Comparison of Hydrological Modeling, Artificial Neural Networks and Multi-Criteria Decision Making Approaches for Determining Flood Source Areas

Flood risk management is a critical task which necessitates flood forecasting and identifying flood source areas for implementation of prevention measures. Hydrological models, multi-criteria decision models (MCDM) and data-driven models such as the Artificial Neural Networks (ANN) have been used to identify flood source areas within a watershed. The aim of this study was to compare the results of hydrological modeling, MCDM and the ANN approaches in order to identify and prioritize flood source areas. The study results show that the classification results of the hydrological model and the ANN have a significant correlation. The correlation between the TOPSIS method with the hydrological model indicate no meaningful correlation. Since the ANN model has simulated the HEC-HMS classifications very accurately, it can be a good substitute for the hydrological models in watersheds with limited data.