M. T. Dastorani - School of Civil Engineering, University of Nottingham, Nottingham NG ۷ ۲RD, UK
N. G. Wright - School of Civil Engineering, University of Nottingham, Nottingham NG ۷ ۲RD, UK

This study aimed to model river flow in a multi-gauging station catchment and provide real-time prediction of peak flow downstream using artificial neural networks (ANN). Three types of ANN (Multi-Layer Perceptron (MLP), Recurrent, and Time Lag Recurrent) were adapted to evaluate the applicability of this technique. The study area covers the Upper Derwent River, a tributary of the River Trent in the UK. River flow was predicted at the subject site with lead times of 3, 6, 9 and 12 hours. Tests were completed using different lengths of input data to evaluate the effect of input data size in model outputs. The number of gauging sites to be used as data sources in the model was also evaluated. According to the results of this research it can be said that for real-time forecasting of flow in gauged catchments the type of neural network is an important factor and dynamic architectures, especially general recurrent networks, show a superior ability even for longer prediction horizons

Neural Network, Real-Time River, Flow Prediction