Neural Networks for Flood Simulation & Forecasting

The simulation of flooding in the sewer network is currently a computationally expensive process that can take many hours or days to complete for large networks.  This project, known as RAPIDS and partially supported by UKWIR (UK Water Industry Research) is studying the use of neural networks as data-driven models  of drainage systems to allow many different forecast scenarios to be investigated in a shorter space of time.  The project will also investigate the use of computational intelligence techniques in the forecasting of rainfall with the aim of creating an efficient nowcasting and scenario simulation tool.  Find out more information about the RAPIDS project


Duncan A., Chen A., Keedwell E., Djordjevic S., Savic D. (2011) Urban Flood Prediction in Real-time from Weather Radar and Rainfall Data using Artificial Neural Networks Weather Radar and Hydrology Symposium 2011, Exeter