Modeling the Groundwater Level of the Miandoab Plain Using Artificial Neural Network Method and Election and Genetic Algorithms

Document Type : Research Article


1 Ph.D. Candidate of Hydrualic Structures of Tabriz University

2 Ph.D. Candidate of Irrigation and Drainage of Gorgan University of Agricultural Sciences and Natural Resources

3 Assistant Professor of Water Engineering of Tabriz University


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.


Main Subjects

[1]. Hamzekhani H, Aghaie M M. Modeling of groundwater in the Miandoab plain using remote sensing technologyto verify the aquifer's effectiveness on surface currents. Remote Sensing Research Center (RSRC). Urmia Lake Restoration Program. Sharif University Technology. 2015; 150 pages. [Persian]
[2]. Urmia lake restoration program. Remote Sensing Research Center. Sharif University Technology. 2015. [Persian]
[3]. Mohtasham M, Dehghani AA, Akbarpour A, Meftah M, Etebari B. Groundwater level determination by using artificial neural network (Case study: BirjandAquiefer). Iran. J. Irrig. Drain. 2010; 1 (4): 1-10. [Persian]
[4]. Merikh-Bayat F. Evolutionary optimization algorithms (with applications in electrical engineering). Jahad Academic Press. 2014. [Persian]
[5]. Yaghini M, Akhavan-Kazemzadeh M R. Evolutionary optimization algorithms. Jahad Academic Press of Amirkabir University. 2016. [Persian]
[6]. Yang Z P, Lu W X, Long Y Q, Li P. Application and comparison of two prediction models for groundwater levels: a case study in Western Jilin Province, China. J. Arid Environ. 2009; 73: 487-492.
[7]. Shiri J, Kisi O. Comparison of genetic programming with neurofuzzy systems for predicting short-term water table depth fluctuations. Comput. Geosci. 2011; 37: 1692-1701.
[8]. Rajaie T, Pour-Aslan, F. Prediction of the time and local of thegroundwater level of Davarzan plain. Hydrogeomorphology. 2015; 4: 1-19. [Persian]
[9]. Mahmoodijam S, Ghoreyshi-Najafabadi S H, Vafaienejad A R, Khazayi S. Potentiometric analysis of groundwater resources using hybrid approach to particle swarm optimization algorithm and spatial information system (case study: Mehran plain, Ilam). Ecohydrology. 2017; 4(4): 1199-1213. [Persian]
[10]. Habibi M H, Nadiri A A, Asghari-Moghaddam A. Spatio-temporal Groundwater Level Prediction Using Hybrid Genetic-Kriging Model (Case Study: Hadishahr Plain). Iran Water Resources. 2016; 11(3): 85-99. [Persian]
[11]. Moosavi V, Vafakhah M, Shirmohammadi B, Behnia N. A wavelet-ANFIS hybrid model for groundwater level forecasting for different prediction periods. J Water Resour Manage 2013; 27: 1301–1321.
[12]. Taghizadeh S A, Fereydony M. Simulation of groundwater level by applying two methods of wavelet-neural fuzzy inference and wavelete-neural network and comparing them with each other. International Conference on Civil Engineering, Architectural and Urban Development. Tehran. 2017; 1-11. [Persian]
[13]. Khashei-Siuki A, Ghahreman B, Kochakzadeh M. Comparison of Artificial Neural Network Models, ANFIS and regression in estimation of Neyshabour plain aquifer level. Iran. J. Irrig. Drain. 2013; 7(1): 10-22. [Persian]
[14]. Nikmanesh M R. Application of artificial intelligence integration methods in prediction of groundwater levels in Khorameh plain of Marvdasht in Fars province. Iranian Water Resources Management Conference. AmirKabir Politechnic University. 2011. [Persian]
[15]. Akbarzadeh F, Hasanpour H, Emamgholizadeh S. Groundwater Level Prediction of Shahrood Plain using RBF Neural Networks. Journal of Watershed Management Research. 2014; 7(13): 104-118. [Persian]
[16]. Abareshi F, Meftah Halghi M, Sanikhani H, Dehghani A A Comparison of three intelligence techniques for predicting water table depth fluctuations (Case study: Zarringol plain). J. Water and Soil Conservation. 2014; 21(1): 163-180. [Persian]
[17]. Mohammadi B, Biazar S M, Asadi, E. Performance of hybrid particle swarm algorithm to simulate water level (Case study: Ardabil aquifer). Stained Rainfall Systems. 2017; 5(15): 77-87. [Persian]
[18]. Zarrinehrood drainage and irrigation project. Groundwater Studies of Miandoab Plain, Mahab Ghods Engineering Avisory Company, West Azarbaijan Regional Water Organization. 1990. [Persian]
[19]. Report of the status and execution of Zarrinehrood projects. Mahab Ghods Engineering Avisory Company, West Azarbaijan Regional Water Organization. 2009. [Persian]
[20]. Emami H, Derakhshan F. Election algorithm: A new socio-politically inspired strategy. AI Communications. 2015; 28: 591–603.
[21]. Menhaj M B. Computational Intelligence, No. 1. The Basic of Artificial Neural Networks. Amirkabir University. 1998. [Persian]
[22]. Goldberg D E. Genetic algorithms in search, optimization and machine learning. Addison-Wesley, Reading, Mass. 1989.
[23]. Larose D T. Discovering knowledge in data: an introduction to data mining. Jhon Wiley & Sons Inc. 2005; 240 p.
Volume 5, Issue 4
January 2019
Pages 1175-1189
  • Receive Date: 02 March 2018
  • Revise Date: 17 September 2018
  • Accept Date: 23 September 2018
  • First Publish Date: 22 December 2018