Predicting Outflow Hydrographs of Potential Dike Breaches in a Bifurcating River System Using NARX Neural Networks

Early flood forecasting systems can mitigate damage during extreme events. Typically, the effects of events in terms inundation depths and extents are computed using detailed hydraulic models. However, a major drawback these models is computational time, which generally order hours to days for large river basins. Gaining insight outflow hydrographs case dike breaches especially important estimate extents. In this study, NARX neural networks that were capable predicting multiple accurately developed. The timing failures cumulative volumes predicted. These findings show networks—specifically, time series—have potential be used within early warning system future.