Suma Mohamadpur; Hamed Rouhani; Hojat Ghorbani Vaghei; Seyed Morteza Seyedian; Abulhasan Fath Abadi
Abstract
In many semi-arid regions of Iran, soil erosion has turned into a serious environmental problem affecting land productivity, nutrient loss, water quality, and fresh water ecosystems. Rates of soil loss differ according to erosion type and land degradation processes. Rill erosion is commonly observed ...
Read More
In many semi-arid regions of Iran, soil erosion has turned into a serious environmental problem affecting land productivity, nutrient loss, water quality, and fresh water ecosystems. Rates of soil loss differ according to erosion type and land degradation processes. Rill erosion is commonly observed when rainstorms occur on steep slopes and sediment transport in rill flows exhibits the characteristics of non-equilibrium transport. In this paper, sediment concentration of rill flow is estimated by adaptive neuro-fuzzy inference system (ANFIS). A series of mathematical equations and parameters affecting rill hydrodynamics and soil detachment were used for well-defined rill sediment concentration. A series of filed experiments were performed to evaluate the model. The stepwise method was used to select the most important and effective input variables from measured input parameters of soil properties, topographic and vegetation attributes affecting sediment concentration of rill flow. Based on the stepwise procedure, the most significant parameters in the model predications were steep slope, vegetation percentage, clay percentage, and shear stress parameters. The values of sediment concentration simulated by the model were in agreement with observed values with Coefficient of Correlation (R2), Root Mean Square Error (RMSE) and Mean Bias Error (MBE) of 0.697, 30.5 and 1.0, respectively. The results of the investigation shows that the data-driven ANFIS modeling approach can be a powerful alternative technique for correctly estimating rill sediment concentration.
Hamed Rouhani; Mohsen Farahi Moghadam
Abstract
In the past decades, much effort has been devoted to simulation of the rainfall-runoff process. Hydrological models are simplified representations of the natural hydrologic system. In each case, the choice of the model to be applied depends mainly on the objective of the modeling but also on the available ...
Read More
In the past decades, much effort has been devoted to simulation of the rainfall-runoff process. Hydrological models are simplified representations of the natural hydrologic system. In each case, the choice of the model to be applied depends mainly on the objective of the modeling but also on the available information. The relative performances of two lumped conceptual-based hydrology models (Tank and SYMHYD) were compared based on daily data of Chehel_Chay catchment in the northeast region of Golestan province. As in Tank and SIMHYD models, parameter spaces are high dimensional, it is difficult to obtain optimal parameters using manual trial and error procedure. These parameters need to be estimated through an inverse method by calibration. Therefore, an automatic optimization procedure based on the Genetic Algorithm (GA) was tested for parameter calibration of two models. For testing the applicability of the model in gauged basin, the model was calibrated for a period of 1992–1996 and validated for a period of 2002–2005. The result showed that RMSE of discharge predictions were as low as 0.821 for a Nash-Sutcliffe coefficient of 0.599 for the Tank model, against 0.819 for a Nash-Sutcliffe coefficient of 0.602 for the SYMHYD model in calibration period. When evaluating the model performance in validation period, SYMHYD model is performing most accurately with RMSE=0.490 and E=0617. It was found the RMSE for Tank model is 0.522, which is slightly higher than SIMHYD (RMSE=0.490). SIMHYD is performing most accurately with E equal to 0.602 and 0.607 in calibration and validation periods, respectively.
