Authors : Tayo P. Ogundunmade; George Olawale Edeki

Volume/Issue : Volume 10 - 2025, Issue 9 - September

Google Scholar : https://tinyurl.com/45uht4es

Scribd : https://tinyurl.com/5n6kdn46

DOI : https://doi.org/10.38124/ijisrt/25sep1204

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : Natural disasters, such as floods, earthquakes, and storms, cause significant human and economic losses worldwide, necessitating accurate early prediction to enhance preparedness. This study leverages spatial (location-based) and temporal (time-based) patterns in the EM-DAT global disaster dataset, containing over 22,071 records with variables like disaster type, location, magnitude, and impacts, to predict disaster occurrence and severity. Three deep learning models Convolutional Long Short-Term Memory (ConvLSTM), Graph Neural Network (GNN), and Long Short-Term Memory (LSTM) were developed to capture spatial-temporal dynamics. The dataset was pre-processed to handle missing values, normalize features, and construct spatial graphs and temporal sequences. Exploratory data analysis (EDA) revealed patterns in disaster frequency, geographic hotspots, and temporal trends. On a held-out test set, the ConvLSTM model achieved the highest performance, with an AUROC of 98.78%, accuracy of 98.45%, Recall of 96.62%, Precision of 97.59% log loss of 0.0912 and F1-score of 97.10%, followed by LSTM and GNN. Visualizations, including spatial heatmaps, temporal prediction curves, confusion matrix and geospatial plots, enhance interpretability. These findings underscore the potential of specialized spatial and temporal models for disaster forecasting, supporting proactive mitigation strategies.

Keywords : Disaster Prediction, Spatial-Temporal Modelling, Deep Learning, Spatial Analysis, Early Warning Systems.

References :

1. IPCC. (2023). Sixth Assessment Report: Climate Change Impacts. Intergovernmental Panel on Climate Change.
2. Smith, R., & Jones, T. (2022). Advances in Disaster Prediction Systems. International Journal of Disaster Risk Reduction, 78, 103123.
3. Chen, X., et al. (2021). Spatial-Temporal Deep Learning for Disaster Prediction. Journal of Disaster Research, 16(3), 45–53.
4. Lee, J., & Kim, H. (2020). Statistical Models for Disaster Forecasting. Natural Hazards Review, 21(4), 04020015.
5. Wang, Y., et al. (2019). Machine Learning for Natural Disaster Prediction. Environmental Modelling & Software, 118, 102–111.
6. Che, Z., et al. (2018). Recurrent Neural Networks for Multivariate Time Series with Missing Values. Scientific Reports, 8(1), 6085.
7. Brown, E. F., & Lee, M. N. (2021). Deep Learning Approaches for Disaster Prediction. Journal of Disaster Research, 16(3), 45–53.
8. Mosavi, A., et al. (2018). Random Forests for Flood Prediction. Water, 10(10), 1362.
9. Zhang, Z., et al. (2021). Challenges in Disaster Data Analysis. Journal of Big Data, 8(1), 45.
10. Shi, X., et al. (2015). Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. NeurIPS.
11. Hu, Y., et al. (2019). Flood Prediction Using ConvLSTM Models. Water Resources Research, 55(12), 10567–10582.
12. Wu, Z., et al. (2020). Graph Neural Networks for Spatial Forecasting. IEEE Transactions on Neural Networks, 31(6), 2301–2312.
13. DeVries, P. M. R., et al. (2018). Deep Learning of Aftershock Patterns. Nature, 560(7717), 632–636.
14. Li, Z., et al. (2021). GNN for Wildfire Spread Prediction. Environmental Modelling & Software, 140, 105032.
15. Ogundunmade TP, Adepoju AA (2022). Modelling Liquefied Petroleum Gas Prices in Nigeria Using Time Series Machine Learning Models. Mod Econ Manag; 1: 5. DOI: 10.53964/mem.2022005.
16. Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780.
17. Le, X. H., et al. (2019). LSTM for Flood Forecasting. Journal of Hydrology, 576, 736–747.
18. Ayansola OA, Ogundunmade TP, Adedamola AO. Statistical Analysis of Cost Reflective Electricity Tariff and Distribution in Nigeria (A Study for Southwest States). Mod Econ Manag, 2023; 2: 5. DOI: 10.53964/mem.2023005.
19. Miller, K. L., & Thompson, J. P. (2019). Transformer Models for Disaster Impact Forecasting. IEEE Transactions on Neural Networks, 30(5), 1401–1412.
20. Xu, Y., et al. (2020). Transformer-Based Time-Series Forecasting for Hurricane Impacts. Journal of Geophysical Research, 125(8), e2020JD032456.
21. Ogundunmade, T.P., Adepoju, A.A. (2024). Predicting the Nature of Terrorist Attacks in Nigeria Using Bayesian Neural Network Model. In: Awe, O.O., Vance, E.A. (eds) Sustainable Statistical and Data Science Methods and Practices. STEAM-H: Science, Technology, Engineering, Agriculture, Mathematics & Health. Springer, Cham. https://doi.org/10.1007/978-3-031-41352-0_14.
22. He, Lei He, Yunhao Xia, Yongqiang Li, Yuxia Bin, Liu Zhang, Siqi Zhang, Cunjie. (2025). Multi-scale extreme climate disaster prediction model integrated with ConvLSTM: taking rainstorm and flood disaster as an example. Geomatics, Natural Hazards and Risk. 16. 10.1080/19475705.2025.2506468.
23. Jeong, Se-Heon Lee, Woo Kil, Hyosub Jang, Soojeong Kim, Jeongheon Kwak, Y.-S. (2024). Deep Learning‐Based Regional Ionospheric Total Electron Content Prediction Long Short‐Term Memory (LSTM) and Convolutional LSTM Approach. Space Weather. 22. 10.1029/2023SW003763.
24. Shen, K. (2023). Introduction to Graph Neural Network. Advances in Systems Analysis, Software Engineering, and High-Performance Computing Book Series, 33–42. https://doi.org/10.4018/978-1-6684-6903-3.ch003.
25. Odeniyi, O. A., Adeosun, M. E., & Ogundunmade, T. P. (2022). Prediction of terrorist activities in Nigeria using machine learning models. Innovations, 71, 87–96.
26. Yu, J., Zhou, X., Lu, S., Xiao, S., Ajun, W., & Yalei, Z. (2023). Study on Five Typical Optimization Models of LSTM. 298–303. https://doi.org/10.1109/cac59555.2023.10450860
27. CRED. (2023). EM-DAT: The International Disaster Database. Centre for Research on the Epidemiology of Disasters.
28. Li, Y., et al. (2020). CNN-Based Flood Detection from Satellite Imagery. Remote Sensing, 12(10), 1625.
29. Lundberg, S. M., & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems, 4765–4774.
30. Taghibakhshi, A., Nytko, N., Zaman, T. U., MacLachlan, S., Olson, L., & West, M. (2022). Learning Interface Conditions in Domain Decomposition Solvers. arXiv. https://doi.org/10.48550/arXiv.2205.09833