ML-Based Prediction of Urban Flooding Using Rainfall Data

• Author(s): Haripriya V; Harshath Ganesh
• Paper ID: 1717967
• Page: 2573-2581
• Published Date: 19-05-2026
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 9 Issue 11 May-2026

Abstract

Urban flooding has emerged as one of the most devastating consequences of rapid, unplanned urbanization across major Indian cities such as Chennai, Mumbai, Bengaluru, and Hyderabad. Every monsoon season, millions of citizens are displaced, critical infrastructure is damaged, and emergency services are stretched beyond capacity. Despite these recurring crises, most municipal bodies in these regions still rely on conventional, rule-based flood management systems that cannot dynamically respond to fast-changing weather conditions.Current flood prediction systems are largely fragmented, where rainfall monitoring networks are disconnected from urban drainage models or real-time flood mapping tools [9]. Consequently, flood warnings are either issued too late or not issued at all, leaving residents and authorities with insufficient time to respond. Furthermore, the absence of spatially granular prediction systems means that even well-equipped cities fail to identify which specific localities will be inundated first. The critical research gap lies in the absence of a unified, machine learning-driven framework that integrates multi-source rainfall data with urban morphology and historical flood records to deliver accurate, early flood predictions. Most existing studies either focus purely on hydrological modelling [10] or sensor data collection [5] in isolation, rather than combining both into a cohesive, real-time prediction system. To address this gap, this paper proposes a Smart Urban Flood Prediction (SUFP) framework. The system leverages historical rainfall data, real-time sensor feeds, and topographical datasets to train ensemble machine learning models for flood prediction. When critical rainfall thresholds are detected, the system autonomously generates flood risk maps and dispatches early warnings to urban planning authorities and citizens [7]. Simultaneously, a centralized geospatial data repository securely stores and retrieves flood event data to continuously improve the model's accuracy over time [4]. The proposed SUFP framework is expected to significantly improve urban flood prediction accuracy, reduce emergency response time, and provide municipal planners with a data-driven tool for designing flood-resilient infrastructure. This research offers a scalable, technology-driven solution for the flood management challenges facing rapidly growing urban centres across Southern India.

Keywords

Urban Flood Prediction, Machine Learning, Rainfall Data Analysis, Smart City Infrastructure, Flood Risk Mapping, Ensemble Learning, Geospatial Data, Early Warning Systems, Urban Hydrology, Remote Sensing

Citations

IRE Journals:
Haripriya V, Harshath Ganesh "ML-Based Prediction of Urban Flooding Using Rainfall Data" Iconic Research And Engineering Journals Volume 9 Issue 11 2026 Page 2573-2581 https://doi.org/10.64388/IREV9I11-1717967

IEEE:
Haripriya V, Harshath Ganesh "ML-Based Prediction of Urban Flooding Using Rainfall Data" Iconic Research And Engineering Journals, 9(11) https://doi.org/10.64388/IREV9I11-1717967