A Machine Learning Framework for AI-Based Wildfire Risk Assessment
Keywords:
AI, Decision Tree, Gradient Boosting, K-Nearest Neighbor, Machine Learning, Naive Bayes, ORNL, Random Forest, Support Vector Machine.Abstract
Forest fires pose a severe risk to both the environment and human life, often causing extensive damage to ecosystems and property. With the growing impact of climate change, including rising temperatures and prolonged droughts, the frequency and intensity of forest fires have increased significantly. Effective early detection and intervention are crucial to minimizing these impacts. In recent years, machine learning (ML) techniques have been applied to forest fire prediction to improve early warning systems. This study aims to reduce the risk and impact of forest fires by predicting their occurrence ahead of time using machine learning. A dataset, sourced from NASA's Oak Ridge National Laboratory (ORNL), containing detailed environmental and forest-related factors, was used for this purpose. Preprocessing steps were applied to prepare the data for classification, including feature selection techniques that narrowed down the dataset from 35 to the most relevant features. Various machine learning algorithms—Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), K-Nearest Neighbor (K-NN), and Naive Bayes (NB)—were employed for classification. The performance of the models was evaluated, and hyperparameter optimization was performed to select the best parameters. The Random Forest model achieved an impressive accuracy of 97%, closely followed by Naive Bayes at 96%, highlighting the effectiveness of these algorithms in predicting forest fires.
References
- FAO, "Global Forest Resources Assessment 2020 – Key findings," Rome, 2020. [Online]. Available: https://www.fao.org/3/ca8753en/ca8753en.pdf. [Accessed: 22-Oct-2023].
- Yeşilyurt, E.N. and Türker, M.F., 2019. Economic Rationality Analysis of Forestry Sector with Econometric Methods (The General Directorate of Forestry Case). Bartın Orman Fakültesi Dergisi, 21(3), pp.893-898.
- M. Arif, K. K. Alghamdi, S. A. Sahel, S. O. Alosaimi, M. E. Alsahaft, M. A. Alharthi, and M. Arif, "Role of machine learning algorithms in forest fire management: A literature review," J. Robot. Autom., vol. 5, pp. 212–226, 2021.
- V. Sevinc, O. Kucuk, and M. Goltas, "A Bayesian network model for prediction and analysis of possible forest fire causes," Forest Ecol. Manage., vol. 457, p. 117723, 2020.
- A. Arpaci, B. Malowerschnig, O. Sass, and H. Vacik, "Using multivariate data mining techniques for estimating fire susceptibility of Tyrolean forests," Appl. Geogr., vol. 53, pp. 258–270, 2014.
- M. Fidanboy, N. A. Nihat, and S. Okyay, "Development of a deep learning-based forest fire prediction model and creation of the Turkey fire risk map," Ormancılık Araştırma Dergisi, vol. 9, no. 2, pp. 206–218, 2022.
- H. Liang, M. Zhang, and H. Wang, "A neural network model for wildfire scale prediction using meteorological factors," IEEE Access, vol. 7, pp. 176746–176755, 2019.
- G. Bayat and K. Yıldız, "Comparison of the Machine Learning Methods to Predict Wildfire Areas," Turkish J. Sci. Technol., vol. 17, no. 2, pp. 241–250, 2022.
- I. D. B. Silva, M. E. Valle, L. C. Barros, and J. F. C. Meyer, "A wildfire warning system applied to the state of Acre in the Brazilian Amazon," Appl. Soft Comput., vol. 89, p. 106075, 2020.
- Y. Shao, Z. Feng, L. Sun, X. Yang, Y. Li, B. Xu, and Y. Chen, "Mapping China’s forest fire risks with machine learning," Forests, vol. 13, no. 6, p. 856, 2022.
- T. Preeti, S. Kanakaraddi, A. Beelagi, S. Malagi, and A. Sudi, "Forest fire prediction using machine learning techniques," 2021 International Conference on Intelligent Technologies (CONIT), pp. 1–6, 2021.
- M. R. Spoorthy and H. Kumar, "Detection of forest fire areas using machine learning," Int. J. Adv. Res. Sci. Comput. Technol., vol. 2, no. 2, 2022.
- P. Mimboro, B. Yanuargi, R. Surimbac, K. Kusrini, and K. Khusnawi, "Forest fire prediction using K-mean clustering and random forest classifier," CSRID Journal, vol. 14, no. 2, pp. 157–165, 2022.
- P. Rakshit, S. Sarkar, S. Khan, P. Saha, S. Bhattacharyya, N. Dey, S. Islam, and S. Pal, "Prediction of forest fire using machine learning algorithms: The search for the better algorithm," 2021 6th International Conference on Innovative Technology in Intelligent System and Industrial Applications (CITISIA), pp. 1–6, 2021.
- Y. Xie and M. Peng, "Forest fire forecasting using ensemble learning approaches," Neural Comput. Appl., vol. 31, pp. 4541–4550, 2018.
