Predicting Forest Areas Susceptible to Fire Risk Using Convolutional Neural Networks

Ansh Gupta

doi:10.51519/journalisi.v6i3.788

Ansh Gupta DPS International Gurgoan, India

Keywords: Machine Learning, Convolutional Neural Network, Deep Learning, Remote sensing, Satellite Imaging, Data processing

Abstract

Wildfires pose a grave danger and threat to both human health and the environment, which is why early detection of wildfires is crucial. In this study, a convolutional neural network, which is a deep learning technique for computer vision, that is capable of classifying satellite imaging of forest cover in Canada as either being prone to wildfires or not being prone to wildfires is created. This model achieved an accuracy of 95.06% and is not only accurate but also reliable and unbiased in terms of the training set and the test set. We also review an existing model for the same dataset. Furthermore, this study discusses the application of this model in the real world, its feasibility, its future scope, and strategies to improve it.

Downloads

Download data is not yet available.

References

L. M. Zavala, R. de Celis, and A. Jordán, "How wildfires affect soil properties. A brief review," Cuad. Investig. Geogr., vol. 40, no. 2, pp. 311–332, 2014. doi: 10.18172/CIG.2522

A. Nappi, P. Drapeau, and J. P. L. Savard, "Salvage logging after wildfire in the boreal forest: Is it becoming a hot issue for wildlife?" Forestry Chron., vol. 80, no. 1, pp. 67–74, 2011. doi: 10.5558/TFC80067-1

E. A. Keller, D. E. DeVecchio, and R. H. Blodgett, Natural Hazards: Earth’s Processes as Hazards, Disasters, and Catastrophes, 2019. doi: 10.4324/9781315164298

M. L. Childs et al., "Daily Local-Level Estimates of Ambient Wildfire Smoke PM2.5 for the Contiguous US," Environ. Sci. Technol., vol. 56, no. 19, pp. 13607–13621, 2022. doi: 10.1021/ACS.EST.2C02934

R. Nasi, R. Dennis, E. Meijaard, G. Applegate, and P. Moore, "Forest fire and biological diversity," Unasylva-FAO, pp. 36-40, 2002.

T. N. Wasserman and S. E. Mueller, "Climate influences on future fire severity: a synthesis of climate-fire interactions and impacts on fire regimes, high-severity fire, and forests in the western United States," Fire Ecol., vol. 19, no. 1, pp. 1–22, 2023. doi: 10.1186/S42408-023-00200-8

S. F. Fonji and G. N. Taff, "Using satellite data to monitor land-use land-cover change in North-eastern Latvia," SpringerPlus, vol. 3, no. 1, pp. 1–15, 2014. doi: 10.1186/2193-1801-3-61

N. Sisodiya, N. Dube, and P. Thakkar, "Next-Generation Artificial Intelligence Techniques for Satellite Data Processing," in Remote Sens. Digit. Image Process., vol. 24, pp. 235–254, 2020. doi: 10.1007/978-3-030-24178-0_11

N. R. Talukdar et al., "Forest fire estimation and risk prediction using multispectral satellite images: Case study," Nat. Hazards Res., vol. 4, no. 2, pp. 304–319, 2024. doi: 10.1016/J.NHRES.2024.01.007

L. Alzubaidi et al., "Review of deep learning: concepts, CNN architectures, challenges, applications, future directions," J. Big Data, vol. 8, no. 1, pp. 1–74, 2021. doi: 10.1186/S40537-021-00444-8

] J. Wu, "Introduction to convolutional neural networks," Natl. Key Lab. Nov. Softw. Technol., Nanjing Univ., China, vol. 5, no. 23, p. 495, 2017.

Y. O. Sayad, H. Mousannif, and H. Al Moatassime, "Predictive modeling of wildfires: A new dataset and machine learning approach," Fire Saf. J., vol. 104, pp. 130-146, 2019.

R. Kanwal, W. Rafaqat, M. Iqbal, and S. Weiguo, "Data-Driven Approaches for Wildfire Mapping and Prediction Assessment Using a Convolutional Neural Network (CNN)," Remote Sens., vol. 15, no. 21, p. 5099, 2023.

C. Nebauer, "Evaluation of convolutional neural networks for visual recognition," IEEE Trans. Neural Netw., vol. 9, no. 4, pp. 685-696, 1998.

N. Srivastava et al., "Dropout: A Simple Way to Prevent Neural Networks from Overfitting," J. Mach. Learn. Res., vol. 15, pp. 1929–1958, 2014.

A. F. Agarap, "Deep Learning using Rectified Linear Units (ReLU)," arXiv preprint arXiv:1803.08375, 2018.

S. R. Dubey, S. K. Singh, and B. B. Chaudhuri, "Activation functions in deep learning: A comprehensive survey and benchmark," Neurocomputing, vol. 503, pp. 92–108, 2022. doi: 10.1016/j.neucom.2022.06.111

D. Kinga and J. B. Adam, "A method for stochastic optimization," in Proc. Int. Conf. Learn. Represent. (ICLR), vol. 5, p. 6, May 2015.

K. Ding, N. Xiao, and K.-C. Toh, "Adam-family Methods with Decoupled Weight Decay in Deep Learning," arXiv preprint arXiv:2310.08858, 2023.

P. M. Radiuk, "Impact of Training Set Batch Size on the Performance of Convolutional Neural Networks for Diverse Datasets," Inf. Technol. Manag. Sci., vol. 20, no. 1, 2018. doi: 10.1515/ITMS-2017-0003

S. A. Mnati, F. I. Hussein, and A. Issa, "Development of an ANN Model for RGB Color Classification using the Dataset Extracted from a Fabricated Colorimeter," Al-Khwarizmi Eng. J., vol. 19, no. 4, pp. 67-77, 2023.

M. Yang et al., "Deep neural networks with L1 and L2 regularization for high dimensional corporate credit risk prediction," Expert Syst. Appl., vol. 213, 118873, 2023. doi: 10.1016/J.ESWA.2022.118873

S. Ruder, "An overview of gradient descent optimization algorithms," arXiv preprint arXiv:1609.04747, 2016.

T. Hernández-Del-Toro, F. Martínez-Santiago, and A. Montejo-Ráez, "Assessing classifier’s performance," in Biosignal Process. Classif. Using Comput. Learn. Intell.: Princ., Algorithms, Appl., pp. 131–149, 2021. doi: 10.1016/B978-0-12-820125-1.00018-X

A. Rock and R. Malhoski, Mapping with ArcGIS Pro: Design Accurate and User-Friendly Maps to Share the Story of Your Data. Packt Publishing Ltd., 2018.