Journal of New Approaches in Water Engineering and Environment
Scientific Journal

Prediction of groundwater quality parameters in Golestan province using response surface method, decision tree and neural network

Document Type : Original Article

Authors

omolbani Mohammadrezapour 1
Behrooz keshtegar 2
ozgur Kisi 3

1 Department of water engineering, Faculty of water and soil, Gorgan University of Agricultural Resources and Natural Resourses, Gorgan, Iran.

2 Department of civil, Faculty of Engineering, University of Zabol, Zabol, Iran.

3 Department of Civil Engineering, Technical University of Lübeck, Lübeck, Germany

https://doi.org/10.22034/nawee.2025.504716.1136
Abstract
Groundwater quality is a main issue in most of the plains in Iran. Therefore, quality management and monitoring of water resources is of great importance. In this study, water quality parameters including sodium adsorption ratio (SAR), total soluble solids ratio (TDS) and electrical conductivity (EC) were predicted using artificial neural network (MLP), decision tree model (M5Tree), and response surface method (RSM). The quality data acquired from 96 observation wells located in Golestan province were used for model inputs are sodium, water pH, chloride, sulfate, calcium and magnesium. Models were evaluated utilizing three criteria of root mean square error (RMSE), detemination coefficient (R2) and mean absolute error (MAE) were used. Three different input combinations were considered to predict EC, SAR and TDS. The results of this study showed that the parameters Na and Cl have the greatest effect on the accuracy of the models. According to the results, the decision tree model (M5Tree) was found to have the highest accuracy in predicting EC followed by the RSM and ANN models. However, the RSM model has a higher efficiency than the other models in predicting the SAR and TDS. According to the obtained results, it can be said that the RSM in general predicts the groundwater quality parameters with relatively better accuracy.

Keywords

Groundwater quality
prediction
neural network
decision tree
response surface method
Adimalla, N., Ravi Manne, Y. Z., Panpan, X., Hui, Q. 2022. Evaluation of groundwater quality and its suitability for drinking purposes in semi-arid region of Southern India: An application of GIS. Geocarto International, 25: 1–12.
Guler, C., Kurt, M., Alpasalan, M., Akbulut, C. 2012. Assessment of the impact of anthropogenic activities on the groundwater hydrology and chemistry in Tarsus coastal plain (Mersin, SE Turkey) using fuzzy clustering, multivariate statistics and GIS techniques. Journal of Hydrology, 435–451.
Haykin, S. 1999. Neural networks: A comprehensive foundation. Prentice-Hall, Upper Saddle River, NJ.
Jalalkamali, A., Jalalkamali, N. 2018. Adaptive network-based fuzzy inference system-genetic algorithm models for prediction groundwater quality indices: A GIS-based analysis. Journal of AI and Data Mining, 6: 439–445.
Heshmatpour, A., & Sajadi, S. J. 2024. A survey on spatial and temporal variations of agricultural water quality in Gorganrood River using fuzzy rules. Journal of New Approaches in Water Engineering and Environment, 3(1): 1–20.
Kisi, O., Azad, A., Kashi, H., Saeedian, A., Hashemi, S. A., Ghorbani, S. 2019. Modeling groundwater quality parameters using hybrid neuro-fuzzy methods. Water Resources Management, 33: 847–861.
Kumru, M. N., Bakac, M. K. 2003. R-mode factor analyses applied to the distribution of element in soils from the Aydin basin, Turkey. Journal of Geological Exploration, 77: 81–91.
Marashi, S. E., Solaimani, K., Habibnejad, M., Jahanshahi, A. 2023. Investigating the quality of groundwater using statistical techniques and geographic information system in Haraz Plain. Journal of Irrigation and Water Engineering, 13(13): 248–268.
Mohammadrezapour, O., Kisi, O., Purahmadi, F. 2018. Fuzzy c-means and K-means clustering with genetic algorithm for identification of homogeneous regions of groundwater quality. Neural Computing and Applications, 32(8): 3763–3775.
Montgomery, D. C. 2001. Design and analysis of experiments. John Wiley and Sons, New York.
Najah, A., Elshafie, A., Karim, O. A., Jaffar, O. 2009. Prediction of Johor River water quality parameters using artificial neural networks. European Journal of Scientific Research, 28: 422–435.
Pourjabbar, A., Sarbu, C., Kostarelos, K., Einax, J., Buchel, G. 2014. Fuzzy hierarchical cross-clustering of data from abandoned mine site contaminated with heavy metals. ScienceDirect, 122–133.
Rizzo, D. M., Mouser, J. M. 2000. Evaluation of geostatistics for combined hydrochemistry and microbial community fingerprinting at a waste disposal site.
Sattari, M. T., Pal, M., Apaydin, H. 2013. M5 Model Tree application in daily river flow forecasting in Sohu Stream, Turkey. Water Resources, 4(3): 233–242.
Sivasankar, V., Kameswari, M., Msagati, T. A. M., Venkatarapathy, M., & Senthil Kumar, M. 2013. Fuzzy set approach—A tool to cluster groundwater quality parameters at Rameswaram, South India. Journal of Water Resources and Ocean Science, 33–39.
Thompson, D. 1982. Response surface experimentation. Journal of Food Processing and Preservation, 6: 155–188.
Vafakhah, M. 2012. Application of artificial neural networks and adaptive neuro-fuzzy inference system models to short-term streamflow forecasting. Canadian Journal of Civil Engineering, 39(4): 402–414.
Yesilnacar, M. I., Sahinkaya, E., Naz, M., Ozkaya, B. 2008. Neural network prediction of nitrate in groundwater of Harran Plain, Turkey. Environmental Geology, 56: 19–25.
Solgi, E., Beigmohammadi, F., Ahmadvand, R., Baser, S. 2025. Nitrate risk assessment in drinking water in different areas of Malayer city. Journal of New Approaches in Water Engineering and Environment.
 
 
Journal of New Approaches in Water Engineering and Environment
Volume 4, Issue 2
Special Issue: Guest Editor: Prof. Ozgur Kisi
September 2025
Pages 37-57

Home

Guide for Authors

Submit Manuscript

Reviewers

Contact Us