Predicting wastewater treatment plant quality parameters using a novel hybrid linear-nonlinear methodology

Khadije Lotfi, Hossein Bonakdari, Isa Ebtehaj, Farouk Mjalli, Mohammad Zeynoddin, Robert Delatolla, Bahram Gharabaghi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Biochemical oxygen demand (BOD), chemical oxygen demand (COD), total dissolved solids (TDS) and total suspended solids (TSS) are the most commonly regulated wastewater effluent parameters. The measurement and prediction of these parameters are essential for assessing the performance and upgrade of wastewater treatment facilities. In this study, a new methodology, combining a linear stochastic model (ARIMA) and nonlinear outlier robust extreme learning machine technique (ORELM) with various preprocesses, is presented to model the quality parameters of effluent wastewater (ARIMA-ORELM). For each of the studied parameters, 144 different (144 × 8 models) linear models (ARIMA) are presented, with the superior model of each parameter being selected based on statistical indices. Moreover, 48 nonlinear models (ORELM) and 48 hybrid models (ARIMA-ORELM) were considered. The use of linear and nonlinear approaches to model the linear and nonlinear terms (respectively) of each time series in the hybrid model increased the efficiency and accuracy of the predictions for all of the time series. The influent wastewater nonlinear TSS model and the effluent COD and BOD models attained the best performance with a high correlation coefficient of 0.95. The use of hybrid models improved the prediction capability of all quality parameters with the best performance being achieved for the effluent BOD model (R 2 = 0.99).

Original languageEnglish
Pages (from-to)463-474
Number of pages12
JournalJournal of Environmental Management
Volume240
DOIs
Publication statusPublished - Jun 15 2019

Fingerprint

Wastewater treatment
methodology
outlier
Learning systems
Biochemical oxygen demand
Effluents
biochemical oxygen demand
effluent
Wastewater
Chemical oxygen demand
wastewater
chemical oxygen demand
wastewater treatment plant
parameter
Time series
prediction
time series
Stochastic models

Keywords

  • ARIMA
  • Biochemical oxygen demand (BOD)
  • Chemical oxygen demand (COD)
  • ORELM
  • Total dissolved solids (TDS)
  • Total suspended solids (TSS)
  • Wastewater

ASJC Scopus subject areas

  • Environmental Engineering
  • Waste Management and Disposal
  • Management, Monitoring, Policy and Law

Cite this

Predicting wastewater treatment plant quality parameters using a novel hybrid linear-nonlinear methodology. / Lotfi, Khadije; Bonakdari, Hossein; Ebtehaj, Isa; Mjalli, Farouk; Zeynoddin, Mohammad; Delatolla, Robert; Gharabaghi, Bahram.

In: Journal of Environmental Management, Vol. 240, 15.06.2019, p. 463-474.

Research output: Contribution to journalArticle

Lotfi, Khadije ; Bonakdari, Hossein ; Ebtehaj, Isa ; Mjalli, Farouk ; Zeynoddin, Mohammad ; Delatolla, Robert ; Gharabaghi, Bahram. / Predicting wastewater treatment plant quality parameters using a novel hybrid linear-nonlinear methodology. In: Journal of Environmental Management. 2019 ; Vol. 240. pp. 463-474.
@article{5b6b99d2209747e281320a47a3aae98d,
title = "Predicting wastewater treatment plant quality parameters using a novel hybrid linear-nonlinear methodology",
abstract = "Biochemical oxygen demand (BOD), chemical oxygen demand (COD), total dissolved solids (TDS) and total suspended solids (TSS) are the most commonly regulated wastewater effluent parameters. The measurement and prediction of these parameters are essential for assessing the performance and upgrade of wastewater treatment facilities. In this study, a new methodology, combining a linear stochastic model (ARIMA) and nonlinear outlier robust extreme learning machine technique (ORELM) with various preprocesses, is presented to model the quality parameters of effluent wastewater (ARIMA-ORELM). For each of the studied parameters, 144 different (144 × 8 models) linear models (ARIMA) are presented, with the superior model of each parameter being selected based on statistical indices. Moreover, 48 nonlinear models (ORELM) and 48 hybrid models (ARIMA-ORELM) were considered. The use of linear and nonlinear approaches to model the linear and nonlinear terms (respectively) of each time series in the hybrid model increased the efficiency and accuracy of the predictions for all of the time series. The influent wastewater nonlinear TSS model and the effluent COD and BOD models attained the best performance with a high correlation coefficient of 0.95. The use of hybrid models improved the prediction capability of all quality parameters with the best performance being achieved for the effluent BOD model (R 2 = 0.99).",
keywords = "ARIMA, Biochemical oxygen demand (BOD), Chemical oxygen demand (COD), ORELM, Total dissolved solids (TDS), Total suspended solids (TSS), Wastewater",
author = "Khadije Lotfi and Hossein Bonakdari and Isa Ebtehaj and Farouk Mjalli and Mohammad Zeynoddin and Robert Delatolla and Bahram Gharabaghi",
year = "2019",
month = "6",
day = "15",
doi = "10.1016/j.jenvman.2019.03.137",
language = "English",
volume = "240",
pages = "463--474",
journal = "Journal of Environmental Management",
issn = "0301-4797",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Predicting wastewater treatment plant quality parameters using a novel hybrid linear-nonlinear methodology

