Accurate prediction of peak discharges due to embankment dam failure is essential to identifying and reducing potential for loss of life and damage in the downstream floodplain. Because, when a dam fails the damage is certain, but the extent of this damage cannot be evaluated in advance. The loss of life and property damage can vary depending on flood area and population. In order to cope with embankment dam breaching and to take necessary steps beforehand many researchers worked on parametric breach models based on Regression Analysis (RA) to estimate the peak outflow from a breached embankment dam since 1970s. RA is a widely-used approach that could provide acceptable results. Since, this approach bears restrictive assumptions, direct application of RA ignoring these assumptions might cause pitfalls and biased calculations. In this study, it is shown that previous works generated by RA gives biased calculations and a new alternative approach, based on Artificial Neural Networks (ANN), is suggested in replacement of classical RA, which gives more accurate results according to both numerical error criteria and scientific background.

The dam-break induced loads and their effects on buildings are of vital importance for assessing the vulnerability of buildings in flood-prone areas. A comprehensive methodology, for risk assessment of buildings subject to flooding, is nevertheless still missing. This research aims to take a step forward by following previous research. To this aim, (1) five statistical procedures including: simple correlation analysis, multiple linear regression model, stepwise multiple linear regression model, principal component analysis and cluster analysis are used to study relationship between mean normalized force on structure and other related variables; (2) a new and efficient variable that can take into account both the shape of the structure and flow conditions is proposed; (3) a new and practical formula for predicting the mean normalized force is suggested for different types of obstacles, which is missing in the previous research.