Nasrin Beiranvand; Alireza Sepahvand; Ali Haghizadeh
Abstract
In this study, five soft computing techniques, GP-PUK, GP-RBF, M5P, REEP Tree and RF were used to predict the SL in Cham Anjir, Bahram Joo, Kaka Reza and Sarab Syed Ali hydrometry stations in Khorramabad, Biranshahr and Alashtar sub-watersheds, Lorestan province. Total data set consists of rain, discharge ...
Read More
In this study, five soft computing techniques, GP-PUK, GP-RBF, M5P, REEP Tree and RF were used to predict the SL in Cham Anjir, Bahram Joo, Kaka Reza and Sarab Syed Ali hydrometry stations in Khorramabad, Biranshahr and Alashtar sub-watersheds, Lorestan province. Total data set consists of rain, discharge and solute load (SL) of three sub-watersheds out of which 70% data used to training and 30% data were used to testing phase. Finally, the models’ accuracy was assessed using three performance evaluation parameters, which were Correlation Coefficient (C.C.), Root Mean Square Error (RMSE) and Maximum Absolute Error (MAE). Results suggest that GP-PUK and GP-RBF models works well than other modeling approaches in estimating the SL in low and high water-periods. The result showed that, In the high-water period, in Cham Anjir, Sarab Said Ali and Kaka Reza stations the GP-RBF model and in the Bahram Joo station the GP-PUK model with the highest C.C and the lowest error were selected the optimal models in estimating the SL. Also, in the low water period, result shown that in Cham Anjir, Sarab Said Ali and Bahram Joo stations the GP-RBF model and in the Kaka Reza station the GP-PUK model were the best models in estimating the SL. Therefore, these models can be used to estimate the solute load of nearby rivers by/without hydrometry station for the management of the quantity and quality of surface water.
leila abdollahi; Mohammad Faraji; ali haghizadh; Somayeh Dehdari
Abstract
Abstract The effects of droughts on surface water and groundwater resources reduce the amount of water available to different sectors. Hydrological drought initially begins with decreasing rainfall and is usually associated with lower levels of lakes and reservoirs. To this end, in order to ma ke appropriate ...
Read More
Abstract The effects of droughts on surface water and groundwater resources reduce the amount of water available to different sectors. Hydrological drought initially begins with decreasing rainfall and is usually associated with lower levels of lakes and reservoirs. To this end, in order to ma ke appropriate management decisions to prevent the harmful effects of drought, it is necessary to assess the characteristics of this phenomenon by assessing and monitoring the drought. In this research, the time series analysis and SDI shaking technique were used to evaluate the hydrological drought at the hydrometric station at the Marian River during the period from 1982 to 2015. The results of hydrological drought on the sunshine station showed that the highest frequency of droughts was related to mild droughts with 29.41% and severe drought with 11.74% and medium drought of 2.94%. Also, the results of self-correlation series analysis, which showed significant correlation for all months except Azar, before the analysis of its effect was removed by Hamed and Rao (modified by Mann-Kendal), and in December, the ordinary Mann-Kendall test used. In all months of the station, except for the month of Aban and Azar (non significant), during the period of 1982-2015, gradual changes are significant at 5% level, and the sudden changes of the time series are significant at 5% level and have a decreasing trend. Also, the results of the Paty's homogeneity test showed that the sudden changes in the time series were significant at all levels at the 5% level.