Authors : N. Bhavana; T. Sagar

Volume/Issue : Volume 10 - 2025, Issue 5 - May

Google Scholar : https://tinyurl.com/565basb9

DOI : https://doi.org/10.38124/ijisrt/25may1041

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

Abstract : Floods and landslides are among the most destructive natural disasters, causing significant loss of life, infrastructure damage, and economic disruption. Timely prediction of these events is critical for minimizing their impact and enhancing disaster preparedness. This study presents a machine learning-based approach for predicting floods and landslides by analyzing historical data, weather patterns, and environmental factors. The proposed system leverages various machine learning algorithms, including decision trees, support vector machines, and random forests, to process and classify data from multiple sources, such as rainfall, soil moisture, terrain characteristics, and previous event records. By training the models on large datasets, the system is capable of identifying key indicators and patterns associated with flood and landslide occurrences. The prediction results are used to generate early warning signals, helping authorities take proactive measures to mitigate the effects of these disasters. The effectiveness of the system is demonstrated through comparative performance evaluation, where it outperforms traditional methods in terms of accuracy and reliability. This machine learning-based framework offers a scalable and efficient solution for real-time disaster prediction, providing a valuable tool for improving the resilience of communities at risk of floods and landslides.

Keywords : Machine Learning, Floods and Landslides.

References :

1. Shrestha, S., & Gupta, H. (2018). Application of Machine Learning Algorithms in Flood Prediction: A Review. Journal of Hydrology, 562, 707-717.
2. Jain, S., Singh, P., & Kumar, P. (2019). A Hybrid Model for Flood Prediction Using Decision Trees and Deep Learning. International Journal of Applied Earth Observation and Geoinformation, 75, 1-10.
3. Lee, C., & Choi, S. (2017). Machine Learning Techniques for Landslide Susceptibility Mapping: A Comparative Study. Landslides, 14(3), 1125-1138.
4. Guzzetti, F., & Reichenbach, P. (2019). Ensemble Models for Landslide Susceptibility Mapping. Geomorphology, 340, 12-23.
5. Khan, S., Ahmed, S., & Butt, R. (2020). Flood Prediction Using Machine Learning and Remote Sensing Data. Environmental Monitoring and Assessment, 192(8), 1-16. -
6. Zhu, J., Wu, J., & Chen, L. (2018). Landslide Prediction Using Deep Learning Models Based on Satellite Data. Journal of Geophysical Research: Earth Surface, 123(8), 1884-1898.
7. Zhang, Y., & Wang, L. (2019). Addressing Data Imbalance in Disaster Prediction Using Machine Learning. International Journal of Disaster Risk Reduction, 34, 456-465.
8. Maggioni, V., & Giglio, M. (2020). Improving the Interpretability of Machine Learning Models for Natural Disaster Prediction. AI and Society, 35(4), 987-998.
9. Bui, D. T., & Nguyen, H. T. (2021). Hybrid Machine Learning Models for Natural Disaster Risk Prediction and Management. Journal of Natural Hazards, 106(1), 1-22.
10. V. P. R. N. Kumar, & Y. S. Chandra. (2019). Application of Machine Learning in Flood Forecasting: A Review and Future Prospects. Environmental Science and Pollution Research, 26(8), 7894-7907.