp. 574–591, Oct. 1959, doi: https://doi.org/10.1113/jphysiol.1959.sp006308.
  • [20] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015, doi: 10.1038/nature14539.
  • [21] W. Rawat and Z. Wang, “Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review,” Neural Comput, vol. 29, pp. 2352–2449, Sep. 2017, doi: 10.1162/NECO_a_00990.
  • [22] A. Biswas, S. K. Ghosh, and A. Ghosh, “Early Fire Detection and Alert System using Modified Inception-v3 under Deep Learning Framework,” Procedia Comput Sci, vol. 218, pp. 2243–2252, 2023, doi: https://doi.org/10.1016/j.procs.2023.01.200.
  • [23] H. C. Reis and V. Turk, “Detection of forest fire using deep convolutional neural networks with transfer learning approach,” Appl Soft Comput, vol. 143, p. 110362, 2023, doi: https://doi.org/10.1016/j.asoc.2023.110362.
  • [24] V. E. Sathishkumar, J. Cho, M. Subramanian, and O. S. Naren, “Forest fire and smoke detection using deep learning-based learning without forgetting,” Fire Ecology, vol. 19, no. 1, p. 9, 2023, doi: 10.1186/s42408-022-00165-0.
  • [25] F. Chollet, “Xception: Deep Learning With Depthwise Separable Convolutions,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jul. 2017.
  • [26] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the Inception Architecture for Computer Vision,” 2015. [Online]. Available: https://arxiv.org/abs/1512.00567
  • [27] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely Connected Convolutional Networks,” in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2261–2269. doi: 10.1109/CVPR.2017.243.
  • [28] B. Wang, G. Huang, H. Li, X. Chen, L. Zhang, and X. Gao, “Hybrid CBAM-EfficientNetV2 Fire Image Recognition Method with Label Smoothing in Detecting Tiny Targets,” Machine Intelligence Research, vol. 21, no. 6, pp. 1145–1161, 2024, doi: 10.1007/s11633-023-1445-5.

Performance Evaluation of Deep Neural Networks for Forest Fire Classification

Year 2025, Volume: 10 Issue: 2, 31 - 45, 29.10.2025
https://doi.org/10.57120/yalvac.1799284

Abstract

Forest fires are destructive natural disasters that not only destroy vast forested areas but also threaten biodiversity, degrade air quality, damage agricultural land, and accelerate climate change. Due to rising global temperatures, prolonged droughts, and human-induced factors, the frequency and intensity of forest fires are increasing year by year. Consequently, the early detection and rapid classification of forest fires are critical for preventing loss of life and property and ensuring the effective management of disaster response processes. This study aims to present a deep learning-based approach for the early detection and classification of forest fires. In this context, four advanced convolutional neural network (CNN) architectures (Xception, InceptionV3, DenseNet121, and EfficientNetV2), which have shown outstanding success in image classification tasks in recent years, were comparatively evaluated for the classification of forest fire images. Training and testing procedures were performed using the Forest Fire Images dataset, consisting of fire and non-fire classes. The experimental results revealed that all models performed well in forest fire classification; however, the Xception model demonstrated superior performance, exhibiting higher accuracy than the others. These results emphasize that deep learning architectures are effective tools for the rapid and accurate classification of forest fires, thereby making significant contributions to forest fire monitoring and management strategies.

