Abstract
Forest fire prediction is an important aspect of combating forest fires. This research focuses on the effectiveness of multi-source data (lightning, hydrometric and weather) in the probability prediction of forest fires using deep learning. The results showed that the weather model had the best predictive power (average \(F1 Score = 0.955\)). The lightning model had an average \(F1 Score = 0.924\), while the hydrometric model had an average \(F1 Score = 0.690\). The single-source models were then merged to see the impact of the multi-source data. The multi-source model had an average \(F1 Score = 0.929\), whereas the average F1Score for the previous three single-source model was 0.856. The results showed that the multi-source model performed similarly to the best-performing single-source model (weather) with a 60% reduction in training data. The multi-source model had a negligible impact from the poor-performing single-source model (hydrometric).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Akkus, C., et al.: Multimodal deep learning. arXiv:2301.04856 (2023)
Canada, N.R.: The State of Canada’s Forests: Annual Report 2022. Natural Resources, Canada (2022)
Gao, J., et al.: A survey on deep learning for multimodal data fusion. Neural Comput. 32, 829–864 (2020)
Holle, R.L.: Some aspects of global lightning impacts. In: International Conference on Lightning Protection (2014)
Johnson, E.A., Miyanishi, K.: Forest Fires: Behavior and Ecological Effects. Academic Press Inc, San Diego (2001)
Johnson, J.M., Khoshgoftaar, T.M.: Deep learning and data sampling with imbalanced big data. In: IEEE 20th International Conference on Information Reuse and Integration for Data Science, IRI, pp. 175–183 (2019)
Kochtubajda, B., Burrows, W.R.: Cloud-to-ground lightning in Canada: 20 years of CLDN data. Atmos. Ocean 58, 316–332 (2020)
Kowsari, K., et al.: RMDL: random multimodel deep learning for classification. In: International Conference on Information Systems and Data Mining (2018)
Mapari, R.G., et al.: An IoT based automated hydroponics farming and real time crop monitoring. In: 2nd International Conference on Intelligent Technologies (CONIT) (2022)
Mutakabbir, A., et al.: Spatio-temporal agnostic deep learning modeling of forest fire prediction using weather data. In: 2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC), pp. 346–351 (2023). https://doi.org/10.1109/COMPSAC57700.2023.00054
Ramachandram, D., Taylor, G.W.: Deep multimodal learning: a survey on recent advances and trends. Signal Process. Mag. 34, 96–108 (2017)
Sanjaya, H., et al.: Indonesia fire danger rating system (Ina-FDRS), a new algorithm for the fire prevention in Indonesia. In: IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS) (2019)
Silviana, S., Saharjo, B., Sutikno, S.: Fire risk analysis based on groundwater level... IOP Conf. Ser. Mater. Sci. Eng. 796, 012041 (2020)
Summaira, J., et al.: Recent advances and trends in multimodal deep learning: a review. arXiv:2105.11087v1 (2021)
Sun, T., et al.: Mountains forest fire spread simulator based on geo-cellular automation combined with Wang Zhengfei velocity model. IEEE J. Sel. Top. Appl. Earth Observ. Rem. Sens. 6, 1971–1987 (2013)
Vikram, R., Sinha, D.: A multimodal framework for forest fire detection and monitoring. Multimed. Tools Appl. 82, 9819–9842 (2023)
Wang, S., Li, J., Russell, H.A.: Methods for estimating surface water storage changes and their evaluations. J. Hydrometeorol. 24, 445–461 (2023)
Young, R., Giese, R.: Introduction to Forest Fire. Wiley, Oxford (1991)
Acknowledgements
This research was funded by NSERC Canada, and supported by Research Computing Services at Carleton University. The authors thank Fatemeh and Parveen for their support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Mutakabbir, A. et al. (2024). Forest Fire Prediction Using Multi-Source Deep Learning. In: Tan, Z., Wu, Y., Xu, M. (eds) Big Data Technologies and Applications. BDTA 2023. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 555. Springer, Cham. https://doi.org/10.1007/978-3-031-52265-9_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-52265-9_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-52264-2
Online ISBN: 978-3-031-52265-9
eBook Packages: Computer ScienceComputer Science (R0)