Prediction and optimization of the Fenton process for the treatment of landfill leachate using an artificial neural network

Anita Maslahati Roudi, Shreeshivadasan Chelliapan, Wan Hanna Melini Wan Mohtar, Hesam Kamyab

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

In this study, the artificial neural network (ANN) technique was employed to derive an empirical model to predict and optimize landfill leachate treatment. The impacts of H2O2:Fe2+ ratio, Fe2+ concentration, pH and process reaction time were studied closely. The results showed that the highest and lowest predicted chemical oxygen demand (COD) removal efficiency were 78.9% and 9.3%, respectively. The overall prediction error using the developed ANN model was within -0.625%. The derived model was adequate in predicting responses (R2 = 0.9896 and prediction R2 = 0.6954). The initial pH, H2O2:Fe2+ ratio and Fe2+ concentrations had positive effects, whereas coagulation pH had no direct effect on COD removal. Optimized conditions under specified constraints were obtained at pH = 3, Fe2+ concentration = 781.25 mg/L, reaction time = 28.04 min and H2O2:Fe2+ ratio = 2. Under these optimized conditions, 100% COD removal was predicted. To confirm the accuracy of the predicted model and the reliability of the optimum combination, one additional experiment was carried out under optimum conditions. The experimental values were found to agree well with those predicted, with a mean COD removal efficiency of 97.83%.

Original languageEnglish
Article number595
JournalWater (Switzerland)
Volume10
Issue number5
DOIs
Publication statusPublished - 4 May 2018

Fingerprint

Chemical Water Pollutants
landfill leachates
Biological Oxygen Demand Analysis
Chemical oxygen demand
neural network
chemical oxygen demand
artificial neural network
neural networks
iron
Neural networks
prediction
demand
Leachate treatment
efficiency
Neural Networks (Computer)
Coagulation
coagulation
removal
landfill leachate
experiment

Keywords

  • Artificial neural network (ANN)
  • Chemical oxygen demand (COD)
  • Fenton treatment
  • Landfill leachate
  • Wastewater treatment

ASJC Scopus subject areas

  • Biochemistry
  • Geography, Planning and Development
  • Aquatic Science
  • Water Science and Technology

Cite this

Prediction and optimization of the Fenton process for the treatment of landfill leachate using an artificial neural network. / Roudi, Anita Maslahati; Chelliapan, Shreeshivadasan; Wan Mohtar, Wan Hanna Melini; Kamyab, Hesam.

In: Water (Switzerland), Vol. 10, No. 5, 595, 04.05.2018.

Research output: Contribution to journalArticle

@article{404a4fc946ed401d823098ede391aad7,
title = "Prediction and optimization of the Fenton process for the treatment of landfill leachate using an artificial neural network",
abstract = "In this study, the artificial neural network (ANN) technique was employed to derive an empirical model to predict and optimize landfill leachate treatment. The impacts of H2O2:Fe2+ ratio, Fe2+ concentration, pH and process reaction time were studied closely. The results showed that the highest and lowest predicted chemical oxygen demand (COD) removal efficiency were 78.9{\%} and 9.3{\%}, respectively. The overall prediction error using the developed ANN model was within -0.625{\%}. The derived model was adequate in predicting responses (R2 = 0.9896 and prediction R2 = 0.6954). The initial pH, H2O2:Fe2+ ratio and Fe2+ concentrations had positive effects, whereas coagulation pH had no direct effect on COD removal. Optimized conditions under specified constraints were obtained at pH = 3, Fe2+ concentration = 781.25 mg/L, reaction time = 28.04 min and H2O2:Fe2+ ratio = 2. Under these optimized conditions, 100{\%} COD removal was predicted. To confirm the accuracy of the predicted model and the reliability of the optimum combination, one additional experiment was carried out under optimum conditions. The experimental values were found to agree well with those predicted, with a mean COD removal efficiency of 97.83{\%}.",
keywords = "Artificial neural network (ANN), Chemical oxygen demand (COD), Fenton treatment, Landfill leachate, Wastewater treatment",
author = "Roudi, {Anita Maslahati} and Shreeshivadasan Chelliapan and {Wan Mohtar}, {Wan Hanna Melini} and Hesam Kamyab",
year = "2018",
month = "5",
day = "4",
doi = "10.3390/w10050595",
language = "English",
volume = "10",
journal = "Water (Switzerland)",
issn = "2073-4441",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "5",

}

TY - JOUR

T1 - Prediction and optimization of the Fenton process for the treatment of landfill leachate using an artificial neural network

AU - Roudi, Anita Maslahati

AU - Chelliapan, Shreeshivadasan

AU - Wan Mohtar, Wan Hanna Melini

AU - Kamyab, Hesam

PY - 2018/5/4

Y1 - 2018/5/4

N2 - In this study, the artificial neural network (ANN) technique was employed to derive an empirical model to predict and optimize landfill leachate treatment. The impacts of H2O2:Fe2+ ratio, Fe2+ concentration, pH and process reaction time were studied closely. The results showed that the highest and lowest predicted chemical oxygen demand (COD) removal efficiency were 78.9% and 9.3%, respectively. The overall prediction error using the developed ANN model was within -0.625%. The derived model was adequate in predicting responses (R2 = 0.9896 and prediction R2 = 0.6954). The initial pH, H2O2:Fe2+ ratio and Fe2+ concentrations had positive effects, whereas coagulation pH had no direct effect on COD removal. Optimized conditions under specified constraints were obtained at pH = 3, Fe2+ concentration = 781.25 mg/L, reaction time = 28.04 min and H2O2:Fe2+ ratio = 2. Under these optimized conditions, 100% COD removal was predicted. To confirm the accuracy of the predicted model and the reliability of the optimum combination, one additional experiment was carried out under optimum conditions. The experimental values were found to agree well with those predicted, with a mean COD removal efficiency of 97.83%.

AB - In this study, the artificial neural network (ANN) technique was employed to derive an empirical model to predict and optimize landfill leachate treatment. The impacts of H2O2:Fe2+ ratio, Fe2+ concentration, pH and process reaction time were studied closely. The results showed that the highest and lowest predicted chemical oxygen demand (COD) removal efficiency were 78.9% and 9.3%, respectively. The overall prediction error using the developed ANN model was within -0.625%. The derived model was adequate in predicting responses (R2 = 0.9896 and prediction R2 = 0.6954). The initial pH, H2O2:Fe2+ ratio and Fe2+ concentrations had positive effects, whereas coagulation pH had no direct effect on COD removal. Optimized conditions under specified constraints were obtained at pH = 3, Fe2+ concentration = 781.25 mg/L, reaction time = 28.04 min and H2O2:Fe2+ ratio = 2. Under these optimized conditions, 100% COD removal was predicted. To confirm the accuracy of the predicted model and the reliability of the optimum combination, one additional experiment was carried out under optimum conditions. The experimental values were found to agree well with those predicted, with a mean COD removal efficiency of 97.83%.

KW - Artificial neural network (ANN)

KW - Chemical oxygen demand (COD)

KW - Fenton treatment

KW - Landfill leachate

KW - Wastewater treatment

UR - http://www.scopus.com/inward/record.url?scp=85046655666&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046655666&partnerID=8YFLogxK

U2 - 10.3390/w10050595

DO - 10.3390/w10050595

M3 - Article

VL - 10

JO - Water (Switzerland)

JF - Water (Switzerland)

SN - 2073-4441

IS - 5

M1 - 595

ER -