Review on Disaster Defect Management Using Machine Learning
Keywords:
Convolutional Neural Networks (CNN), Disaster prediction, Disaster type, Image analysis, Machine Learning (ML)Abstract
Accurate prediction of the type of disaster and the rate affected using images can go a long way in improving disaster management. Machine learning models have been proven to analyze disaster images to extract meaningful insights into the challenges of timely disaster response and mitigation. Using large datasets of disaster imagery, these models classify the types of disasters that occur, such as floods, wildfires, and earthquakes, while estimating the level of damage. This is beneficial in expediting resource allocation and prioritizing rescue operations. This paper explores a framework where the ML model processes disaster images to predict the type of disaster and rate of being affected. The model has used more advanced techniques, such as CNN for feature extraction, and regression layers to estimate the severity. Finally, we also discuss applications, limitations, and potential improvements to the model. The findings show the transformative role of image-based ML models in disaster assessment and response planning, paving the way for more efficient disaster management systems.
References
H. S. Munawar, A. W. A. Hammad, and S. T. Waller, “A review on flood management technologies related to image processing and machine learning,” Automation in Construction, vol. 132, p. 103916, Dec. 2021, doi: https://doi.org/10.1016/j.autcon.2021.103916.
M. Yu, C. Yang, and Y. Li, “Big Data in Natural Disaster Management: A Review,” Geosciences, vol. 8, no. 5, p. 165, May 2018, doi: https://doi.org/10.3390/geosciences8050165.
P. Akileswar, K. K. Priya, A. Gunasri, V. H. Kiran, and T. Deepika, “Machine Learning-Enhanced Disaster Management System,” May 01, 2024. https://www.researchgate.net/publication/380215433_Machine_Learning-Enhanced_Disaster_Management_System
Krizhevsky A., I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Communications of the ACM, vol. 60, no. 6, pp. 84–90, May 2012. Available: https://dl.acm.org/doi/10.1145/3065386
S. N. K. B. Amit, S. Shiraishi, T. Inoshita and Y. Aoki, "Analysis of satellite images for disaster detection," 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China, 2016, pp. 5189-5192, doi: https://doi.org/10.1109/IGARSS.2016.7730352.
S. Sankaranarayanan, M. Prabhakar, S. Satish, P. Jain, A. Ramprasad, and A. Krishnan, “Flood prediction based on weather parameters using deep learning,” Journal of Water and Climate Change, Nov. 2019, doi: https://doi.org/10.2166/wcc.2019.321.
T. Gupta and S. Roy, "A Hybrid Model based on Fused Features for Detection of Natural Disasters from Satellite Images," IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, Waikoloa, HI, USA, 2020, pp. 1699-1702, doi: https://doi.org/10.1109/IGARSS39084.2020.9324611.
K. S. A, Priya Nandihal, Seemanthini K, M. D. R, and Liyakathunisa Liyakathunisa, “Prior Detection of Alzheimer’s Disease with the Aid of MRI Images and Deep Neural Networks,” Malaysian Journal of Computer Science, pp. 16–28, Dec. 2022, doi: https://doi.org/10.22452/mjcs.sp2022no2.2.
