RETRACTED ARTICLE: Evaluating groundwater level fluctuation by support vector regression and neuro-fuzzy methods: a comp
- PDF / 2,109,925 Bytes
- 15 Pages / 439.37 x 666.142 pts Page_size
- 8 Downloads / 220 Views
Evaluating groundwater level fluctuation by support vector regression and neuro-fuzzy methods: a comparative study Mohammad Mirzavand • Benyamin Khoshnevisan • Shahaboddin Shamshirband • Ozgur Kisi • Rodina Ahmad Shatirah Akib
•
Received: 4 October 2014 / Accepted: 3 January 2015 Ó Springer Science+Business Media Dordrecht 2015
Abstract Quantitative groundwater modeling is essential in water resources management. In this article, the abilities of two different data-driven methods, support vector regression (SVR) and an adaptive neuro-fuzzy inference system (ANFIS), were investigated in estimating monthly groundwater level fluctuation in the Kashan plain, Isfahan province, Iran, by using the inputs of stream flow, evaporation, spring discharge, aquifer discharge and rainfall. Polynomial and radial basis function (RBF) was used as the kernel function of the SVR. Root mean squared error (RMSE) and correlation coefficient (R) statistics were used for evaluation of the applied models. The results indicated that the ANFIS model, having an RMSE of 3.6 m and R of 0.985, performed better than the
M. Mirzavand Department of Watershed Management, Faculty of Natural Resources and Earth Sciences, University of Kashan, Kashan, Iran B. Khoshnevisan Department of Agricultural Machinery Engineering, Faculty of Agricultural, Engineering and Technology, University of Tehran, Karaj, Iran S. Shamshirband (&) Department of Computer Systems and Information Technology, Faculty of Computer Science and Information Technology, University of Malaya (UM), 50603 Kuala Lumpur, Malaysia e-mail: [email protected] O. Kisi Department of Civil Engineering, Faculty of Architecture and Engineering, Canik Basari University, 55080 Samsun, Turkey R. Ahmad Department of Software Engineering, Faculty of Computer Science and Information Technology, University of Malaya (UM), 50603 Kuala Lumpur, Malaysia S. Akib Department of Civil Engineering, Faculty of Engineering, University of Malaya (UM), 50603 Kuala Lumpur, Malaysia
123
Nat Hazards
optimal SVR_rbf model (RMSE = 13 m and R = 821) in the test period. Among the SVR methods, the SVR_rbf model was found to be better than the SVR_poly model. Keywords
Groundwater level fluctuation Soft computing ANFIS SVR_rbf SVR_poly
1 Introduction Groundwater is an important source of freshwater throughout the world (Li et al. 2013). In arid and semiarid environments, groundwater plays a significant role in the ecosystem. The sustainable use of water for industry, agriculture and wildlife is critical (Ghazavi et al. 2012). In arid and semiarid regions, rainfall is highly variable and significantly lower than the evaporation rate; consequently, groundwater can be a major component of the water (Jolly et al. 2008). The use of groundwater is growing because of the rapid development of the economy, demand for water resources, low costs, high quality and availability in arid regions (Tajul Baharuddin et al. 2013; Todd and Mays 2005; Li et al. 2014; Pe´rez-Martı´n et al. 2014). About 55 % of Iran’s water re
Data Loading...