Journal of Soft Computing Paradigm
IRO Journals
Volume 7 — Issue 2 — June 2025

Innovative Flood Risk Assessment Integrating (LSTM) Network for Rainfall Prediction and Image based Damage Analysis

https://doi.org/10.36548/jscp.2025.2.007
Arun Prasad K.
Assistant Professor, Department of Information Technology, Jerusalem College of Engineering, Chennai, India
Kavinya P.
Department of Information Technology, Jerusalem College of Engineering, Chennai, India
Gayathri S.
Department of Information Technology, Jerusalem College of Engineering, Chennai, India
PDF
PDF

How to Cite

K., Arun Prasad, Kavinya P., and Gayathri S. 2025. “Innovative Flood Risk Assessment Integrating (LSTM) Network for Rainfall Prediction and Image Based Damage Analysis”. Journal of Soft Computing Paradigm 7 (2): 160-75. https://doi.org/10.36548/jscp.2025.2.007.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

— Machine learning
— Rainfall data
— Model Evaluation
— Feature Extraction
— Flood prediction
— Image based Analysis
Published: 22-07-2025

Abstract

Our project emphasizes the importance of addressing flooding, a serious natural disaster that places populations in serious danger of death, widespread property loss, and economic disruption. Despite technological progress, the ability of officials to respond in a timely manner is often undermined by the unpredictable nature of floods and the limitations of existing prediction methods. The severity of the disaster is aggravated by poor resource allocation and delayed evacuations. Additionally, existing flood damage assessment methods often lack accuracy and timeliness in providing insights into the extent of damage. Authorities therefore struggle to effectively prioritize recovery efforts, leading to prolonged suffering for affected populations. What is desperately needed is an integrated system that combines effective damage assessment with accurate flood forecasting. This project seeks to develop an all-in-one solution that not only predicts floods but also evaluates the damage they inflict in real time using rainfall information and advanced image analysis software. By providing alerts and notifications to authorities in a timely manner, this technology facilitates proactive catastrophe management. To guarantee that resources are allocated effectively for recovery purposes, it will also estimate the economic impact of floods. Aiming to preserve lives and reduce monetary harm, the project addresses a significant gap in flood readiness.

References

  1. Thomas, Mitchell, Elizabeth Tellman, Daniel E. Osgood, Ben DeVries, Akm Saiful Islam, Michael S. Steckler, Maxwell Goodman, and Maruf Billah. "A framework to assess remote sensing algorithms for satellite-based flood index insurance." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 16 (2023): 2589-2604.
  2. Farooq, Muhammad Shoaib, Rabia Tehseen, Junaid Nasir Qureshi, Uzma Omer, Rimsha Yaqoob, Hafiz Abdullah Tanweer, and Zabihullah Atal. "FFM: Flood forecasting model using federated learning." IEEE Access 11 (2023): 24472-24483.
  3. Liu, Yang, Lihu Wang, Shuaibing Du, Li Zhao, and Xuemei Liu. "Flood forecasting method based on improved VMD-FOS-QR-RBL." IEEE Access 11 (2022): 4207-4218.
  4. Krullikowski, Christian, Candace Chow, Marc Wieland, Sandro Martinis, Bernhard Bauer-Marschallinger, Florian Roth, Patrick Matgen et al. "Estimating ensemble likelihoods for the Sentinel-1-based global flood monitoring product of the copernicus emergency management service." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 16 (2023): 6917-6930.
  5. Zhao, Jie, Yu Li, Patrick Matgen, Ramona Pelich, Renaud Hostache, Wolfgang Wagner, and Marco Chini. "Urban-aware u-net for large-scale urban flood mapping using multitemporal sentinel-1 intensity and interferometric coherence." IEEE Transactions on Geoscience and Remote Sensing 60 (2022): 1-21.
  6. Aatif, Khansa, Muhammad Abuzar Fahiem, and Fahima Tahir. "Forecasting Floods Using Deep Learning Models: A Longitudinal Case Study of Chenab River, Pakistan." IEEE Access (2024).
  7. Ziv, Shlomi Ziskin, and Yuval Reuveni. "Flash floods prediction using precipitable water vapor derived from GPS tropospheric path delays over the eastern mediterranean." IEEE Transactions on Geoscience and Remote Sensing 60 (2022): 1-17.
  8. Jiang, Jiange, Chen Chen, Yang Zhou, Stefano Berretti, Lei Liu, Qingqi Pei, Jianming Zhou, and Shaohua Wan. "Heterogeneous dynamic graph convolutional networks for enhanced spatiotemporal flood forecasting by remote sensing." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 17 (2024): 3108-3122.
  9. Pech-May, Fernando, Raúl Aquino-Santos, Omar Álvarez-Cárdenas, Jorge Lozoya Arandia, and German Rios-Toledo. "Segmentation and visualization of flooded areas through sentinel-1 images and u-net." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 17 (2024): 8996-9008.
  10. Wang, Songsong, and Ouguan Xu. "Uncertainty forecasting model for mountain flood based on bayesian deep learning." IEEE Access 12 (2024): 47830-47841.
  11. Hakim, Dimara Kusuma, Rahmat Gernowo, and Anang Widhi Nirwansyah. "Flood prediction with time series data mining: Systematic review." Natural Hazards Research 4, no. 2 (2024): 194-220.
  12. Tian, Chang, Pengyu Song, Chunhui Zhao, and Jinliang Ding. "Structure feature extraction for hierarchical alarm flood classification and alarm prediction." IEEE Transactions on Automation Science and Engineering 21, no. 3 (2023): 3944-3954.
  13. Aljohani, Fares Hamad, Ahmad B. Alkhodre, Adnan Ahamad Abi Sen, Muhammad Sher Ramazan, Bandar Alzahrani, and Muhammad Shoaib Siddiqui. "Flood Prediction using Hydrologic and ML-based Modeling: A Systematic Review." International Journal of Advanced Computer Science & Applications 14, no. 11 (2023).
  14. Wang, Songsong, and Ouguan Xu. "Uncertainty forecasting model for mountain flood based on bayesian deep learning." IEEE Access 12 (2024): 47830-47841