Forecasting of ozone pollution using artificial neural networks

Reem S. Ettouney, Farouq S. Mjalli, John G. Zaki, Mahmoud A. El-Rifai, Hisham M. Ettouney

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Purpose: The objective of this study is to develop and validate a neural-based modelling methodology applicable to site-specific short- and medium-term ozone concentration forecasting. A novel modelling technique utilizing two feed forward artificial neural networks (FFNN) is developed to improve the performance of time series predictions. Design/methodology/approach: Air pollution and meteorological data were collected for one year in two locations in Kuwait. The hourly averages of the data were processed to generate a covariance matrix and analyzed to generate the principal component method. A two-FFNN model is then used to predict the actual data. Findings: The newly developed model improves the prediction accuracy over the conventional method. Owing to the presence of noise and other minor disturbances in the data, shorter-range modelling gives better modelling results. Originality/value: A novel modelling technique is developed to predict the time series of zone concentration.

Original languageEnglish
Pages (from-to)668-683
Number of pages16
JournalManagement of Environmental Quality
Volume20
Issue number6
DOIs
Publication statusPublished - Jun 2009

Fingerprint

Ozone
artificial neural network
Pollution
ozone
Neural networks
Kuwait
pollution
Neural Networks (Computer)
Time series
Air Pollution
modeling
Noise
Covariance matrix
Air pollution
time series
methodology
prediction
atmospheric pollution
disturbance
matrix

Keywords

  • Forecasting
  • Industrial air pollutants
  • Kuwait
  • Neural nets
  • Ozone
  • Time series analysis

ASJC Scopus subject areas

  • Management, Monitoring, Policy and Law
  • Biochemistry, Genetics and Molecular Biology(all)

Cite this

Forecasting of ozone pollution using artificial neural networks. / Ettouney, Reem S.; Mjalli, Farouq S.; Zaki, John G.; El-Rifai, Mahmoud A.; Ettouney, Hisham M.

In: Management of Environmental Quality, Vol. 20, No. 6, 06.2009, p. 668-683.

Research output: Contribution to journalArticle

Ettouney, Reem S. ; Mjalli, Farouq S. ; Zaki, John G. ; El-Rifai, Mahmoud A. ; Ettouney, Hisham M. / Forecasting of ozone pollution using artificial neural networks. In: Management of Environmental Quality. 2009 ; Vol. 20, No. 6. pp. 668-683.
@article{7f656049add241c6a694b30abb862115,
title = "Forecasting of ozone pollution using artificial neural networks",
abstract = "Purpose: The objective of this study is to develop and validate a neural-based modelling methodology applicable to site-specific short- and medium-term ozone concentration forecasting. A novel modelling technique utilizing two feed forward artificial neural networks (FFNN) is developed to improve the performance of time series predictions. Design/methodology/approach: Air pollution and meteorological data were collected for one year in two locations in Kuwait. The hourly averages of the data were processed to generate a covariance matrix and analyzed to generate the principal component method. A two-FFNN model is then used to predict the actual data. Findings: The newly developed model improves the prediction accuracy over the conventional method. Owing to the presence of noise and other minor disturbances in the data, shorter-range modelling gives better modelling results. Originality/value: A novel modelling technique is developed to predict the time series of zone concentration.",
keywords = "Forecasting, Industrial air pollutants, Kuwait, Neural nets, Ozone, Time series analysis",
author = "Ettouney, {Reem S.} and Mjalli, {Farouq S.} and Zaki, {John G.} and El-Rifai, {Mahmoud A.} and Ettouney, {Hisham M.}",
year = "2009",
month = "6",
doi = "10.1108/14777830910990843",
language = "English",
volume = "20",
pages = "668--683",
journal = "Management of Environmental Quality",
issn = "1477-7835",
publisher = "Emerald Group Publishing Ltd.",
number = "6",

}

TY - JOUR

T1 - Forecasting of ozone pollution using artificial neural networks

AU - Ettouney, Reem S.

AU - Mjalli, Farouq S.

AU - Zaki, John G.

AU - El-Rifai, Mahmoud A.

AU - Ettouney, Hisham M.

PY - 2009/6

Y1 - 2009/6

N2 - Purpose: The objective of this study is to develop and validate a neural-based modelling methodology applicable to site-specific short- and medium-term ozone concentration forecasting. A novel modelling technique utilizing two feed forward artificial neural networks (FFNN) is developed to improve the performance of time series predictions. Design/methodology/approach: Air pollution and meteorological data were collected for one year in two locations in Kuwait. The hourly averages of the data were processed to generate a covariance matrix and analyzed to generate the principal component method. A two-FFNN model is then used to predict the actual data. Findings: The newly developed model improves the prediction accuracy over the conventional method. Owing to the presence of noise and other minor disturbances in the data, shorter-range modelling gives better modelling results. Originality/value: A novel modelling technique is developed to predict the time series of zone concentration.

AB - Purpose: The objective of this study is to develop and validate a neural-based modelling methodology applicable to site-specific short- and medium-term ozone concentration forecasting. A novel modelling technique utilizing two feed forward artificial neural networks (FFNN) is developed to improve the performance of time series predictions. Design/methodology/approach: Air pollution and meteorological data were collected for one year in two locations in Kuwait. The hourly averages of the data were processed to generate a covariance matrix and analyzed to generate the principal component method. A two-FFNN model is then used to predict the actual data. Findings: The newly developed model improves the prediction accuracy over the conventional method. Owing to the presence of noise and other minor disturbances in the data, shorter-range modelling gives better modelling results. Originality/value: A novel modelling technique is developed to predict the time series of zone concentration.

KW - Forecasting

KW - Industrial air pollutants

KW - Kuwait

KW - Neural nets

KW - Ozone

KW - Time series analysis

UR - http://www.scopus.com/inward/record.url?scp=70350322118&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350322118&partnerID=8YFLogxK

U2 - 10.1108/14777830910990843

DO - 10.1108/14777830910990843

M3 - Article

VL - 20

SP - 668

EP - 683

JO - Management of Environmental Quality

JF - Management of Environmental Quality

SN - 1477-7835

IS - 6

ER -