AU - Lotfi, Khadije

AU - Bonakdari, Hossein

AU - Ebtehaj, Isa

AU - Mjalli, Farouk

AU - Zeynoddin, Mohammad

AU - Delatolla, Robert

AU - Gharabaghi, Bahram

PY - 2019/6/15

Y1 - 2019/6/15

N2 - Biochemical oxygen demand (BOD), chemical oxygen demand (COD), total dissolved solids (TDS) and total suspended solids (TSS) are the most commonly regulated wastewater effluent parameters. The measurement and prediction of these parameters are essential for assessing the performance and upgrade of wastewater treatment facilities. In this study, a new methodology, combining a linear stochastic model (ARIMA) and nonlinear outlier robust extreme learning machine technique (ORELM) with various preprocesses, is presented to model the quality parameters of effluent wastewater (ARIMA-ORELM). For each of the studied parameters, 144 different (144 × 8 models) linear models (ARIMA) are presented, with the superior model of each parameter being selected based on statistical indices. Moreover, 48 nonlinear models (ORELM) and 48 hybrid models (ARIMA-ORELM) were considered. The use of linear and nonlinear approaches to model the linear and nonlinear terms (respectively) of each time series in the hybrid model increased the efficiency and accuracy of the predictions for all of the time series. The influent wastewater nonlinear TSS model and the effluent COD and BOD models attained the best performance with a high correlation coefficient of 0.95. The use of hybrid models improved the prediction capability of all quality parameters with the best performance being achieved for the effluent BOD model (R 2 = 0.99).

AB - Biochemical oxygen demand (BOD), chemical oxygen demand (COD), total dissolved solids (TDS) and total suspended solids (TSS) are the most commonly regulated wastewater effluent parameters. The measurement and prediction of these parameters are essential for assessing the performance and upgrade of wastewater treatment facilities. In this study, a new methodology, combining a linear stochastic model (ARIMA) and nonlinear outlier robust extreme learning machine technique (ORELM) with various preprocesses, is presented to model the quality parameters of effluent wastewater (ARIMA-ORELM). For each of the studied parameters, 144 different (144 × 8 models) linear models (ARIMA) are presented, with the superior model of each parameter being selected based on statistical indices. Moreover, 48 nonlinear models (ORELM) and 48 hybrid models (ARIMA-ORELM) were considered. The use of linear and nonlinear approaches to model the linear and nonlinear terms (respectively) of each time series in the hybrid model increased the efficiency and accuracy of the predictions for all of the time series. The influent wastewater nonlinear TSS model and the effluent COD and BOD models attained the best performance with a high correlation coefficient of 0.95. The use of hybrid models improved the prediction capability of all quality parameters with the best performance being achieved for the effluent BOD model (R 2 = 0.99).

KW - ARIMA

KW - Biochemical oxygen demand (BOD)

KW - Chemical oxygen demand (COD)

KW - ORELM

KW - Total dissolved solids (TDS)

KW - Total suspended solids (TSS)

KW - Wastewater

UR - http://www.scopus.com/inward/record.url?scp=85063779137&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063779137&partnerID=8YFLogxK

U2 - 10.1016/j.jenvman.2019.03.137

DO - 10.1016/j.jenvman.2019.03.137

M3 - Article

VL - 240

SP - 463

EP - 474

JO - Journal of Environmental Management

JF - Journal of Environmental Management

SN - 0301-4797

ER -