election algorithm

In recent years, increasing salinity and reducing the quality of groundwater have become one of the environmental challenges due to the penetration and mixing of pollutants. These challenges have created serious risks for the development of human societies and health. In order to prevent future risks and appropriate planing for preserving water resources, a qualitative study of groundwater resources is an essential requirement. In this research, a swarm intelligence approach based on election algorithm and gray wolf optimization algorithm is presented to determine the optimal values ​​for water quality parameters such as TDS, EC and SAR. In order to evaluate the proposed method, data on the plain of Bostanabad city in the 10 years period (2003-2013) were used and the results were evaluated based on Wilcox, Schuler and Piper measures. The results of the experiments show that the underground water of Bostanabad city is modest to acceptable for agriculture and drinking and is suitable for industry due to corrosion and hardness. Most of the data were in the C2S2 class, which is suitable for agriculture. The correlation coefficient above 95% indicates the acceptable accuracy of the gray wolf optimization algorithm in comparison with the election algorithm in estimating the groundwater quality parameters.

It is very important to predicte and modifed the groundwater levels in the future period and the possibility of water resources planning and management to improve aquifer conditions. In this study, for the first time, used election algorithm to predicted groundwater level in the Miandoab plain. EA algorithm is a repeat algorithm inspired by presidential election and working with a set of khown solutions as a population. Also the results were compared of ANN and Genetic algorithm. Water table level data such as temperature, precipitation, humidity, evaporation and water surface data for the 2005 -2015 period was used as our data in this study. Based on the calculations performed and the results predicted from the statistical parameters, the election algorithm has a significant ability in the groundwater level with RMSE, R2 and NSE, 0.027, 0.93 and 0.74, respectively, in comparison to ANN method and GA algorithm and provides reliable results.