Cprecip parameter for checking snow entry for forecasting weekly discharge of the Haraz River flow by artificial neural network

Prediction of river flows requires the use of computer facilities and the latest innovations in this field. Artificial Neural Networks (ANNs), as a data-driven approach, are widely and successfully used in the management of water resources, which includes river flow forecasts. However, not using a number of parameters that influence the flow of streams as an input to the network will significantly reduce the performance of the model. One of these parameters, especially in snow basins, is snow. Snow Water Equivalent (SWE) is a common parameter in river flow modeling and is used to effect the snow in the models. This study attempts to introduce cumulative precipitation parameters (Cprecip) instead of SWE. Some basins lack the required SWE; therefore, the Cprecips are applied in order to cope with the changes in these basins. The results show that the Cprecip can be used to replace the SWE when the suitable changes occur according to the conditions of the studied basin.