- M. Castelli, L. Vanneschi, and A. Popović, "Predicting burned areas of forest fires: An artificial intelligence approach," Fire Ecol., vol. 11, no. 1, pp. 106–118, 2015.
- T. Niranjan, D. Swetha, V. Charitha, and A. J. Stephen, "Predicting burned area of forest fires," Int. Res. J. Comput. Sci., vol. 6, pp. 132–136, 2019.
- R. Coughlan, F. Di Giuseppe, C. Vitolo, C. Barnard, P. Lopez, and M. Drusch, "Using machine learning to predict fire-ignition occurrences from lightning forecasts," Meteorol. Appl., vol. 28, no. 1, p. e1973, 2020.
- Y. Pang, Y. Li, Z. Feng, Z. Feng, Z. Zhao, S. Chen, and H. Zhang, "Forest fire occurrence prediction in China based on machine learning methods," Remote Sens., vol. 14, no. 21, p. 5546, 2022.
- J. Chen, X. Wang, Y. Yu, X. Yuan, X. Quan, and H. Huang, "Improved prediction of forest fire risk in central and northern China by a time-decaying precipitation model," Forests, vol. 13, no. 3, p. 480, 2022.
- C. Lai, S. Zeng, W. Guo, X. Liu, Y. Li, and B. Liao, "Forest fire prediction with imbalanced data using a deep neural network method," Forests, vol. 13, no. 7, p. 1129, 2022.
- X. J. Walker, J. L. Baltzer, L. L. Bourgeau-Chavez, N. J. Day, W. J. De Groot, C. Dieleman, E. E. Hoy, J. F. Johnstone, E. S. Kane, M. A. Parisien, S. Potter, B. M. Rogers, M. R. Turetsky, S. Veraverbeke, E. Whitman, and M. C. Mack, "ABoVE: Synthesis of burned and unburned forest site data, AK and Canada, 1983-2016," ORNL DAAC, Oak Ridge, Tennessee, USA, 2022.
- L. Moreira, C. Dantas, L. Oliveira, J. Soares, and E. Ogasawara, "On evaluating data preprocessing methods for machine learning models for flight delays," 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1–8, 2018.
- Ramagundam, S. (2022). Ai-Driven Real-Time Scheduling For Linear Tv Broadcasting: A Data-Driven Approach. International Neurourology Journal, 26(3), 20-25.
- H. Lin and H. Ding, "Predicting ion channels and their types by the dipeptide mode of pseudo amino acid composition," J. Theor. Biol., vol. 269, no. 1, pp. 64–69, 2011.
- J. Qiu, H. Wang, J. Lu, B. Zhang, and K. L. Du, "Neural network implementations for PCA and its extensions," Int. Scholarly Res. Notices, vol. 2012, 2012.
- Ramagundam, S. (2023). Predicting broadband network performance with ai-driven analysis. Journal of Research Administration, 5(2), 11287-11299.
- M. M. Uddin, A. A. Bakar, and S. Chien, "Machine learning for prediction and optimization of forest fire outbreaks," Int. J. Comput. Appl., vol. 178, no. 6, pp. 15–23, 2019.
- T. M. Mitchell, Machine Learning. McGraw-Hill, 1997.
- D. Singh, A. Prakash, and P. Gupta, "A study on K-NN algorithm for classification and its applications," Int. J. Comput. Sci. Inf. Technol., vol. 8, no. 4, pp. 1–8, 2016.
- S. Islam, S. U. Rehman, and W. Ali, "A comparative study of K-NN algorithm with different distance metrics," J. Artif. Intell., vol. 2, no. 1, pp. 7–12, 2007.
- Ramagundam, S. (2021). Next Gen Linear Tv: Content Generation And Enhancement With Artificial Intelligence. International Neurourology Journal, 25(4), 22-28.
- S. Ray, "Decision tree classifier: A survey," Int. J. Comput. Sci. Inf. Technol., vol. 10, no. 1, pp. 45–52, 2019.
- A. C. Lorena, A. C. de Carvalho, and G. Zaverucha, "Random forest for classification: A survey," Comput. Intell., vol. 27, no. 3, pp. 184–214, 2011.
- P. Gislason, J. A. Benediktsson, and J. R. Sveinsson, "Random forests for land cover classification," Pattern Recognit. Lett., vol. 27, no. 4, pp. 294–300, 2006.
- J. H. Friedman, "Greedy function approximation: A gradient boosting machine," The Annals of Statistics, vol. 29, no. 5, pp. 1189–1232, 2001.
- L. Xie, X. Li, and Y. Han, "Gradient boosting based machine learning for prediction of forest fires," Comput. Stat. Data Anal., vol. 128, pp. 45–57, 2019.
- I. Rish, "An empirical study of the naive Bayes classifier," Proc. IJCAI 2001 Workshop Empirical Methods in Artif. Intell., pp. 41–46, 2001.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT

This work is licensed under a Creative Commons Attribution 4.0 International License.