Welcome to the InfoSci Platform
Reference Hub6
Statistical Learning Methods for Classification and Prediction of Groundwater Quality Using a Small Data Record

Statistical Learning Methods for Classification and Prediction of Groundwater Quality Using a Small Data Record

Mohamad Sakizadeh, Hassan Rahmatinia
Copyright: © 2017 |Volume: 8 |Issue: 4 |Pages: 17
ISSN: 1947-3192|EISSN: 1947-3206|EISBN13: 9781522513926|DOI: 10.4018/IJAEIS.2017100103
Cite Article Cite Article

MLA

Sakizadeh, Mohamad, and Hassan Rahmatinia. "Statistical Learning Methods for Classification and Prediction of Groundwater Quality Using a Small Data Record." IJAEIS vol.8, no.4 2017: pp.37-53. http://doi.org/10.4018/IJAEIS.2017100103

APA

Sakizadeh, M. & Rahmatinia, H. (2017). Statistical Learning Methods for Classification and Prediction of Groundwater Quality Using a Small Data Record. International Journal of Agricultural and Environmental Information Systems (IJAEIS), 8(4), 37-53. http://doi.org/10.4018/IJAEIS.2017100103

Chicago

Sakizadeh, Mohamad, and Hassan Rahmatinia. "Statistical Learning Methods for Classification and Prediction of Groundwater Quality Using a Small Data Record," International Journal of Agricultural and Environmental Information Systems (IJAEIS) 8, no.4: 37-53. http://doi.org/10.4018/IJAEIS.2017100103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

The objective of this study was to consider the efficiency of support vector machine (SVM) and artificial neural network (ANN) for the classification and prediction of groundwater quality using a small data record in Malayer, Iran. For this purpose, 14 groundwater quality variables that had been collected from 27 groundwater sampling wells were used. Cluster analysis discriminated the total sampling stations into two groups. The classification was implemented by SVM using polynomial and RBF kernel methods. The respective sensitivity and specificity of this model were 0.89 and 0.80 while that of positive predictive value and negative predictive value were 0.89 and 0.86, respectively. The prediction of water quality index (WQI) was implemented using ANN. Despite the high correlation coefficient between the predicted and observed values of WQI(r = 0.90), the generalization ability of this model was low(r = 0.60) indicating the over-fitting of the model to the training data set.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.