A. Rezaei, M. Mahdavi, K. Luxe, S. Feiznia, M. H. Mahdian,
Volume 11, Issue 1 (4-2007)
Abstract
The model in this research was created based on the Artificial Neural Network (ANN) and calibrated in the Sefid-rood dam basin (excluding Khazar zone). This research was done by gathering and selecting peak flows of hydrographs from 12 sub basins, the concentration time of which was equal to or less than 24 hours and was caused only by rainfall. From all the selected sub basins, totally 661 hydrographs were prepared and their peak flows data wes used to make prediction model. The input variables of the model consisted of the depth of daily flooding rainfalls, and so the five days before rainfall of every peak flow, the area of sub basins, the main stream length, the slope of 10-85 percent of main stream, the median height of sub basins, the area of geological formations and rock units, classified at three hydrological groups of I, II, III, the base flow, and output variable was only peak flow. By using Feed Forward Artificial Neural Network with training method of back propagation error the function approximation of inputs to output was created by passing the three processes of training (learning), testing and validation. So based on that data and variables, the Multivariable Linear Regression model was created. The comparison of observed peak flows, based on validation data package, showed that the statistical parameters of (R2) coefficient and Fisher’s test parameter coefficient (F) for ANN model and MLR respectively were 0.84, 33.66 and 0.33, 3.60, indicating the superiority of ANN to traditional methods.
F. Esmaeili, M. Vafakhah, V. Moosavi,
Volume 27, Issue 1 (5-2023)
Abstract
Digital elevation models (DEMs) are one of the most important data required in watershed modeling with hydrological models and their spatial resolution has a significant impact on the accuracy of simulating hydrological processes. In the present study, the effect of spatial resolution of five DEMs derived from the topographic map (TOPO) with a scale of 1:25000, ALOS PALSAR, ASTER, SRTM, and GTOPO with a spatial accuracy of 10, 12.5, 30, 90, and 1000 m, respectively, on the estimation of parameters of geomorphological and geomorphoclimatic unit hydrographs models has been evaluated in Amameh watershed. Thirty-four single flood events were used during the years 1970 to 2015. The results showed that in the GUH method, the application of the TOPO and ALOS PALSAR DEMs had the best results with root mean square error (RMSE) of 1.7 and 1.8 m3/s and Nash-Sutcliffe Efficiency (NSE) of 0.4 and 0.3, respectively. While the GTOPO DEM had the least efficiency with RMSE of 2.8 m3/s and NSE of -2. Similarly, the lowest and highest RMSE in the GCUH method belonged to TOPO and GTOPO DEMs with RMSE of 3.8 and 18 m3/s and NSE of 0.2 and -6, respectively. Generally, the GUH method had more favorable results than the GCUH method in all DEMs.
