Authors

Ravindra Patil

Pd. Dr. Vithalarao Vikhe Patil Instt. of Technology (POLYTECHNIC). Loni Tal. Rahata Dist. Ahmednagar Maharashtra, India

Ganesh Singh

Pd. Dr. Vithalarao Vikhe Patil Instt. of Technology (POLYTECHNIC). Loni Tal. Rahata Dist. Ahmednagar Maharashtra, India

Amrutha Modi

Pd. Dr. Vithalarao Vikhe Patil Instt. of Technology (POLYTECHNIC). Loni Tal. Rahata Dist. Ahmednagar Maharashtra, India

Abstract

Effective disaster risk management (DRM) necessitates scientifically grounded methodologies to bridge the gap between risk prevention and preparedness strategies. Deliberations surrounding the United Nations post-2015 framework for disaster risk reduction emphasize the critical importance of transboundary early warning systems (EWS) in enhancing preparedness capabilities, minimizing loss of life, protecting property, and mitigating the socio-economic impacts of extreme events. Large-scale continental and global flood forecasting systems generate essential early warning information for national and international civil protection agencies, enabling informed decision-making and proactive response planning. This study evaluates the potential economic benefits of early flood warnings by analyzing forecast outputs from the European Flood Awareness System (EFAS) in conjunction with established flood damage cost datasets and estimations of avoided losses. The cost–benefit analysis indicates that the monetary returns are approximately €400 for every €1 invested in the system. To address methodological uncertainties, a comprehensive sensitivity analysis is conducted to quantify variability in the benefit estimates and establish a range of potential economic outcomes. The findings provide robust evidence of significant financial advantages associated with continental-scale, cross-border flood early warning systems. These results reinforce global efforts to expand and strengthen large-scale early warning infrastructures as a strategic approach to enhancing resilience against natural hazards.

Keywords

Random Forest Support Vector Machine (SVM) and Long Short-Term Memory (LSTM) Logistic Regression MLP (Multiplier) KNN (k-nearest neighbour)

Citation of this Article

Ravindra Patil, Ganesh Singh, & Amrutha Modii. (2025). Hydrological Flood Forecasting through Machine Learning Methods. Current Journal of Engineering and Science Research. 2(8), 18-23. Article DOI: https://doi.org/10.47001/CJESR/2025.208004

Licence Copyright (c) 2026 Current Journal of Engineering and Science Research. This work is licensed under a Creative Commons Attribution Non Commercial 4.0 International Licence.

References

  1. Pappenberger, F.; Cloke, H.L.; Parker, D.J.; Wetterhall, F.; Richardson, D.S.; Thielen, J. The monetary benefit of early flood warnings in Europe. Environ. Sci. Policy 2015, 51, 278–291.
  2. Krzysztofowicz, R. Bayesian system for probabilistic river stage forecasting. J. Hydrol. 2002, 268, 16–40.
  3. Todini, E. Role and treatment of uncertainty in real-time flood forecasting. Hydrol. Process. 2004, 18, 2743–2746.
  4. Clark, M.P.; Slater, A.G. Probabilistic quantitative precipitation estimation in complex terrain. J. Hydrometeorol. 2006, 7, 3–22.
  5. [5] Vrugt, J.A.; Robinson, B.A. Treatment of uncertainty using ensemble methods: Comparison of sequential data assimilation and Bayesian model averaging. Water Resources. 2007, 43.
  6. Ebtehaj, M.; Moradkhani, H.; Gupta, H.V. Improving robustness of hydrologic parameter estimation by the use of moving block bootstrap re-sampling. Water Resour. Res. 2010, 46.
  7. He, X.; Refsgaard, J.C.; Sonnenborg, T.O.; Vejen, F.; Jensen, K.H. Statistical analysis of the impact of radar rainfall uncertainties on water resources modeling. Water Resources. 2011, 47.
  8. Legleiter, C.J.; Kyriakidis, P.C.; McDonald, R.R.; Nelson, J.M. Effects of uncertain topographic input data on two dimensional flow modelling in a gravel-bed river. Water Resour. Res. 2011, 47.
  9. Sikorska, A.E.; Scheidegger, A.; Banasik, K.; Rieckermann, J. Bayesian uncertainty assessment of flood predictions in ungauged urban basins for conceptual rainfall-runoff models. Hydrol. Earth Syst. Sci. 2012, 16, 1221–1236.
  10. Montanari, A.; Koutsoyiannis, D. A blueprint for process-based modeling of uncertain hydrological systems. Water Resour. Res. 2012, 48.
  11. Prof. Parthasarathi Choudhary and A. Sankarasubramanian (2009), ―River Flood Forecasting Using Complementary Muskingumrating Equations ‖ ,Journal of Hydrologic Engineering, Vol. 14, No. 7, July 1, 2009.
  12. Korada Hari Venkata Durga Rao, Vala Venkateshwar Rao, Vinay Kumar Dadhwal, Gandarbha Behera, and Jaswant Raj Sharma, ―A Distributed Model for Real-Time Flood Forecasting In The Godavari Basin Using Space Inputs‖, International Journal Disaster Risk Sci. 2011, 2 (3): 31– 40.
  13. Sulafa Hag Elsafi (2014) ―Artificial Neural Networks (Anns) For Flood Forecasting at Dongola Station in the River Nile, Sudan‖, Alexandria Engineering Journal (2014) 53, 655–662.