Development of A Novel Machine Learning Model for Accurate ‎Classification of Forest Fire Scenarios

  • Authors

    • R. Arif Mohamed Khan Assistant Professor, Department of Computer Science and Business Systems, Sethu Institute of Technology College, Pulloor, Kariapatti, ‎Virudhunagar District, Tamil Nadu, India
    • Elangovan Muniyandy Department of Biosciences, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, India; Applied ‎Science Research Center, Applied Science Private University, Amman, Jordan
    • Kavitha Gunasekaran Assistant Professor, Department of Artificial Intelligence and Data Science, Ramco Institute of Technology, Rajapalayam, India
    • P. Rajeswari Department of Electronics and Teleommunication Engineering, Dayananda Sagar College of Engineering, Bangalore, Karnataka, India
    • M. RAMYA Department of Computer Applications, Sri Meenakshi Government Arts College for Women (A), Madurai, India
    • Vishnu Kant Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India
    https://doi.org/10.14419/ykmgaa53

    Received date: May 15, 2025

    Accepted date: June 14, 2025

    Published date: July 8, 2025

  • Forest Fires; Modified Mayfly Optimizer Tuning Gradient Boosting Decision Trees (MMO-GBoostDT); Environmental Variability; ‎Classification.

  • Abstract

    Forest fires pose significant environmental and economic threats, necessitating accurate classification for timely intervention. Traditional ‎classification methods often lack precision due to complex fire dynamics and environmental variability. This research aims to develop a ‎novel Machine Learning (ML) model that enhances the classification accuracy of forest fire scenarios by addressing data imbalance and ‎improving feature selection. The proposed model involves Modified Mayfly Optimizer Tuning Gradient Boosting Decision Trees (MMO-‎GBoostDT). The MMO is employed to optimize hyper parameters for GBoostDT model. By fine-tuning the hyper parameters, the ‎proposed MMO-GBoostDT model improves the model’s ability to generalize and prevent over fitting. The dataset consists of aerial and ‎terrestrial images. Noise reduction employing median filtering is utilized to remove unwanted noise in aerial images. Independent spectral ‎features were extracted to enhance fire classification using independent component analysis (ICA), and Mutual Information (MI). ‎Experimental results indicate that the proposed MMO-GBoostDT method outperforms existing methods by achieving a higher precision ‎‎(97.8%), recall (98.5%), accuracy (98.65%) and F1-score (98.2%). The model effectively reduces the false positive and enhances ‎classification robustness. The model demonstrates superior classification accuracy and resilience against data imbalance‎.

