Performance Evaluation of Machine Learning Models for Early Detection of Forest Fires
DOI:
https://doi.org/10.71350/jmis.5Keywords:
Forest Fires, Machine Learning, Image ClassificationAbstract
Forest fires have devastating effects on ecosystem balance and biodiversity worldwide. They are also a problem that causes serious social and economic damage. Therefore, early detection and intervention of fires are crucial. This study presents a model for the high-performance detection and classification of forest fires using image-based data processing techniques and machine learning algorithms. In this context, a comprehensive dataset consisting of images containing and not containing fires was prepared, and the generalization ability of the model was enhanced using data augmentation methods. Gradient boosting, XGBoost random forest, k-nearest neighbors (KNN), and artificial neural network algorithms were used to analyze the classification performance. The performance of each algorithm was maximized through feature extraction and 5-fold cross-validation. The models were comparatively evaluated using performance evaluation metrics such as precision, sensitivity, and F1-score in the obtained results. The results of the study showed that the algorithm with the highest performance in early detection was random forest with an F1-score value of 91.9%. This model was followed by gradient boosting and KNN models with an F1-score value of 90.9%.
References
[1] Kalogiannidis, S., Chatzitheodoridis, F., Kalfas, D., Patitsa, C., & Papagrigoriou, A. (2023). Socio-psychological, economic and environmental effects of forest fires. Fire, 6(7), Article 280. https://doi.org/10.3390/fire6070280
[2] Abbass, K., Qasim, M. Z., Song, H., Murshed, M., Mahmood, H., & Younis, I. (2022). A review of the global climate change impacts, adaptation, and sustainable mitigation measures. Environmental Science and Pollution Research, 29(28), 42539–42559. https://doi.org/10.1007/s11356-022-19718-6
[3] Dale, V. H., Joyce, L. A., McNulty, S., Neilson, R. P., Ayres, M. P., Flannigan, M. D., ... & Wotton, B. M. (2001). Climate change and forest disturbances: Climate change can affect forests by altering the frequency, intensity, duration, and timing of fire, drought, introduced species, insect and pathogen outbreaks, hurricanes, windstorms, ice storms, or landslides. BioScience, 51(9), 723–734. https://doi.org/10.1641/0006-3568(2001)051[0723:CCAFDC]2.0.CO;2
[4] Mansoor, S., Farooq, I., Kachroo, M. M., Mahmoud, A. E. D., Fawzy, M., Popescu, S. M., ... & Ahmad, P. (2022). Elevation in wildfire frequencies with respect to the climate change. Journal of Environmental Management, 301, Article 113769. https://doi.org/10.1016/j.jenvman.2021.113769
[5] Pausas, J. G., & Keeley, J. E. (2021). Wildfires and global change. Frontiers in Ecology and the Environment, 19(7), 387–395. https://doi.org/10.1002/fee.2359
[6] Ren, X., Li, C., Ma, X., Chen, F., Wang, H., Sharma, A., ... & Masud, M. (2021). Design of multi-information fusion based intelligent electrical fire detection system for green buildings. Sustainability, 13(6), Article 3405. https://doi.org/10.3390/su13063405
[7] Li, P., & Zhao, W. (2020). Image fire detection algorithms based on convolutional neural networks. Case Studies in Thermal Engineering, 19, Article 100625. https://doi.org/10.1016/j.csite.2020.100625
[8] Özel, B., Alam, M. S., & Khan, M. U. (2024). Review of modern forest fire detection techniques: Innovations in image processing and deep learning. Information, 15(9), Article 538. https://doi.org/10.3390/info15090538
[9] Soori, M., Arezoo, B., & Dastres, R. (2023). Artificial intelligence, machine learning and deep learning in advanced robotics, a review. Cognitive Robotics, 3, 54–70. https://doi.org/10.1016/j.cogr.2023.04.001
