Prediction of groundwater quality parameter in the Tabriz plain, Iran using soft computing methods
Authors:
- 29 August 2019
- journal article
- research article
- Published by IWA Publishing in Journal of Water Supply: Research and Technology—AQUA
- Vol. 68 (7) , 573-584
Abstract
Aquifers are one of the largest available freshwater resources. In this paper, total dissolved solids (TDS) of the groundwater aquifer in Tabriz plain is estimated by groundwater physicochemical parameters including Na, HCO3, Ca, Mg, and SO4 in the eastern region of Urmia Lake. For this purpose, four soft computing approaches, namely, multilayer perceptron (MLP), adaptive neuro-fuzzy inference system (ANFIS), support vector machine (SVM), and gene expression programming (GEP) were used to predict TDS for a period of ten years (2002–2012). Data were collected from the East Azerbaijan Regional Water Organization, which totaled 1,742 samples. In the application, of the whole data set, 70% (1,220 samples) was used for training and 30% (522 samples) for testing. In the following, the correlation coefficient (R), root mean square error (RMSE), and mean absolute error (MAE) statistics were used for evaluating the accuracy of the models. According to the results, MLP, ANFIS, SVM, and GEP models could be employed successfully in estimating TDS alterations. A comparison was made between these soft computing approaches that corroborated the superiority of the GEP model over MLP, SVM, and ANFIS models with RMSE = 58.93, R = 0.998, and MAE = 5.21.Keywords
This publication has 21 references indexed in Scilit:
- Forecasting Water Level Fluctuations of Urmieh Lake Using Gene Expression Programming and Adaptive Neuro-Fuzzy Inference SystemThe International Journal of Ocean and Climate Systems, 2012
- Application of Artificial Neural Network to Predict TDS in Talkheh Rud RiverJournal of Irrigation and Drainage Engineering, 2012
- Comparison of three artificial intelligence techniques for discharge routingJournal of Hydrology, 2011
- Uncertainty analysis for the forecast of lake level fluctuations using ensembles of ANN and ANFIS modelsExpert Systems with Applications, 2011
- Estimation of Mean Annual Flood in Indian Catchments Using Backpropagation Neural Network and M5 Model TreeWater Resources Management, 2009
- An ANN‐based model for spatiotemporal groundwater level forecastingHydrological Processes, 2008
- Data mining in hydrologyHydrological Processes, 2005
- Support-vector networksMachine Learning, 1995
- Genetic programming as a means for programming computers by natural selectionStatistics and Computing, 1994
- Fuzzy setsInformation and Control, 1965