Iranian Journal of

Background and Objective: Determination of quality parameters of drinkable water is important, especially in developing countries, to increase the productivity and better management and planning of water resources. The aim of current study was to apply CART decision tree data mining technique to determine the most effective factors on drinkable water quality in Kazeroon plain, located west of Fars province, Iran.
Materials and Methods: Qualitative parameters of 60 drinkable wells such as SAR, Na, Cl, SO₄, TH, TDS, pH, NO₃, CaCO₃, HCO₃, Ca, Mg, K and EC were taken in the study area. The most effective factors on quality of drinkable water were determined with 90% accuracy, using CART decision tree data mining technique in Clementine 12.0 software.
Results: The results showed that total dissolved solids (TDS) and calcium content (Ca) had the highest impact on quality of drinking water. Therefore, when the TDS of water in this plain is equal or less than 495 mg/L and the calcium content is equal or less than 6.150 meq/L, the water is suitable for drinking.
Conclusion: The TDS and Ca content were the most effective parameters on the quality of drinkable water in this plain, due to its geological formation and the existence of CaCO₃ in its structure. The water purification, reduction of soluble material concentration, and monitoring of wells in this plain are recommended.
 

Background and Objective: In the present study, EC and TDS quality parameters of Karun River were modeled using data-mining algorithms including LSSVM, ANFIS, and ANN, at Mollasani, Ahvaz and Farsiat hydrometric stations.
Material and Methods: Eight different inputs including the combination of Cl^-1, Ca⁺², Na⁺¹, Mg⁺², K⁺¹, CO₃^2-, HCO₃, and SO₄^2- with discharge flow (Q) were selected as non-random and random calibration inputs for these algorithms. Then, in order to guarantee the accuracy of the results, the simulation was performed by random calibration and the results of the two methods were compared. In the next step, the EC and TDS parameters were modeled based on the four parameters of Na⁺¹, Cl^-1, Ca⁺², and Q and a lag time of zero to three months.
Results: Modeling results indicated that Na⁺¹, Cl^-1, and Ca⁺² have the highest influence on modeling of EC and TDS parameters. The LSSVM algorithm was the most accurate in modeling EC and TDS parameters. Among the studied stations, the highest precision for EC and TDS modeling belongs to Ahvaz and Mollasani station, which has 16% and 36% higher coefficient of determination. LSSVM has highest accuracy in modeling the oscillation and peak EC and TDS parameters in during times.
Conclusion: The methods and models applied in the present study especially the LSSVM algorithm, can be a useful decision-making tool for predicting and qualitative management of rivers, including rivers in the Karun catchment area. The results of modeling the quality parameters of the rivers were reliable and usable by using both non-random and random calibration methods. However, the accuracy of the random calibration method was slightly higher.