International Journal of
Physical Sciences

  • Abbreviation: Int. J. Phys. Sci.
  • Language: English
  • ISSN: 1992-1950
  • DOI: 10.5897/IJPS
  • Start Year: 2006
  • Published Articles: 2557

Full Length Research Paper

Specifications of thermal waters and their classification on the base of neural network method: Examples from Simav geothermal area, Western Turkey

Ali Ferhat Bayram1, Seyfettin Sinan Gültekin and Ali Rıza SöÄŸüt*
1Department of Geology Engineering, Faculty of Engineering and Architecture, Selcuk University, Konya (TR-42003), Turkey. 2Department of Electrical and Electronic Engineering, Faculty of Engineering and Architecture, Selcuk University, Konya (TR-42003), Turkey. 3Department of Geology Engineering, Faculty of Engineering and Architecture, Selcuk University, Konya (TR-42003), Turkey.
Email: [email protected]

  •  Accepted: 22 December 2010
  •  Published: 04 January 2011


Western Turkey is one of the best known geothermal fields in Turkey. There are numerous geothermal energy plants (for example Kızıldere, Nazilli, Hıdırbeyli, Balçova, Tuzla) in Aegean region, Western Turkey. Simav geothermal field is located within the Aegean Graben System in Western Anatolia. Rock units in the study area are mainly the formation of Menderes Massive. The Simav geothermal waters were divided into four types: (1) Eynal, (2) Çitgöl, (3) geothermal water and (4) cold water. In this study, we aimed to introduce a method for classifying waters in the study area using some parameters such as temperature, pH, electrical conductivity and major ions by means of Artificial Neural Network (ANN) method. The data at hand obtained from wells indicate that the drilled water can be used for drinking and irrigation, the data also reveals that the ground water flows towards the desiccated lake. The cold water analysis gave high CO3+HCO3, Ca, Mg ion values, and low NH4, NO3, Fe, NO2, Al and Mn ion values. On the other hand, the hot water analysis indicate that a cation trend of Na+K>Ca>Mg and an anion trend of HCO3+CO3>SO4>Cl. While preparing the training data set in ANN method, for input, T (°C), EC (mS), pH, Na (mg/l), K (mg/l), Ca (mg/l), Mg (mg/l), CO3 (mg/l), HCO3 (mg/l), Cl (mg/l) and SO4 (mg/l) values of 50 water samples from the study area were used. Four output values were used. In each output value, the known water was represented by 1 and others by 0. A test data set of 15 samples in which the T, EC, pH, Na, K, Ca, Mg, CO3, HCO3, Cl and SO4 values are known but their group are unknown was prepared. And these input values were run in ANN model in order to see how the waters were grouped.  The advantages of artificial neural networks can be exploited to solve this problem. The most common ANN architecture is Multilayered Perceptrons, which was used in this study. For this solution, the first artificial neural network model using Extended Delta-Bar-Delta (EDBD) algorithm has been successfully implemented. Mean Square Error result of these model obtained by EDBD algorithm is 1.3x10–3. These results show that the group in which the waters in the study area fall can be determined with high accuracy by using some parameters of water such as the ion content of water.


Key words: Geothermal waters, chemistry, hydrology, Artificial Neural Network (ANN), Simav, Turkey.