Modeling Surface Runoff in Al-Mohammadi Valley: Influence of Climate and Soil Parameters

The use of artificial neural networks (ANNs) is becoming increasingly common in the analysis of hydrology and water resources problems.In this research, an ANN was developed and used to model the rainfall-runoff relationship, in a catchment located in a arid climate in western part of Iraq.The aim of this paper is to model the rainfall-runoff relationship in the Al-Mohammadi Valley using a black box type model based on ANN methodology.The multilayer perceptron (MLP) neural network was chosen for use in the current study.Six parameters were considered as independent parameters in the model: daily precipitation, evaporation, temperature, with soil surface properties such as profile soil moisture, root zone soil wetness in addition to soil surface wetness.The Data had been used for about thirty-one years from 1990 up to 2015.The results and comparative study indicate that the artificial neural network method is more suitable to predict river runoff than classical multi linear regression model with a correlation coefficient of 0.61.The results show that the proposed ANN prediction model had a great probability to simulate and predict Runoff.It was observed that the predicted Runoff were close to the observed values with (R = 0.995) for.The significant values of 0.712, and 0.707 for the t-test and F-test respectively indicated the capability of these models to predicate data and there were no significantly different between predicated and observed values.The most variable affecting Runoff values among the runoff input variables is the precipitation as 100% normalized importance analysis, followed by the temperature 85.7%, then soil surface wetness is 72.1%, and the evaporation is 43.4%.