The rainfall-runoff simulation provides the basis for the hydrological and climate change studies, and the climate studies are based on the rainfall-runoff simulation. In general, there are different models to simulate rainfall and runoff, each with different structures and inputs. In the present paper, two different models in terms of structure were selected: A) Artificial Neural network (ANN) that requires the rainfall, maximum temperature, minimum temperature and runoff data (6 ANN structures were formed based on the relations of partial auto-correlation and cross-correlation), B) Soil and Water Assessment Tool (SWAT) which requires the rainfall, maximum temperature, minimum temperature, and runoff data and the land use, Digital Elevation Model (DEM), and geological maps. In this study, the R², NSE and MBE parameters were used to investigate the error, the monthly and annual averages to investigate the uncertainty, and the SWAT-CUP model of the SUFI-2 algorithm to select sensitive and important parameters for calibrating the SWAT model (in this study, 12 parameters were selected from the sensitive and important parameters). The results of this study showed that based on the error and uncertainty parameters, the ANN model performance (R² = 0.76) during the validation period and the highest MBE = 0.09 in May) is better than the SWAT model (R² = 0.67 in the validation period and the highest MBE = 1.24 in May). Also, the ANN model outperforms the SWAT model in estimating the extreme values. In general, this study found that it is a good practice to utilize the ANN model in the studies associated with climate change and the studies that do not have enough information, and to employ the SWAT model in the studies having a large amount of information and consider the routing and evaluation of the climate change effects on the erosion.

降雨径流模拟为水文和气候变化研究提供了基础，而气候研究则基于降雨径流模拟。通常，有不同的模型来模拟降雨和径流，每种模型具有不同的结构和输入。在本文中，我们选择了两种不同的结构模型：A）需要降雨，最高温度，最低温度和径流数据的人工神经网络（ANN）（根据局部自动模型的关系形成了6种ANN结构）相关和互相关），B）土壤和水评估工具（SWAT），它需要降雨，最高温度，最低温度和径流数据以及土地利用，数字高程模型（DEM）和地质图。在这项研究中，R ²，NSE和MBE参数用于调查误差，月度和年度平均值用于调查不确定性，SUFI-2算法的SWAT-CUP模型用于选择敏感和重要的参数来校准SWAT模型（在本研究中，从敏感和重要参数中选择了12个参数）。这项研究的结果表明，基于误差和不确定性参数， 验证期间的ANN模型性能（R ² = 0.76）和5月的最高MBE = 0.09）要比SWAT模型（R ^2）好。 验证期间= 0.67，5月份最高MBE = 1.24）。同样，在估计极值时，ANN模型优于SWAT模型。总体而言，该研究发现，在与气候变化相关的研究和没有足够信息的研究中使用ANN模型，并在信息量大和成本高的研究中采用SWAT模型是一个好习惯。考虑气候变化对侵蚀的影响的路由和评估。