Al-Rafidain Engineering Journal (AREJ)

Abstract

Abstract:
Modeling a hydrologic time series has been one of the most complicated tasks
owing to the wide range of data, the uncertainties in the parameters influencing the
time series and also due to the non availability of adequate data. Recently, Artificial
Neural Networks (ANNs) have become quite popular in time series forecasting in
various fields. This paper demonstrates the use of ANNs to forecast Khabur monthly
river flows for flow data from January 1958 to December 1975. Using the feed
forward network. The network is trained using the lagged or delayed variables from
SARIMA model as an input variables for the network. ANN model for mouthy flow
gives better result in comparison with Traditional ANN models and SARIMA model.