Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{185214,
        author = {Bunga Varshith and Dr. G. Narasimha Rao},
        title = {Hybrid Flood Forecasting System Integrating Machine Learning And Geospatial Analysis: A Study of Vijayawada, India},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {5},
        pages = {976-980},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=185214},
        abstract = {Floods are the natures destructive force causing major human, economic and agricultural loss. A flood forecasting system can minimize such losses; a Decision Support System (DSS) for Flood Forecasting in Vijayawada (India) is presented in this paper. The proposed system can predict the flood by using Sentinel-1 SAR-GRD for flood extent mapping, SRTM-DEM for flood depth estimation, and a 5-year-size historical dataset of hydrological (India-WRIS) and meteorological (Open-Meteo) variables. A geospatial analysis was performed of the severe September 2024 flood event, and results including an inundation area of 65.35 km2 and corresponding depth of inundation were derived. This ground truth generated by the satellite was used to improve the historical dataset which was used as an input to train a two-stage machine learning architecture. This architecture first applies the random forest classifier to estimate the probability of occurrence of flood, and if the risk is high, the second stage applies a random forest regressor to estimate the potential inundation area. The final DSS is an interactive dashboard that integrates live 7-day weather forecasts from the Open-Meteo API to provide a dynamic flood risk assessment, thereby demonstrating a reliable and scalable framework for data-driven disaster management.},
        keywords = {Flood Forecasting, Decision Support System (DSS), Machine Learning, Sentinel-1 SAR, Geospatial Analysis, Random Forest Classifier, Random Forest Regressor.},
        month = {October},
        }