Combining principal component regression and artificial neural networks for more accurate predictions of ground-level ozone

Research output: Contribution to journalArticle

136 Citations (Scopus)

Abstract

This work encompasses ozone modeling in the lower atmosphere. Data on seven environmental pollutant concentrations (CH4, NMHC, CO, CO2, NO, NO2, and SO2) and five meteorological variables (wind speed, wind direction, air temperature, relative humidity, and solar radiation) were used to develop models to predict the concentration of ozone in Kuwait's lower atmosphere. The models were developed by using summer air quality and meteorological data from a typical urban site when ozone concentration levels were the highest. The site was selected to represent a typical residential area with high traffic influences. The combined method, which is based on using both multiple regression combined with principal component analysis (PCR) and artificial neural network (ANN) modeling, was used to predict ozone concentration levels in the lower atmosphere. This combined approach was used to improve the prediction accuracy of ozone. The predictions of the models were found to be consistent with observed values. The R2 values were 0.965, 0.986, and 0.995 for PCR, ANN, and the combined model prediction, respectively. It was found that combining the predictions from the PCR and ANN models reduced the root mean square errors (RMSE) of ozone concentrations. It is clear that combining predictions generated by different methods could improve the accuracy and provide a prediction that is superior to a single model prediction.

Original languageEnglish
Pages (from-to)396-403
Number of pages8
JournalEnvironmental Modelling and Software
Volume23
Issue number4
DOIs
Publication statusPublished - Apr 2008

Fingerprint

artificial neural network
Ozone
ozone
Neural networks
prediction
atmosphere
urban site
Solar radiation
Air quality
Mean square error
Principal component analysis
wind direction
modeling
multiple regression
relative humidity
solar radiation
Atmospheric humidity
principal component analysis
air quality
air temperature

Keywords

  • Artificial neural network
  • Combining forecast
  • Principal component regression
  • Tropospheric ozone concentration

ASJC Scopus subject areas

  • Ecological Modelling
  • Environmental Science(all)

Cite this

@article{977de1d40bb94bac9fdd7b9fe3324882,
title = "Combining principal component regression and artificial neural networks for more accurate predictions of ground-level ozone",
abstract = "This work encompasses ozone modeling in the lower atmosphere. Data on seven environmental pollutant concentrations (CH4, NMHC, CO, CO2, NO, NO2, and SO2) and five meteorological variables (wind speed, wind direction, air temperature, relative humidity, and solar radiation) were used to develop models to predict the concentration of ozone in Kuwait's lower atmosphere. The models were developed by using summer air quality and meteorological data from a typical urban site when ozone concentration levels were the highest. The site was selected to represent a typical residential area with high traffic influences. The combined method, which is based on using both multiple regression combined with principal component analysis (PCR) and artificial neural network (ANN) modeling, was used to predict ozone concentration levels in the lower atmosphere. This combined approach was used to improve the prediction accuracy of ozone. The predictions of the models were found to be consistent with observed values. The R2 values were 0.965, 0.986, and 0.995 for PCR, ANN, and the combined model prediction, respectively. It was found that combining the predictions from the PCR and ANN models reduced the root mean square errors (RMSE) of ozone concentrations. It is clear that combining predictions generated by different methods could improve the accuracy and provide a prediction that is superior to a single model prediction.",
keywords = "Artificial neural network, Combining forecast, Principal component regression, Tropospheric ozone concentration",
author = "Al-Alawi, {Saleh M.} and Abdul-Wahab, {Sabah A.} and Bakheit, {Charles S.}",
year = "2008",
month = "4",
doi = "10.1016/j.envsoft.2006.08.007",
language = "English",
volume = "23",
pages = "396--403",
journal = "Environmental Modelling and Software",
issn = "1364-8152",
publisher = "Elsevier BV",
number = "4",

}

TY - JOUR

T1 - Combining principal component regression and artificial neural networks for more accurate predictions of ground-level ozone

AU - Al-Alawi, Saleh M.

AU - Abdul-Wahab, Sabah A.

AU - Bakheit, Charles S.

PY - 2008/4

Y1 - 2008/4

N2 - This work encompasses ozone modeling in the lower atmosphere. Data on seven environmental pollutant concentrations (CH4, NMHC, CO, CO2, NO, NO2, and SO2) and five meteorological variables (wind speed, wind direction, air temperature, relative humidity, and solar radiation) were used to develop models to predict the concentration of ozone in Kuwait's lower atmosphere. The models were developed by using summer air quality and meteorological data from a typical urban site when ozone concentration levels were the highest. The site was selected to represent a typical residential area with high traffic influences. The combined method, which is based on using both multiple regression combined with principal component analysis (PCR) and artificial neural network (ANN) modeling, was used to predict ozone concentration levels in the lower atmosphere. This combined approach was used to improve the prediction accuracy of ozone. The predictions of the models were found to be consistent with observed values. The R2 values were 0.965, 0.986, and 0.995 for PCR, ANN, and the combined model prediction, respectively. It was found that combining the predictions from the PCR and ANN models reduced the root mean square errors (RMSE) of ozone concentrations. It is clear that combining predictions generated by different methods could improve the accuracy and provide a prediction that is superior to a single model prediction.

AB - This work encompasses ozone modeling in the lower atmosphere. Data on seven environmental pollutant concentrations (CH4, NMHC, CO, CO2, NO, NO2, and SO2) and five meteorological variables (wind speed, wind direction, air temperature, relative humidity, and solar radiation) were used to develop models to predict the concentration of ozone in Kuwait's lower atmosphere. The models were developed by using summer air quality and meteorological data from a typical urban site when ozone concentration levels were the highest. The site was selected to represent a typical residential area with high traffic influences. The combined method, which is based on using both multiple regression combined with principal component analysis (PCR) and artificial neural network (ANN) modeling, was used to predict ozone concentration levels in the lower atmosphere. This combined approach was used to improve the prediction accuracy of ozone. The predictions of the models were found to be consistent with observed values. The R2 values were 0.965, 0.986, and 0.995 for PCR, ANN, and the combined model prediction, respectively. It was found that combining the predictions from the PCR and ANN models reduced the root mean square errors (RMSE) of ozone concentrations. It is clear that combining predictions generated by different methods could improve the accuracy and provide a prediction that is superior to a single model prediction.

KW - Artificial neural network

KW - Combining forecast

KW - Principal component regression

KW - Tropospheric ozone concentration

UR - http://www.scopus.com/inward/record.url?scp=36148953966&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36148953966&partnerID=8YFLogxK

U2 - 10.1016/j.envsoft.2006.08.007

DO - 10.1016/j.envsoft.2006.08.007

M3 - Article

AN - SCOPUS:36148953966

VL - 23

SP - 396

EP - 403

JO - Environmental Modelling and Software

JF - Environmental Modelling and Software

SN - 1364-8152

IS - 4

ER -