Home / Current Issue / Paper 1725034
Flash Flood Prediction System for Hilly Regions Using Multi-Source Data
Subject area: Science,Engineering and Technology · Area of research: Internet of Things
Abstract
Flash floods in hilly and mountainous regions develop rapidly, which makes localized risk detection and timely warning difficult because of sparse ground-sensor coverage, challenges in integrating different data sources, and communication delays in remote areas. This paper presents a Flash Flood Prediction System for Hilly Regions using Multi-Source Data. The system combines rainfall information, Sentinel-1 satellite imagery, IoT ground-sensor telemetry, and historical and terrain data. Sensor data is filtered, validated, and preprocessed at the edge before integration. A hybrid artificial intelligence approach uses Random Forest to analyse terrain and historical information and Long Short-Term Memory (LSTM) to identify trends in live data, and a late-fusion process combines the outputs into localized risk levels: Low, Watch, Warning, and Evacuate. A Flask-based machine-learning backend serves predictions through an API, a React-based dashboard displays real-time risk on a map, and alerts are designed to reach communities and response authorities through SMS, application notifications, and local sirens. An IoT sensor-node prototype and a live monitoring interface are presented. Quantitative validation is identified as future work.
Keywords
Flash flood prediction, IoT sensors, LSTM, Random Forest, Sentinel-1 SAR
References
[1] Khan I, Bahuguna H, Kainthola A, Ahmed R, Asgher MS. National-scale landslide susceptibility and risk mapping of India using a hybrid data-driven approach. Scientific Reports. 2025;16:3519. https://doi.org/10.1038/s41598-025-33446-0
[2] Liu Y, Hazarika H, Kanaya H, Takiguchi O, Murai M, Hidayat MN, et al. Design and deployment of an IoT-based landslide early warning system. In: 2022 International Conference and Utility Exhibition on Energy, Environment and Climate Change (ICUE); 2022 Oct 26–28; Pattaya, Thailand. p. 1–7. https://doi.org/10.1109/ICUE55325.2022.10113491
[3] Song T, Ding W, Wu J, Liu H, Zhou H, Chu J. Flash flood forecasting based on long short-term memory networks. Water. 2020;12(1):109. https://doi.org/10.3390/w12010109
[4] Carlà T, Intrieri E, Raspini F, Bardi F, Farina P, Ferretti A, et al. Perspectives on the prediction of catastrophic slope failures from satellite InSAR. Scientific Reports. 2019;9:14137. https://doi.org/10.1038/s41598-019-50792-y
[5] Raspini F, Bianchini S, Ciampalini A, Del Soldato M, Solari L, Novali F, et al. Continuous, semi-automatic monitoring of ground deformation using Sentinel-1 satellites. Scientific Reports. 2018;8:7253. https://doi.org/10.1038/s41598-018-25369-w
[6] Geological Survey of India. National Landslide Susceptibility Mapping (NLSM) Programme [Internet]. Available from: https://bhusanket.gsi.gov.in/LS_hazard.html
How to cite this paper
@article{1725034,
author = {Sangana Kotireddy, Chilumula Nishanth, Angara Karthik, Sai Sohan, Joanan Nishant},
title = {Flash Flood Prediction System for Hilly Regions Using Multi-Source Data},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {10},
number = {5},
pages = {2227-2233},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1725034.pdf},
abstract = {Flash floods in hilly and mountainous regions develop rapidly, which makes localized risk detection and timely warning difficult because of sparse ground-sensor coverage, challenges in integrating different data sources, and communication delays in remote areas. This paper presents a Flash Flood Prediction System for Hilly Regions using Multi-Source Data. The system combines rainfall information, Sentinel-1 satellite imagery, IoT ground-sensor telemetry, and historical and terrain data. Sensor data is filtered, validated, and preprocessed at the edge before integration. A hybrid artificial intelligence approach uses Random Forest to analyse terrain and historical information and Long Short-Term Memory (LSTM) to identify trends in live data, and a late-fusion process combines the outputs into localized risk levels: Low, Watch, Warning, and Evacuate. A Flask-based machine-learning backend serves predictions through an API, a React-based dashboard displays real-time risk on a map, and alerts are designed to reach communities and response authorities through SMS, application notifications, and local sirens. An IoT sensor-node prototype and a live monitoring interface are presented. Quantitative validation is identified as future work.},
keywords = {Flash flood prediction, IoT sensors, LSTM, Random Forest, Sentinel-1 SAR},
month = {November},
}