Home / Current Issue / Paper 1717876
Machine Learning-Based Prediction of Urban Flooding Using Rainfall Data
Subject area: Science,Engineering and Technology · Area of research: M L, AI, Flood Prediction, Data Science
DOI: https://doi.org/10.64388/IREV9I11-1717876
Abstract
Urban flooding is becoming a more common problem due to rapid urban development, climate change and increase in intensity of rain. As the concrete areas grow, and poorly designed drainage systems proliferate, the land has more difficulty absorbing the water whenever an extreme event occurs, and urban flooding becomes a problem. Past methods of predicting flooding used hydrological and hydrodynamic modelling, both of which required large quantities of data from the environment as well as computational resources, thus making real-time prediction of floods challenging. As new advancements in machine learning have emerged, they have offered a more trackable solution by being able to analyse rainfall and environmental data quickly and accurately, predicting a flood event. The present research aims to present rationalization and design of a Machine Learning Based Flood Prediction System in Presence of both Rainfall and Meteorological Data in Urban Regions. This system uses past flood records, temperature, humidity, and rainfall intensities; the various factors are analysed and patterns of flooding are created. In addition, different machine learning algorithms (Logistic Regression, Random Forest, Support Vector Machine (SVM), and XGBOOST) were utilised and compared to predict the most accurate method of predicting floods. The accuracy, precision, recall and F1 score were used to evaluate the prediction accuracy of each method. The initial aim of this proposed system would be to generate the real-time warning for floods and would help to improve the status of emergency response of disaster management agencies and reduce the social and economic loss faced by urban flooding.
Keywords
Urban Flood Prediction, Machine Learning, Rainfall Forecasting, Disaster Management, XGBoost, Smart City.
How to cite this paper
@article{1717876,
author = {Raghavendra R, Bhogayta Aum R},
title = {Machine Learning-Based Prediction of Urban Flooding Using Rainfall Data},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {11},
pages = {2235-2247},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1717876.pdf},
abstract = {Urban flooding is becoming a more common problem due to rapid urban development, climate change and increase in intensity of rain. As the concrete areas grow, and poorly designed drainage systems proliferate, the land has more difficulty absorbing the water whenever an extreme event occurs, and urban flooding becomes a problem. Past methods of predicting flooding used hydrological and hydrodynamic modelling, both of which required large quantities of data from the environment as well as computational resources, thus making real-time prediction of floods challenging. As new advancements in machine learning have emerged, they have offered a more trackable solution by being able to analyse rainfall and environmental data quickly and accurately, predicting a flood event. The present research aims to present rationalization and design of a Machine Learning Based Flood Prediction System in Presence of both Rainfall and Meteorological Data in Urban Regions. This system uses past flood records, temperature, humidity, and rainfall intensities; the various factors are analysed and patterns of flooding are created. In addition, different machine learning algorithms (Logistic Regression, Random Forest, Support Vector Machine (SVM), and XGBOOST) were utilised and compared to predict the most accurate method of predicting floods. The accuracy, precision, recall and F1 score were used to evaluate the prediction accuracy of each method. The initial aim of this proposed system would be to generate the real-time warning for floods and would help to improve the status of emergency response of disaster management agencies and reduce the social and economic loss faced by urban flooding.},
keywords = {Urban Flood Prediction, Machine Learning, Rainfall Forecasting, Disaster Management, XGBoost, Smart City.},
month = {May},
doi = {https://doi.org/10.64388/IREV9I11-1717876}
}