FloodControlDSS:

FloodControlDSS is a coupled simulation-optimization model intended for determining optimal flow releases in a multi-storage system for flood control. The models include (a) a batch of scripts for data acquisition of forecasted precipitation and their automated post-processing; (b) a hydrological model (HEC-HMS) for rainfall-runoff conversion, (c) a hydraulic model (HEC-RAS) for simulating river inundation, and (d) the genetic algorithm and pattern search optimization methods. Because the optimization may require thousands of simulations, the current runtimes of FloodControlDSS could take several hours or even days. We are currently exploring Machine Learning methods to reduce the runtime of predictions drastically.

• Can handle any number of storage systems.

• The optimization methods include the genetic algorithm and pattern search.

• The framework uses the HEC-HMS and HEC-RAS as the hydrologic and hydraulic models, respectively.