Artificial neural networks (ANNs) are used by hydrologists and engineers to forecast flows at the outlet of a watershed. They are employed in particular where hydrological data are limited. Despite these developments, practitioners still prefer conventional hydrological models. This study applied the standard conceptual HEC-HMS's soil moisture accounting (SMA) algorithm and the multi layer perceptron (MLP) for forecasting daily outflows at the outlet of Khosrow Shirin watershed in Iran. The MLP [optimized with the scaled conjugate gradient] used the logistic and tangent sigmoid activation functions resulting into 12 ANNs. The R 2 and RMSE values for the best trained MPLs using the tangent and logistic sigmoid transfer function were 0.87, 1.875 m 3 s -1 and 0.81, 2.297 m 3 s -1 , respectively. The results showed that MLPs optimized with the tangent sigmoid predicted peak flows and annual flood volumes more accurately than the HEC-HMS model with the SMA algorithm, with R 2 and RMSE values equal to 0.87, 0.84 and 1.875 and 2.1 m 3 s -1 , respectively. Also, an MLP is easier to develop due to using a simple trial and error procedure. Practitioners of hydrologic modeling and flood flow forecasting may consider this study as an example of the capability of the ANN for real world flow forecasting.

No abstract

The comprehensive large-scale assessment of future available water resources is crucial for food security in countries dealing with water shortages like Iran. Kerman province, located in the south east of Iran, is an agricultural hub and has vital importance for food security. This study attempts to project the impact of climate change on available water resources of this province and then, by defining different scenarios, to determine the amount of necessary reduction in cultivation areas to achieve water balance over the province. The GFDL-ESM2M climate change model, RCP scenarios, and the CCT (Climate Change Toolkit) were used to project changes in climatic variables, and the Soil and Water Assessment Tool (SWAT) was used for hydrological simulation. The future period for which forecasts are made is 2020–2050. Based on the coefficient of determination (R2) and Nash–Sutcliffe coefficient, the CCT demonstrates good performance in data downscaling. The results show that under all climate change scenarios, most parts of the province are likely to experience an increase in precipitation yet to achieve water balance a 10% decrease in the cultivation area is necessary under the RCP8.5 scenario. The results of the SWAT model show that green water storage in central and western parts of the province is higher than that in other parts.

No abstract

No abstract