Home / Current Issue / Paper 1717650
A Real-Time Location-Based Flood and Landslide Risk Prediction System Using Machine Learning and Live Weather Data
Subject area: Science,Engineering and Technology · Area of research: ML-Based Flood & Landslide Prediction
DOI: https://doi.org/10.64388/IREV9I11-1717650
Abstract
Every year, millions of lives are lost because of floods, landslides, and other types of natural disasters, particularly in South Asia, owing to the absence of early warning systems that can be considered effective. The purpose of this paper is to present our product, "Flood Guard Pro" – a system to predict imminent flooding and landslides using real-time data and location-based information. The proposed system uses a three-layered architecture consisting of the React 18 frontend and Python Flask backend as well as the SQLite database. Data on live weather conditions, including rainfall, humidity, temperature, and pressure, will be provided by OpenWeatherMap.The risk zones will be assessed based on the rule-based algorithm, together with the usage of Haversine distance. Thus, it will be possible to establish whether a particular area poses low, medium, or high risks (safe zone, flood, and landslide prone areas correspondingly).Additionally, the system will feature a two-language chatbot, created using AI technology and capable of offering safety guidelines to users. Other important additions will include offline availability, OTP login, voice commands and notifications, admin panel, etc.
Keywords
Flood Prediction, Landslide Risk, Real-Time Alert System, Haversine Distance, OpenWeatherMap API, React, Flask, Progressive Web App, Geolocation, Bilingual Chatbot, Disaster Management
References
[1] M. Wahba, E. Mabrouk, Y. M. Youssef, M. Saber, N. S. Alarifi, N. Y. Rebouh, and M. M. Mansour, "Enhanced hazard mapping for flood and landslide risks using memetic programming and machine learning techniques to support sustainable development goals," IEEE Access, vol. 13, pp. 182410–182429, 2025, doi: 10.1109/ACCESS.2025.3623933.
[2] P. C. V. Chaganti, K. Vasireddy, E. R. Reddy, R. R. Dondeti, and S. Syama, "Predicting landslides and floods with deep learning," in Proc. 4th Int. Conf. Electronics and Sustainable Communication Systems (ICESC), 2023, pp. 1259–1265, doi: 10.1109/ICESC57686.2023.10193456.
[3] R. Kumar, N. Sahi, et al., "Flood prediction using supervised machine learning algorithms," in Proc. IEEE 5th Int. Conf. Smart Electronics and Communication (ICOSEC), 2024, doi: 10.1109/ICOSEC61587.2024.10722348.
[4] Y. Chen, "Modeling rules of regional flash flood susceptibility prediction using different machine learning models," Frontiers in Earth Science, 2023.
[5] M. Rondinone, et al., "Assessing flood and landslide susceptibility using XGBoost: Case study of the Basento River in Southern Italy," Applied Sciences, 2025.
[6] N. Bhavana and T. Sagar, "Machine learning based flood and landslide prediction," International Journal of Innovative Science and Research Technology, vol. 10, no. 5, 2025.
[7] L. B. L. Santos, "Machine learning-based hydrological models for flash floods: A systematic literature review, “Smart Construction and Sustainable Cities, 2025.
How to cite this paper
@article{1717650,
author = {G. Poovizhi, M. Sirisha, S. Sobana, A. Vidhyalakshmi, M. Samundeeswari},
title = {A Real-Time Location-Based Flood and Landslide Risk Prediction System Using Machine Learning and Live Weather Data},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {11},
pages = {1443-1451},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1717650.pdf},
abstract = {Every year, millions of lives are lost because of floods, landslides, and other types of natural disasters, particularly in South Asia, owing to the absence of early warning systems that can be considered effective. The purpose of this paper is to present our product, "Flood Guard Pro" – a system to predict imminent flooding and landslides using real-time data and location-based information. The proposed system uses a three-layered architecture consisting of the React 18 frontend and Python Flask backend as well as the SQLite database. Data on live weather conditions, including rainfall, humidity, temperature, and pressure, will be provided by OpenWeatherMap.The risk zones will be assessed based on the rule-based algorithm, together with the usage of Haversine distance. Thus, it will be possible to establish whether a particular area poses low, medium, or high risks (safe zone, flood, and landslide prone areas correspondingly).Additionally, the system will feature a two-language chatbot, created using AI technology and capable of offering safety guidelines to users. Other important additions will include offline availability, OTP login, voice commands and notifications, admin panel, etc.},
keywords = {Flood Prediction, Landslide Risk, Real-Time Alert System, Haversine Distance, OpenWeatherMap API, React, Flask, Progressive Web App, Geolocation, Bilingual Chatbot, Disaster Management},
month = {May},
doi = {https://doi.org/10.64388/IREV9I11-1717650}
}