UAV-Based Forest Fire Early Warning and Intervention Simulation System with High-Accuracy Hybrid AI Model
Source abstract
Abstract
In this study, a hybrid deep learning model that combines the VGG16 and ResNet101V2 architectures is proposed for image-based fire detection. In addition, a balanced drone guidance algorithm is developed to efficiently assign tasks to available UAVs. In the fire detection phase, the hybrid model created by combining the VGG16 and ResNet101V2 architectures has been optimized with Global Average Pooling and layer merging techniques to increase classification success. The DeepFire dataset was used throughout the training process, achieving an extremely high accuracy rate of 99.72% and 100% precision. After fire detection, a task assignment algorithm was developed to assign existing drones to fire points at minimum cost and with balanced load distribution. This algorithm performs task assignments using the Hungarian (Kuhn–Munkres) method and cost optimization, and is adapted to direct approximately equal numbers of drones to each fire when the number of fires is less than the number of drones. The developed system was tested in a Python-based simulation environment and evaluated using performance metrics such as total intervention time, energy consumption, and task balance. The results demonstrate that the proposed hybrid model provides highly accurate fire detection and that the task assignment system creates balanced and efficient intervention scenarios.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fire Detection and Safety Systems · Fire effects on ecosystems · UAV Applications and Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Engineering, Istanbul Medeniyet University, İstanbul 34700, Turkey
Department of Software Engineering, Istanbul Gedik University, İstanbul 34876, Turkey
References (43)
Show source-provided references
1. Human–environmental drivers and impacts of the globally extreme 2017 Chilean fires
2. Intergovernmental Panel on Climate Change (IPCC) (2021). Climate Change 2021: The Physical Science Basis, Cambridge University Press. Available online: https://www.ipcc.ch/report/ar6/wg1/.
3. CT Fire: A CNN Transformer for wildfire classification on ground and aerial images10.1080/01431161.2023.2283904 ↗
4. Diaconu, B.M. (2023). Recent advances and emerging directions in fire detection systems based on machine learning algorithms. Fire, 6.10.3390/fire6110441 ↗
5. DeepFire: A Novel Dataset and Deep Transfer Learning Benchmark for Forest Fire Detection
6. An efficient fire detection system based on deep neural network for real time applications10.1007/s11760-024-03311-0 ↗
7. Alkhammash, E.H. (2025). Multi-Classification Using YOLOv11 and Hybrid YOLO11n-MobileNet Models: A Fire Classes Case Study. Fire, 8.10.3390/fire8010017 ↗
8. Imagenet classification with deep convolutional neural networks
9. Deep convolutional neural networks for image classification: A comprehensive review10.1162/neco_a_00990 ↗
10. Albawi, S., Mohammed, T.A., and Al-Zawi, S. (2017). Understanding of a convolutional neural network. 2017 International Conference on Engineering and Technology (ICET), Antalya, Turkey, 21–23 August 2017, IEEE.10.1109/ICEngTechnol.2017.8308186 ↗
11. Tan, M., and Le, Q.V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, USA, 9–15 June 2019, PMLR.
12. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large scale image recognition. arXiv.
13. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv.
14. The Hungarian method for the assignment problem10.1002/nav.3800020109 ↗
15. Algorithms for the assignment and transportation problems10.1137/0105003 ↗
16. Burkard, R.E., Dell’Amico, M., and Martello, S. (2009). Assignment Problems, SIAM.10.1137/1.9780898717754 ↗
17. A systematic analysis of performance measures for classification tasks10.1016/j.ipm.2009.03.002 ↗
18. Supriya, Y., and Gadekallu, T.R. (2023). Particle swarm-based federated learning approach for early detection of forest fires. Sustainability, 15.10.3390/su15020964 ↗
19. Khan, S., and Khan, A. (2022). FFireNet: Deep learning based forest fire classification and detection in smart cities. Symmetry, 14.10.3390/sym14102155 ↗
20. Saputra, M.A. (2023). Implementasi Website Deteksi Kebakaran Hutan Dan Lahan Menggunakan Densenet201. [Undergraduate Thesis, Institut Teknologi Telkom Purwokerto].10.52985/insyst.v5i2.317 ↗
21. Davis, M., and Shekaramiz, M. (2023). Desert/Forest fire detection using machine/deep learning techniques. Fire, 6.10.3390/fire6110418 ↗
22. TeutongNet: A fine tuned deep learning model for improved forest fire detection10.60084/ljes.v1i1.42 ↗
23. Alkhammash, E.H. (2025). Leveraging Large Language Models for Enhanced Classification and Analysis: Fire Incidents Case Study. Fire, 8.10.3390/fire8010007 ↗
24. He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 26 June–1 July 2016, IEEE.10.1109/CVPR.2016.90 ↗
25. Revisiting resnets: Improved training and scaling strategies
26. He, K., Zhang, X., Ren, S., and Sun, J. (2016). Identity mappings in deep residual networks. Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, 11–14 October 2016, Proceedings, Part IV, Springer International Publishing.
27. Accelerating very deep convolutional networks for classification and detection10.1109/TPAMI.2015.2502579 ↗
28. Convolutional neural network: A review of models, methodologies and applications to object detection10.1007/s13748-019-00203-0 ↗
29. Deep learning in medical image analysis10.1146/annurev-bioeng-071516-044442 ↗
30. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks10.1109/TPAMI.2016.2577031 ↗
31. Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A.A. (2016). Inception-v4, inception-ResNet and the impact of residual connections on learning. arXiv.10.1609/aaai.v31i1.11231 ↗
32. Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., Langlotz, C., and Shpanskaya, K. (2017). CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv.
33. Hybrid deep CNN–SVM model for classification of Alzheimer’s disease from structural MRI data
34. Solving the many to many assignment problem by improving the Kuhn–Munkres algorithm with backtracking10.1016/j.tcs.2016.01.002 ↗
35. A survey on transfer learning10.1109/TKDE.2009.191 ↗
36. How transferable are features in deep neural networks?
37. Dropout: A simple way to prevent neural networks from overfitting
38. Kingma, D.P., and Ba, J. (2015, January 14–16). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations (ICLR), Banff, AB, Canada.
39. Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation
40. Han, J., Kamber, M., and Pei, J. (2011). Data Mining: Concepts and Techniques, Elsevier. [3rd ed.].
41. Provost, F., and Fawcett, T. (2013). Data Science for Business: What You Need to Know About Data Mining and Data-Analytic Thinking, O’Reilly Media.
42. Evaluation metrics and statistical tests for machine learning10.1038/s41598-024-56706-x ↗
43. Classification assessment methods10.1016/j.aci.2018.08.003 ↗