Urban Stormwater Runoff Prediction Using Recurrent Neural Networks

It has been recognized that urban stormwater pollution can be a large contributor to the water quality problems of many receiving waters. Stormwater pollution is one of most important issues the District of Columbia faces. The downtown core of the District is serviced by combined sewer system. Therefore, evaluations of stormwater runoff are necessary to enhance the performance of an assessment operation and develop better water resources management and plan. In order to accomplish the goal, a predictive model based on recurrent neural networks with the Levenberg-Marquardt backpropagation training algorithm is developed to forecast the stormwater runoff using the precipitation and the previous stormwater runoff. This computational modeling tool explored a new computational intelligence solution for monitoring and controlling urban water pollution in the District of Columbia. The experimental results show that Levenberg-Marquardt backpropagation training algorithm proved to be successful in training the recurrent neural network for the stormwater runoff prediction.