  • References

    1. Alkhatib, A. A., Abdelal, Q., & Kanan, T. (2021). Wireless Sensor Network for Forest Fire Detection and behavior Analysis. International Journal of Advances in Soft Computing & Its Applications, 13(1), 82-104.
    2. Sudhir, M. (2022). Untangling Pancard by Designing Optical Character Reader Tool Box By Correlating Alpha Numeric Character. International Journal of communication and computer Technologies, 10, 7-10. https://doi.org/10.31838/ijccts/10.01.03.
    3. Pragati, S. S., & Umbrajkar, P. (2020). Forest fire detection using machine learning. International Journal of Advance Scientific Research and Engi-neering Trends, 4(12), 6-12.
    4. Cadé, D., & Blanchet, B. (2013). From Computationally-Proved Protocol Specifications to Implementations and Application to SSH. Journal of Wire-less Mobile Networks, Ubiquitous Computing, and Dependable Applications, 4(1), 4-31.
    5. Sevinc, V., Kucuk, O., & Goltas, M. (2020). A Bayesian network model for prediction and analysis of possible forest fire causes. Forest Ecology and Management, 457, 117723. https://doi.org/10.1016/j.foreco.2019.117723.
    6. Park, H. B., Kim, Y., Jeon, J., Moon, H. S., & Woo, S. (2019). Practical Methodology for In-Vehicle CAN Security Evaluation. Journal of Internet Services and Information Security, 9(2), 42-56.
    7. Xu, R., Lin, H., Lu, K., Cao, L., & Liu, Y. (2021). A forest fire detection system based on ensemble learning. Forests, 12(2), 217. https://doi.org/10.3390/f12020217.
    8. Ananthi, J., Sengottaiyan, N., Anbukaruppusamy, S., Upreti, K., & Dubey, A. K. (2022). Forest fire prediction using IoT and deep learn-ing. International Journal of Advanced Technology and Engineering Exploration, 9(87), 246-256. https://doi.org/10.19101/IJATEE.2021.87464.
    9. Shi, C., & Zhang, F. (2023). A forest fire susceptibility modeling approach based on integration machine learning algorithm. Forests, 14(7), 1506. https://doi.org/10.3390/f14071506.
    10. Itasanmi, S. A., & Okanlawon, O. (2019). Information Needs and Information Seeking Pattern of Adult Learners. Indian Journal of Information Sources and Services, 9(2), 110–115. https://doi.org/10.51983/ijiss.2019.9.2.612.
    11. Janiec, P., & Gadal, S. (2020). A comparison of two machine learning classification methods for remote sensing predictive modeling of the forest fire in the North-Eastern Siberia. Remote Sensing, 12(24), 4157. https://doi.org/10.3390/rs12244157.
    12. Arnita, V., Zainal, S. R. M., & Jalaludin, D. (2018). To Be or Not to Be? The Influencing Factors towards Pursuing as Professional Accountant Among Indonesian S1 Accounting Students. International Academic Journal of Science and Engineering, 5(2), 1–10. https://doi.org/10.9756/IAJSE/V5I1/1810022.
    13. Kalantar, B., Ueda, N., Idrees, M.O., Janizadeh, S., Ahmadi, K., & Shabani, F., 2020. Forest fire susceptibility prediction based on machine learning models with resampling algorithms on remote sensing data. Remote Sensing, 12(22), p.3682. https://doi.org/10.3390/rs12223682.
    14. Rihan, M., Bindajam, A.A., Talukdar, S., Naikoo, M.W., Mallick, J. and Rahman, A. (2023). Forest fire susceptibility mapping with sensitivity and uncertainty analysis using machine learning and deep learning algorithms. Advances in Space Research, 72(2), 426-443. https://doi.org/10.1016/j.asr.2023.03.026.
    15. Raktur, H., & Jea, T. (2024). Design of compact wideband wearable antenna for health care and internet of things system. National Journal of Anten-nas and Propagation, 6(1), 40–48. https://doi.org/10.31838/NJAP/06.01.06.
    16. Hoa, N. T., & Voznak, M. (2025). Critical review on understanding cyber security threats. Innovative Reviews in Engineering and Science, 2(2), 17-24.
    17. 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(4), 472-485. https://doi.org/10.1007/s41976-024-00140-0.
    18. Rahman, A.K.Z.R., Sakif, S., Sikder, N., Masud, M., Aljuaid, H., & Bairagi, A.K. (2023). Unmanned aerial vehicle assisted forest fire detection using deep convolutional neural network. Intelligent Automation & Soft Computing, 35(3), 3259-3277. https://doi.org/10.32604/iasc.2023.030142.
    19. Singh, S., Jha, M., Talati, B., & Jaiswal, A. (2024). Forest fire detection using CNN.
    20. Abdusalomov, A.B., Islam, B.M.S., Nasimov, R., Mukhiddinov, M., & Whangbo, T.K., 2023. An improved forest fire detection method based on the detectron2 model and a deep learning approach. Sensors, 23(3), 1512. https://doi.org/10.3390/s23031512.
    21. Apostolakis, A., Girtsou, S., Giannopoulos, G., Bartsotas, N.S., & Kontoes, C. (2022). Estimating next day’s forest fire risk via a complete machine learning methodology. Remote Sensing, 14(5), 1222. https://doi.org/10.3390/rs14051222.
    22. Xie, Y., & Peng, M. (2019). Forest fire forecasting using ensemble learning approaches. Neural Computing and Applications, 31(9), 4541-4550. https://doi.org/10.1007/s00521-018-3515-0.
    23. Sarkar, M.S., Majhi, B.K., Pathak, B., Biswas, T., Mahapatra, S., Kumar, D., Bhatt, I.D., Kuniyal, J.C., & Nautiyal, S., (2024). Ensembling machine learning models to identify forest fire-susceptible zones in Northeast India. Ecological Informatics, 81, 102598. https://doi.org/10.1016/j.ecoinf.2024.102598.
    24. Parizi, L., Dobrigkeit, J., & Wirth, K. (2025). Trends in software development for embedded systems in cyber-physical systems. SCCTS Journal of Embedded Systems Design and Applications, 2(1), 57–66.
    25. Sadulla, S. (2024). Optimization of data aggregation techniques in IoT-based wireless sensor networks. Journal of Wireless Sensor Networks and IoT, 1(1), 31-36. https://doi.org/10.31838/WSNIOT/01.01.05.
    26. Veerappan, S. (2025). Digital Twin Modeling for Predictive Maintenance in Large-Scale Power Transformers. National Journal of Electrical Machines & Power Conversion, 39-44.
    27. Nabadova, G. (2024). Controlling the movement of hexacopter along the intended route. Results in Nonlinear Analysis, 7(4), 26-34.
    28. Subermaniam, L., Kuppusamy, M., Isakulova, N., Ghate, A. D., Subrahmanyam, S., & John, B. (2025). A Systematic Review of Sustainability Man-agement in Small and Medium Enterprises to Improve Sustainable Development Goals. Acta Innovations, 38-48.
    29. Sriwardany, S., Fadhilah, D. D., & Sunny, R. (2025). risk management in rice farming using hybrid fmea-ahp: a case study from hamparan perak, in-donesia. Acta Innovations, 24-37

  • Downloads

  • How to Cite

    Khan, R. A. M. ., Muniyandy , E. ., Gunasekaran, . K. ., Rajeswari , P. ., RAMYA, M. ., & Kant, V. . (2025). Development of A Novel Machine Learning Model for Accurate ‎Classification of Forest Fire Scenarios. International Journal of Basic and Applied Sciences, 14(SI-1), 203-210. https://doi.org/10.14419/ykmgaa53