Rainfall-runoff transformation of a watershed is one of the most complex hydrology phenomena, nonlinier process, time-varying and spatial distribution. Rainfall-runoff relationships play an important role
in water resource management planning and therefore, different types of models with various degrees of
complexity have been developed for this purpose. The application of Artificial Neural Networks (ANNs)
on rainfall-runoff modelling has studied more extensively in order to appreciate and fulfil the potential of
this modelling approach. Back propagation method has used in this study for modelling monthly rainfall
for small size catchments areas. ANN model developed in this study successfully predicts relationship for
rainfall-runoff with 90.14% accuracy on learning process and 72.41% accuracy on testing process.
These results show that ANN provides a systematic approach for runoff estimation and represents
improvement in prediction accuracy.