Modeling Groundwater Quality Parameters Using Hybrid Neuro-Fuzzy Methods

Ozgur Kisi (), Armin Azad (), Hamed Kashi (), Amir Saeedian (), Seyed Ali Asghar Hashemi () and Salar Ghorbani ()
Additional contact information
Ozgur Kisi: Ilia State University
Armin Azad: Semnan University
Hamed Kashi: Technology University of Munich
Amir Saeedian: Semnan University
Seyed Ali Asghar Hashemi: Agriculture Research and Education Organization - Natural Resources Research Center of Semnan Province
Salar Ghorbani: Semnan University

Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), 2019, vol. 33, issue 2, No 24, 847-861

Abstract: Abstract In this study, the application of four evolutionary algorithms, continuous genetic algorithm (CGA), particle swarm optimization (PSO), ant colony optimization for continuous domains (ACOR), and differential evolution (DE) were considered for training and optimization of adaptive neuro-fuzzy inference system (ANFIS) to model groundwater quality variables. At first, using correlation and sensitivity analysis, the best inputs were selected to estimate electrical conductivity (EC), sodium adsorption ratio (SAR) and total hardness (TH). After that, the quality variables were modeled by simple ANFIS and the ANFIS trained by evolutionary algorithms. Finally, the models’ performances were evaluated using determination coefficient (R2), root mean square error (RMSE), and mean absolute percentage error (MAPE) and sensitivity analysis. Results indicated that: 1) All the suggested algorithms improved the ANFIS performance in the modeling of EC and TH. Also, in SAR, CGA and PSO had a better performance than existing algorithms of ANFIS. 2) CGA with the most appropriate results, was the best algorithm in improving ANFIS performance for modeling the groundwater quality variables such that the amounts of R2, RMSE, and MAPE were improved by 0.14, 35.4, and 0.59 for TH, by 0.13, 226 (μmho Cm−1), 2.16 for EC, and by 0.15, 690, and 19.04 for SAR, respectively. 3) Sensitivity analysis showed that the results obtained by correlation analysis was dependable and could be used as a primary step in choosing the best input data for prediction of groundwater quality variables.

Keywords: Ant colony optimization for continuous domains; Continuous genetic algorithm; Differential evolution; Partial swarm optimization; ANFIS; Groundwater quality variables (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
http://link.springer.com/10.1007/s11269-018-2147-6 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:waterr:v:33:y:2019:i:2:d:10.1007_s11269-018-2147-6

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11269

DOI: 10.1007/s11269-018-2147-6

Access Statistics for this article

Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA) is currently edited by G. Tsakiris

More articles in Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA) from Springer, European Water Resources Association (EWRA)
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().