The relation between rainfall and runoff forms one of the main hydrological cycle elements. It is one of the most complex hydrological phenomena because of the great numbers of parameters used in modeling the physical processes, the expansion of thei
r parameter space, and the temporary change in watershed specifications. Thus, modeling the relation between rainfall and runoff is necessary for hydrological and hydraulic engineering design, integrated management of water resourses, and forecasting flood and preventing its dangers. This research aims at modeling the relation between rainfall and runoff in Alkabeer Aljononbee catchment. It depends on the technique of Artificial Neural Network (ANN). The mathematical model was built by the ntstool and nntool available in the Matlab program. This model depends on daily rainfall, evaporation, air temperature, and relative humidity data taken from meteorological stations that are distributed in the watershed. The daily runoff data have also been used for checking the performance accuracy of the network, using the Simulink technique. The results of this research confirm that artificial neural network technology offers good results in modeling the relation rainfall-runoff, depending on the set of data used. So it could be a better alternative than traditional approaches.
This study has reached to that ANN (5-9-1) (five neurons in input
layer_nine neurons in hidden layer _ one neuron in output layer) is the
optimum artificial network that hybrid system has reached to it with
mean squared error equals (1*10^-4) (0.7
m3/sec), where this software
has summed up millions of experiments in one step and in limited time, it
has also given a zero value of a number of network connections, such as
some connections related of relative humidity input because of the lake
of impact this parameter on the runoff when other parameters are
avaliable.
This study recommend to use this technique in forecasting of
evaporation and other climatic elements.