Artificial Intelligence Assisted Decision Support System for Forest Fire Crisis Management in Turkey

Year 2025, Volume: 8 Issue: 2, 95 - 113, 26.12.2025

İbrahim Emre Yaraş , Aytuğ Onan

https://doi.org/10.70030/sjmakeu.1789925

Abstract

Natural disasters, particularly forest fires, significantly impact societies by causing loss of life and property. Effective crisis management, encompassing disaster response and subsequent mitigation efforts, is critically important. This paper, drawing upon an Artificial Intelligence (AI) based Decision Support System (DSS) developed for natural disasters in Turkey, focuses specifically on forest fire management. The system utilizes historical fire data and machine learning (ML) techniques to predict the impacts of fires, enhance decision-making processes, and provide timely, accurate information to decision-makers. Data on forest fires in Turkey, primarily from the satellite-based NASA FIRMS dataset and atmospheric analysis from ECMWF ERA5, were analyzed and interpreted. Preprocessing steps, including data cleaning and feature extraction, were applied. An XGBoost classification model was developed and evaluated for fire risk prediction, demonstrating high performance in identifying fire-prone regions and their potential intensity. The developed AI-based system determines provincial risk scores, aiming for effective resource allocation for natural disasters. Performance metrics such as accuracy, precision, and F1 score were calculated, and the model's performance was examined. The system culminates in a user-friendly prototype, the Turkey Disaster Management System (TDMS), offering risk-based resource allocation simulations and AI-supported reporting for proactive fire management.

Keywords

Artificial Intelligence , Machine Learning , Decision Support System , Forest Fires , Data Analysis , Risk Management

References

• Jain, P., Coogan, S. C. P., Subramanian, S. G., Crowley, M., Taylor, S., & Flannigan, M. D. (2020). A review of machine learning applications in wildfire science and management. Environmental Reviews, 28(4), 478–505. https://doi.org/10.1139/er-2020-0019
• Ghali, R., & Akhloufi, M. A. (2023). Deep learning approaches for wildland fires remote sensing: Classification, detection, and segmentation. Remote Sensing, 15(7), 1821. https://doi.org/10.3390/rs15071821
• Giglio, L., Schroeder, W., & Justice, C. O. (2016). The Collection 6 MODIS active fire detection algorithm and fire products. Remote Sensing of Environment, 178, 31–41. https://doi.org/10.1016/j.rse.2016.02.054
• Iban, M. C., & Sekertekin, A. (2022). Machine learning-based wildfire susceptibility mapping using remotely sensed fire data and GIS: A case study of Adana and Mersin provinces, Turkey. Ecological Informatics, 69, 101647. https://doi.org/10.1016/j.ecoinf.2022.101647
• Abujayyab, S. K. M., Kassem, M. M., Khan, A. A., Wazirali, R., Coşkun, M., Taşoğlu, E., Öztürk, A., & Toprak, F. (2022). Wildfire susceptibility mapping using five boosting machine learning algorithms: The case study of the Mediterranean region of Turkey. Advances in Civil Engineering, 2022, 3959150. https://doi.org/10.1155/2022/3959150
• Aksoy, E., Kocer, A., Yılmaz, İ., Akçal, A. N., & Akpınar, K. (2023). Assessing fire risk in wildland–urban interface regions using a machine learning method and GIS data: The example of Istanbul’s European side. Fire, 6(10), 408. https://doi.org/10.3390/fire6100408
• Chéret, V., & Denux, J.-P. (2011). Analysis of MODIS NDVI time series to calculate indicators of Mediterranean forest fire susceptibility. GIScience & Remote Sensing, 48(2), 171–194. https://doi.org/10.2747/1548-1603.48.2.171
• Saleh, A., Zulkifley, M. A., Harun, H. H., Gaudreault, F., Davison, I., & Spraggon, M. (2024). Forest fire surveillance systems: A review of deep learning methods. Heliyon, 10(1), e23127. https://doi.org/10.1016/j.heliyon.2023.e23127
• Wei, C., Xu, J., Li, Q., & Jiang, S. (2022). An intelligent wildfire detection approach through cameras based on deep learning. Sustainability, 14(23), 15690. https://doi.org/10.3390/su142315690
• Rösch, M., Nolde, M., Ullmann, T., & Riedlinger, T. (2024). Data-driven wildfire spread modeling of European wildfires using a spatiotemporal graph neural network. Fire, 7(6), 207. https://doi.org/10.3390/fire7060207
• Andrianarivony, H. S., & Akhloufi, M. A. (2024). Machine learning and deep learning for wildfire spread prediction: A review. Fire, 7(12), 482. https://doi.org/10.3390/fire7120482
• Iban, M. C., & Aksu, O. (2024). SHAP-driven explainable artificial intelligence framework for wildfire susceptibility mapping using MODIS active fire pixels: İzmir, Turkey. Remote Sensing, 16(15), 2842. https://doi.org/10.3390/rs16152842
• Ntinopoulos, N., Sakellariou, S., Christopoulou, O., & Sfougaris, A. (2023). Fusion of remotely sensed fire-related indices for wildfire prediction through the contribution of artificial intelligence. Sustainability, 15(15), 11527. https://doi.org/10.3390/su151511527
• Shwartz-Ziv, R., & Armon, A. (2022). Tabular data: Deep learning is not all you need. Information Fusion, 81, 84–90. https://doi.org/10.1016/j.inffus.2021.11.011
• Guido, R., Ferrisi, S., Lofaro, D., & Conforti, D. (2024). An overview on the advancements of support vector machine models in healthcare applications: A review. Information, 15(4), 235. https://doi.org/10.3390/info15040235
• Chen, X., Yu, D., & Zhang, X. (2024). Optimal weighted random forests. Journal of Machine Learning Research, 25, Article 100. (Preprint: https://doi.org/10.48550/arXiv.2305.10042)
• Wiens, M., Verone-Boyle, A., Henscheid, N., Podichetty, J. T., & Burton, J. (2025). A tutorial and use case example of the eXtreme gradient boosting (XGBoost) artificial intelligence algorithm for drug development applications. Clinical and Translational Science, 18(3), e70172. https://doi.org/10.1111/cts.70172
• Davis, J., & Goadrich, M. (2006). The relationship between precision–recall and ROC curves. In Proceedings of the 23rd International Conference on Machine Learning (pp. 233–240). ACM. https://doi.org/10.1145/1143844.1143874
• Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861–874. https://doi.org/10.1016/j.patrec.2005.10.010
• Zhou, S., & Erdoğan, A. (2019). A spatial optimization model for resource allocation for wildfire suppression and resident evacuation. Computers & Industrial Engineering, 138, 106101. https://doi.org/10.1016/j.cie.2019.106101
• Hoyer, S., & Hamman, J. J. (2017). xarray: N-D labeled arrays and datasets in Python. Journal of Open Research Software, 5(1), 10. https://doi.org/10.5334/jors.148
• Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. arXiv. https://doi.org/10.48550/arXiv.1705.07874