References

  • [1] D. Bowman et al., “Fire in the Earth System,” Science, vol. 324, pp. 481–484, May 2009, doi: 10.1126/science.1163886.
  • [2] B. Calda, N. An, M. T. Turp, and L. Kurnaz, “İklim Değişikliğinin Akdeniz Havzasındaki Orman Yangınlarına Etkisi,” International Journal of Advances in Engineering and Pure Sciences, vol. 32, no. 1, pp. 15–32, 2020, doi: 10.7240/jeps.571001.
  • [3] CTIF, “World Fire Statistics | CTIF - International Association of Fire Services for Safer Citizens through Skilled Firefighters.” Accessed: Aug. 14, 2025. [Online]. Available: https://www.ctif.org/world-fire-statistics
  • [4] R. N. Vasconcelos et al., “Fire Detection with Deep Learning: A Comprehensive Review,” Land (Basel), vol. 13, no. 10, 2024, doi: 10.3390/land13101696.
  • [5] A. Saleh, M. A. Zulkifley, H. H. Harun, F. Gaudreault, I. Davison, and M. Spraggon, “Forest fire surveillance systems: A review of deep learning methods,” Heliyon, vol. 10, no. 1, p. e23127, 2024, doi: https://doi.org/10.1016/j.heliyon.2023.e23127.
  • [6] NASA VIIRS Land Team, “NASA VIIRS Active Fire Product,” 2025. [Online]. Available: https://viirsland.gsfc.nasa.gov/Products/NASA/FireESDR.html
  • [7] K. Govil, M. L. Welch, J. T. Ball, and C. R. Pennypacker, “Preliminary Results from a Wildfire Detection System Using Deep Learning on Remote Camera Images,” Remote Sens (Basel), vol. 12, no. 1, 2020, doi: 10.3390/rs12010166.
  • [8] M. Mukhiddinov, A. B. Abdusalomov, and J. Cho, “A Wildfire Smoke Detection System Using Unmanned Aerial Vehicle Images Based on the Optimized YOLOv5,” Sensors, vol. 22, no. 23, 2022, doi: 10.3390/s22239384.
  • [9] J. Feng, D. Zhu, and  L., “A Novel Method for Forest Fire Detection Based on Convolutional Neural Network,” 2018. doi: 10.18178/wcse.2018.06.047.
  • [10] S. B. KUKUK and Z. H. Kilimci, “Comprehensive Analysis of Forest Fire Detection Using Deep Learning Models and Conventional Machine Learning Algorithms,” 2021. doi: 10.22399/ijcesen.950045.
  • [11] S. T. Seydi, V. Saeidi, B. Kalantar, N. Ueda, and A. A. Halin, “Fire-Net: A Deep Learning Framework for Active Forest Fire Detection,” 2022. doi: 10.1155/2022/8044390.
  • [12] Y. Xu, J. Li, L. Zhang, H. Liu, and F. Zhang, “CNTCB-YOLOv7: An Effective Forest Fire Detection Model Based on ConvNeXtV2 and CBAM,” 2024. doi: 10.3390/fire7020054.
  • [13] Y. Wang, L. M. Dang, and J. Ren, “Forest Fire Image Recognition Based on Convolutional Neural Network,” 2019. doi: 10.1177/1748302619887689.
  • [14] K. YÜKSEL, “Yanan Orman Alani Tespi̇ti̇nde Farkli Uzaktan Algilama İndi̇sleri̇ni̇n Değerlendi̇ri̇lmesi̇: 2022 Yili Mersi̇n (Gülnar) Orman Yangini Örneği̇,” 2022. doi: 10.57165/artgrid.1179074.
  • [15] P. L. Kumari, Z. Abid, A. Abid, and G. D. Saxena, “Robust Forest Fire Detection Using Deep Convolutional Neural Networks,” vol. 01, no. 01, pp. 49–57, 2024, doi: 10.58599/ijsmcse.2024.1111.
  • [16] B. Aksoy, K. Korucu, Ö. Çalışkan, Ş. Osmanbey, and H. D. Halis, “İnsansız Hava Aracı ile Görüntü İşleme ve Yapay Zekâ Teknikleri Kullanılarak Yangın Tespiti: Örnek Bir Uygulama,” Duzce University Journal of Science and Technology, vol. 9, no. 6, pp. 112–122, 2021, doi: 10.29130/dubited.1016195.
  • [17] Prasad Mohnish Sai, “Forest Fire Images,” 2022, Kaggle. [Online]. Available: https://www.kaggle.com/datasets/mohnishsaiprasad/forest-fire-images
  • [18] D. H. Hubel and T. N. Wiesel, “Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex,” J Physiol, vol. 160, no. 1, pp. 106–154, Jan. 1962, doi: https://doi.org/10.1113/jphysiol.1962.sp006837.
  • [19] D. H. Hubel and T. N. Wiesel, “Receptive fields of single neurones in the cat’s striate cortex,” J Physiol, vol. 148, no. 3, pp. 574–591, Oct. 1959, doi: https://doi.org/10.1113/jphysiol.1959.sp006308.
  • [20] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015, doi: 10.1038/nature14539.
  • [21] W. Rawat and Z. Wang, “Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review,” Neural Comput, vol. 29, pp. 2352–2449, Sep. 2017, doi: 10.1162/NECO_a_00990.
  • [22] A. Biswas, S. K. Ghosh, and A. Ghosh, “Early Fire Detection and Alert System using Modified Inception-v3 under Deep Learning Framework,” Procedia Comput Sci, vol. 218, pp. 2243–2252, 2023, doi: https://doi.org/10.1016/j.procs.2023.01.200.
  • [23] H. C. Reis and V. Turk, “Detection of forest fire using deep convolutional neural networks with transfer learning approach,” Appl Soft Comput, vol. 143, p. 110362, 2023, doi: https://doi.org/10.1016/j.asoc.2023.110362.
  • [24] V. E. Sathishkumar, J. Cho, M. Subramanian, and O. S. Naren, “Forest fire and smoke detection using deep learning-based learning without forgetting,” Fire Ecology, vol. 19, no. 1, p. 9, 2023, doi: 10.1186/s42408-022-00165-0.
  • [25] F. Chollet, “Xception: Deep Learning With Depthwise Separable Convolutions,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jul. 2017.
  • [26] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the Inception Architecture for Computer Vision,” 2015. [Online]. Available: https://arxiv.org/abs/1512.00567
  • [27] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely Connected Convolutional Networks,” in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2261–2269. doi: 10.1109/CVPR.2017.243.
  • [28] B. Wang, G. Huang, H. Li, X. Chen, L. Zhang, and X. Gao, “Hybrid CBAM-EfficientNetV2 Fire Image Recognition Method with Label Smoothing in Detecting Tiny Targets,” Machine Intelligence Research, vol. 21, no. 6, pp. 1145–1161, 2024, doi: 10.1007/s11633-023-1445-5.
There are 28 citations in total.

Details

Primary Language English
Subjects Machine Vision
Journal Section Articels
Authors

Oğuzhan Kilim 0000-0003-3365-7327

Şerafettin Atmaca 0000-0003-2407-1113

Tuncay Yiğit 0000-0001-7397-7224

Hamit Armağan 0000-0002-8948-1546

Early Pub Date October 29, 2025
Publication Date October 29, 2025
Submission Date October 8, 2025
Acceptance Date October 29, 2025
Published in Issue Year 2025 Volume: 10 Issue: 2

Cite

APA Kilim, O., Atmaca, Ş., Yiğit, T., Armağan, H. (2025). Performance Evaluation of Deep Neural Networks for Forest Fire Classification. Yalvaç Akademi Dergisi, 10(2), 31-45. https://doi.org/10.57120/yalvac.1799284