Author(s): Zakermoshfegh Mohammad; Yazdandoost Farhad; Ghalkhani Hossein; Bozorgy Babak; Mirzaee Mehdi
Linked Author(s): Farhad Yazdandoost
Keywords: River Flow Forecasting; Artificial neural network; NAM model; Kashkan River
Abstract: River flow forecasting is required to be provided by a wide range of data of river systems. Since there are a lot of parameters with uncertainities and non-linear relationships, the calibration of conceptual or physically-based models is often a difficult and time consuming procedure. So it is preferred to implement a heuristic black box model to perform a non-linear mapping between the input and output spaces without detailed consideration of the internal structure of the physical process. In this paper, the capability of artificial neural networks (ANNs) for stream flow forecasting in Kashkan River in west of Iran is investigated and compared to a NAM model which is a lumped conceptual model with shuffled complex evolution (SCE) algorithm for auto calibration. The most popular ANN namely Multi Layer Perceptron (MLP) network is introduced and implemented. The results show that the discharge can be more adequately forecasted by this kind of ANN compared to the NAM model.