The prediction of floods with acceptable accuracy is the most important step in designing flood control structures and operating flood damage mitigation projects. It is more difficult for ungauged catchments where no flow data is available to calibrate efficient methods. In recent years, the technique of Artificial Neural Networks (ANN) has been applied as a successful tool to solve various problems concerned with hydrology and water resources engineering and planning. In this research the applicability of this technique has been investigated to predict the index flood for several ungauged catchments across the UK.Catchment descriptors have been used as input data and the index flood of the catchments as output. Different types and number of catchment descriptors were used as inputs to choose those that show the best relationship with the catchment hydrological behaviour and flood magnitude. A network with 7 inputs represented the best result Although a network with only three inputs showed an accuracy slightly less than the network with 7 inputs. ANN models with different architectures have been used with training and validation sets of data to find the best ANN for this application. It has been found that the Multi-Layer Perceptron network with three layers, and Tanh function for hidden layer and Sigmoid function for output layer is the most accurate network for this purpose.In this research the best result has been obtained when the ANN was trained for a group of catchments which are hydrologically similar. The classification of the catchments according to their similarity in hydrological behaviour was done using WINFAP-FEH software (developed by the UK Institute of Hydrology). It identifies the catchments which are homogenous to the subject site using some parameters including drainage area, annual rainfall and base flow index. The outputs of the model where close enough to the measured values both in training and validation phases. The results obtained from catchment classification and index flood prediction using different ANN model structures and inputs will be presented in appropriate tables and graphs.

Keywords