An Inclusive Flood Awareness and Prediction System Using Ensemble Machine Learning for Disaster Preparedness

View at publisher Summarise with VIRAT
Authors: Sindhu L, V. Mohanraj, Vignesh B, Shree Nathish, Sakthi L, Ravikumar S
Cited by: 0
References: 17

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Inclusive Flood Awareness and Prediction System uses the strength of machine learning to enhance flood preparedness in flood-affected regions. Choosing the volume of information users feed it with several essential environmental variables, like precipitation, precipitation of yesterday, temperature, soil moisture, river levels, elevation, and geographic position the platform predicts the risk of flooding in real-time and send email alerts whenever the moderate or highlevel danger is identified. It is smart because it is based on an ensemble model which is a combination of a Support Vector machine and a random forest where the two algorithms are created to complement each other and provide extremely confident predictions under different circumstances. The system was tuned to a 94.2% accuracy, once feature scaling and hyperparameter tuning were done, along with accuracy features; precision, recall, and F1-score, are in the 90s range, which represents the robustness of the generalization applicability of the system. The solution is developed in Python and Flask and provides a user-friendly web interface serving to visualize the results in real time, which makes it easy to conduct advanced flood forecasting making it scalable and communityfriendly in the end so that it serves to protect lives, infrastructure and livelihoods.

Fields of Study & Subjects

Flood Risk Assessment and Management Hydrological Forecasting Using AI Energy and Environmental Systems

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
1459–1466
Publication date
21 January 2026
Language
EN