Performance of ANFIS versus MLP-NN dissolved oxygen prediction models in water quality monitoring

A. Najah, A. El-Shafie, Othman A. Karim, Amr H. El-Shafie

Research output: Contribution to journalArticle

42 Citations (Scopus)

Abstract

We discuss the accuracy and performance of the adaptive neuro-fuzzy inference system (ANFIS) in training and prediction of dissolved oxygen (DO) concentrations. The model was used to analyze historical data generated through continuous monitoring of water quality parameters at several stations on the Johor River to predict DO concentrations. Four water quality parameters were selected for ANFIS modeling, including temperature, pH, nitrate (NO3) concentration, and ammoniacal nitrogen concentration (NH3-NL). Sensitivity analysis was performed to evaluate the effects of the input parameters. The inputs with the greatest effect were those related to oxygen content (NO3) or oxygen demand (NH3-NL). Temperature was the parameter with the least effect, whereas pH provided the lowest contribution to the proposed model. To evaluate the performance of the model, three statistical indices were used: the coefficient of determination (R 2), the mean absolute prediction error, and the correlation coefficient. The performance of the ANFIS model was compared with an artificial neural network model. The ANFIS model was capable of providing greater accuracy, particularly in the case of extreme events.

Original languageEnglish
Pages (from-to)1658-1670
Number of pages13
JournalEnvironmental Science and Pollution Research
Volume21
Issue number3
DOIs
Publication statusPublished - Feb 2014

Fingerprint

Water Quality
Fuzzy inference
Dissolved oxygen
Water quality
dissolved oxygen
Oxygen
water quality
Monitoring
monitoring
prediction
Temperature
Neural Networks (Computer)
Statistical Models
Rivers
Nitrates
pH effects
Nitrogen
extreme event
artificial neural network
Sensitivity analysis

Keywords

  • ANFIS
  • Dissolved oxygen
  • Johor River
  • Water quality prediction

ASJC Scopus subject areas

  • Environmental Chemistry
  • Health, Toxicology and Mutagenesis
  • Pollution

Cite this

Performance of ANFIS versus MLP-NN dissolved oxygen prediction models in water quality monitoring. / Najah, A.; El-Shafie, A.; A. Karim, Othman; El-Shafie, Amr H.

In: Environmental Science and Pollution Research, Vol. 21, No. 3, 02.2014, p. 1658-1670.

Research output: Contribution to journalArticle

@article{711ca18bcba94fbb86078caac94c8168,
title = "Performance of ANFIS versus MLP-NN dissolved oxygen prediction models in water quality monitoring",
abstract = "We discuss the accuracy and performance of the adaptive neuro-fuzzy inference system (ANFIS) in training and prediction of dissolved oxygen (DO) concentrations. The model was used to analyze historical data generated through continuous monitoring of water quality parameters at several stations on the Johor River to predict DO concentrations. Four water quality parameters were selected for ANFIS modeling, including temperature, pH, nitrate (NO3) concentration, and ammoniacal nitrogen concentration (NH3-NL). Sensitivity analysis was performed to evaluate the effects of the input parameters. The inputs with the greatest effect were those related to oxygen content (NO3) or oxygen demand (NH3-NL). Temperature was the parameter with the least effect, whereas pH provided the lowest contribution to the proposed model. To evaluate the performance of the model, three statistical indices were used: the coefficient of determination (R 2), the mean absolute prediction error, and the correlation coefficient. The performance of the ANFIS model was compared with an artificial neural network model. The ANFIS model was capable of providing greater accuracy, particularly in the case of extreme events.",
keywords = "ANFIS, Dissolved oxygen, Johor River, Water quality prediction",
author = "A. Najah and A. El-Shafie and {A. Karim}, Othman and El-Shafie, {Amr H.}",
year = "2014",
month = "2",
doi = "10.1007/s11356-013-2048-4",
language = "English",
volume = "21",
pages = "1658--1670",
journal = "Environmental Science and Pollution Research",
issn = "0944-1344",
publisher = "Springer Science + Business Media",
number = "3",

}

TY - JOUR

T1 - Performance of ANFIS versus MLP-NN dissolved oxygen prediction models in water quality monitoring

AU - Najah, A.

AU - El-Shafie, A.

AU - A. Karim, Othman

AU - El-Shafie, Amr H.

PY - 2014/2

Y1 - 2014/2

N2 - We discuss the accuracy and performance of the adaptive neuro-fuzzy inference system (ANFIS) in training and prediction of dissolved oxygen (DO) concentrations. The model was used to analyze historical data generated through continuous monitoring of water quality parameters at several stations on the Johor River to predict DO concentrations. Four water quality parameters were selected for ANFIS modeling, including temperature, pH, nitrate (NO3) concentration, and ammoniacal nitrogen concentration (NH3-NL). Sensitivity analysis was performed to evaluate the effects of the input parameters. The inputs with the greatest effect were those related to oxygen content (NO3) or oxygen demand (NH3-NL). Temperature was the parameter with the least effect, whereas pH provided the lowest contribution to the proposed model. To evaluate the performance of the model, three statistical indices were used: the coefficient of determination (R 2), the mean absolute prediction error, and the correlation coefficient. The performance of the ANFIS model was compared with an artificial neural network model. The ANFIS model was capable of providing greater accuracy, particularly in the case of extreme events.

AB - We discuss the accuracy and performance of the adaptive neuro-fuzzy inference system (ANFIS) in training and prediction of dissolved oxygen (DO) concentrations. The model was used to analyze historical data generated through continuous monitoring of water quality parameters at several stations on the Johor River to predict DO concentrations. Four water quality parameters were selected for ANFIS modeling, including temperature, pH, nitrate (NO3) concentration, and ammoniacal nitrogen concentration (NH3-NL). Sensitivity analysis was performed to evaluate the effects of the input parameters. The inputs with the greatest effect were those related to oxygen content (NO3) or oxygen demand (NH3-NL). Temperature was the parameter with the least effect, whereas pH provided the lowest contribution to the proposed model. To evaluate the performance of the model, three statistical indices were used: the coefficient of determination (R 2), the mean absolute prediction error, and the correlation coefficient. The performance of the ANFIS model was compared with an artificial neural network model. The ANFIS model was capable of providing greater accuracy, particularly in the case of extreme events.

KW - ANFIS

KW - Dissolved oxygen

KW - Johor River

KW - Water quality prediction

UR - http://www.scopus.com/inward/record.url?scp=84895075043&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84895075043&partnerID=8YFLogxK

U2 - 10.1007/s11356-013-2048-4

DO - 10.1007/s11356-013-2048-4

M3 - Article

C2 - 23949111

AN - SCOPUS:84895075043

VL - 21

SP - 1658

EP - 1670

JO - Environmental Science and Pollution Research

JF - Environmental Science and Pollution Research

SN - 0944-1344

IS - 3

ER -