[10] Buchelt, A., Adrowitzer, A., Kieseberg, P., Gollob, C., Nothdurft, A., Eresheim, S., ... & Holzinger, A. (2024). Exploring artificial intelligence for applications of drones in forest ecology and management. Forest Ecology and Management, 551, Article 121530. https://doi.org/10.1016/j.foreco.2023.121530
[11] Lakshmanaswamy, P., Sundaram, A., & Sudanthiran, T. (2024). Prioritizing the right to environment: Enhancing forest fire detection and prevention through satellite data and machine learning algorithms for early warning systems. Remote Sensing in Earth Systems Sciences, 7, 1–14. https://doi.org/10.1007/s41976-024-00121-x
[12] Mtasher, A. K., & Kareem, D. M. (2024). Advancing early warning systems for fire detection: A comprehensive approach in machine learning. Iraqi Journal for Computers and Informatics, 50(1), 187–194. https://doi.org/10.25195/ijci.v50i1.488
[13] Yıldırım, O., Gunay, F. B., & Yağanoğlu, M. (2023). Makine öğrenmesi yöntemleriyle orman yangını tahmini. Journal of the Institute of Science and Technology, 13(3), 1468–1481. https://doi.org/10.21597/jist.1221714
[14] Khosla, C., & Saini, B. S. (2020, Haziran). Enhancing performance of deep learning models with different data augmentation techniques: A survey [Bildiri sunumu]. 2020 International Conference on Intelligent Engineering and Management (ICIEM), Londra, Birleşik Krallık. https://doi.org/10.1109/ICIEM48762.2020.9160048
[15] Maharana, K., Mondal, S., & Nemade, B. (2022). A review: Data pre-processing and data augmentation techniques. Global Transitions Proceedings, 3(1), 91–99. https://doi.org/10.1016/j.gltp.2022.04.020
[16] Maleki, F., Ovens, K., Gupta, R., Reinhold, C., Spatz, A., & Forghani, R. (2022). Generalizability of machine learning models: Quantitative evaluation of three methodological pitfalls. Radiology: Artificial Intelligence, 5(1), Article e220028. https://doi.org/10.1148/ryai.220028
[17] Nti, I. K., Nyarko-Boateng, O., & Aning, J. (2021). Performance of machine learning algorithms with different K values in K-fold CrossValidation. International Journal of Information Technology and Computer Science, 13(6), 61–71. https://doi.org/10.5815/ijitcs.2021.06.05
[18] Ghiasi, M. M., & Zendehboudi, S. (2021). Application of decision tree-based ensemble learning in the classification of breast cancer. Computers in Biology and Medicine, 128, Article 104089. https://doi.org/10.1016/j.compbiomed.2020.104089
[19] Zhang, S. (2021). Challenges in KNN classification. IEEE Transactions on Knowledge and Data Engineering, 34(10), 4663–4675. https://doi.org/10.1109/TKDE.2021.3049250
[20] Boateng, E. Y., Otoo, J., & Abaye, D. A. (2020). Basic tenets of classification algorithms K-nearest-neighbor, support vector machine, random forest and neural network: A review. Journal of Data Analysis and Information Processing, 8(4), 341–357. https://doi.org/10.4236/jdaip.2020.84020
[21] Joshi, A., Sasumana, J., Ray, N. M., & Kaushik, V. (2021). Neural network analysis. M. A. Shanker (Ed.), Advances in Bioinformatics (pp. 351–364). AkiNik Publications.
[22] Galić, D., Stojanović, Z., & Čajić, E. (2024). Application of neural networks and machine learning in image recognition. Tehnički Vjesnik, 31(1), 316–323. https://doi.org/10.17559/TV-20230524000656
[23] Erickson, B. J., & Kitamura, F. (2021). Magician’s corner: 9. Performance metrics for machine learning models. Radiology: Artificial Intelligence, 3(3), Article e200126. https://doi.org/10.1148/ryai.2021200126
[24] Yacouby, R., & Axman, D. (2020, Kasım). Probabilistic extension of precision, recall, and f1 score for more thorough evaluation of classification models [Bildiri sunumu]. First Workshop on Evaluation and Comparison of NLP Systems, Çevrimiçi. https://doi.org/10.18653/v1/2020.eval4nlp-1.9
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Journal of Manufacturing and Intelligent Systems
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
