Surface water quality prediction using data mining method (Case study: Rivers of northern side of Sahand Mountain)

Document Type : Research Article

Authors

1 Assistant Professor, Department of Water Engineering, University of Tabriz, Tabriz, Iran

2 Assistant Professor, Department of Water Engineering, Shahrekord University, Shahrekord, Iran

3 MSc MSc Student of Civil Engineering, Islamic Azad University of Maragheh, Maragheh, Iran

Abstract

Monitoring and assessment of surface water quality are very expensive and time consuming processes, thus finding cheap, simple and relatively exact methods which determine water quality class based on minimum parameters would be very useful. Decision tree as one of the data mining techniques classifies data sets based on a tree structure. In this study, the decision tree method was used to classify water quality in some hydrometric stations located at northern side of Sahand Mountain, including Bostanabad, PoleSenikh, Lighvan and Vanyar. The water quality classes were defined based on if-then rules. For every considered river, the discharge and 12 hydrochemical parameters, including Ca2+, Mg2+, Cl-, HCO3-, Na%, pH, SO42-, total anions, total cations, total dissolved solids (TDS), sodium adsorption ratio (SAR) and Electrical conductivity (EC) were collected and used for developing decision tree model. The results showed that the decision tree model could evaluate water quality class with high accuracy based on only four parameters: EC, pH, SAR and Na+. Moreover, the error of developed models in testing phase for Bostanabad, Vanyar, PoleSenikh and Lighvan stations were 3.4, 8.1, 22.9 and 1.6%, respectively.

Keywords

Main Subjects


منابع
[1]. U.S. Salinity Laboratory Staff, Diagnosis and improvement of saline and alkali soils: U.S. Dept. Agric. Handbook; 1954. No.60, 160 p.
[2]. Mirabbasi R, Mazloumzadeh SM, Rahnama MB. Evaluation of irrigation water quality using fuzzy logic, Research Journal of Environmental Sciences, 2008; 2(5): 340-352.
[3]. Santos MF, Cortez P, Quintela H, Neves J, Vicente H & Arteiro J. Ecological Mining - A Case Study on Dam Water Quality. In A. Zanasi, C. Brebbia and N. Ebecken (Eds.), Data Mining VI - Data Mining, Text Mining and their Business Applications, WIT Transactions of Information and Communication Technologies 35, 523-531, WIT Press, ISBN:1-84564-017-9, ISSN:1746-4463; 2005.
[4]. Yahya SM, Rahman AU, Abbasi HN. Assessment of seasonal and polluting effects on the quality of river water by using regression analysis: A case study of River Indus in province of Sindh, Pakistan. International Journal of Environmental Protection. 2012; 2(2): 10-16.
[5]. Rahmani AR, Samadi MT, Heydari M. Water quality assessment of Hamadan-Bahar Plain rivers using Wilcox diagram fir irrigation, Journal of Agricultural Research, 2007; 8(1b): 27-35. [Persian]
[6]. Goljan F, Karbasi AR, Hajizadeh Zaler N, Nabi Bidhendi GR. Water quality of Nour City rivers, Journal of Water Sciences Research, 2009; 1(1): 35-48. [Persian]
[7]. Olyaie E, Banejad H, Samadi MT, Rahmani AR, Saghi MH, Performance Evaluation of Artificial Neural Networks for Predicting Rivers Water Quality Indices (BOD and DO) in Hamadan Morad Beik River, Water and Soil Science, 2010; 20(3): 199-210. [Persian]
[8]. Hajian Nejad M, Rahsepar AR, Measurement and Simulation of Dissolved Oxygen in Zayande Rood River, Journal of Health System Research, 2010; 6(2): 821-828. [Persian]
[9]. Salajegheh A, Razavizadeh S, Khorasani N, Hamidifar M, Salajegheh S, Land use Changes and its Effects on Water Quality (Case study: Karkheh Watershed), 2011; 58:81-86. [Persian]
[10]. Saghebian SM, Sattari MT, Mirabbasi R, Pal M. Ground water quality classification by decision tree method in Ardebil region, Iran. Arabian Journal of Geosciences. 2013; 7(11): 4767-4777.
[11]. Hasani Z, Mirabbasi Najafabadi R, Ghasemi AR. Prediction of groundwater quality in Khanmirza plain using decision tree method, Hydrogeology. 2016; 1(3): 15-30. [Persian]
[12]. Norouzi H, Nadiri A, Asghari Moghaddam A. Investigation of Malikan Plain Groundwater’s Pollution to Arsenic, Ecohydrology. 2016; 3(2): 151-166. [Persian]
[13]. Witten IH, Frank E. Data Mining: Practical Machine Learning Tools and Techniques, second edition, Elsevier: San Francisco. ISBN 0-12-088407-0; 2005.
[14]. Quinlan JR. C4.5 Programs for machine learning, Morgan, Kaufmann, 1993; San Mateo, California
[15]. Quinlan JR. Data mining tools See5 and C5.0 [cited Feb 2012]. Available from http://www.rulequest.com/see5-info.html. 2000.
 
Volume 4, Issue 2
June 2017
Pages 407-419
  • Receive Date: 25 December 2016
  • Revise Date: 12 March 2017
  • Accept Date: 15 March 2017
  • First Publish Date: 22 June 2017
  • Publish Date: 22 June 2017