Spatial and temporal air quality pattern recognition using environmetric techniques

A case study in Malaysia

Sharifah Norsukhairin Syed Abdul Mutalib, Hafizan Juahir, Azman Azid, Sharifah Mohd Sharif, Mohd Talib Latif, Ahmad Zaharin Aris, Sharifuddin M. Zain, Doreena Dominick

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

The objective of this study is to identify spatial and temporal patterns in the air quality at three selected Malaysian air monitoring stations based on an eleven-year database (January 2000-December 2010). Four statistical methods, Discriminant Analysis (DA), Hierarchical Agglomerative Cluster Analysis (HACA), Principal Component Analysis (PCA) and Artificial Neural Networks (ANNs), were selected to analyze the datasets of five air quality parameters, namely: SO 2, NO2, O3, CO and particulate matter with a diameter size of below 10 μm (PM10). The three selected air monitoring stations share the characteristic of being located in highly urbanized areas and are surrounded by a number of industries. The DA results show that spatial characterizations allow successful discrimination between the three stations, while HACA shows the temporal pattern from the monthly and yearly factor analysis which correlates with severe haze episodes that have happened in this country at certain periods of time. The PCA results show that the major source of air pollution is mostly due to the combustion of fossil fuel in motor vehicles and industrial activities. The spatial pattern recognition (S-ANN) results show a better prediction performance in discriminating between the regions, with an excellent percentage of correct classification compared to DA. This study presents the necessity and usefulness of environmetric techniques for the interpretation of large datasets aiming to obtain better information about air quality patterns based on spatial and temporal characterizations at the selected air monitoring stations.

Original languageEnglish
Pages (from-to)1717-1728
Number of pages12
JournalEnvironmental Sciences: Processes and Impacts
Volume15
Issue number9
DOIs
Publication statusPublished - Sep 2013

Fingerprint

Malaysia
pattern recognition
Discriminant analysis
discriminant analysis
Air quality
Pattern recognition
air quality
Air
Cluster analysis
Principal component analysis
artificial neural network
cluster analysis
Monitoring
principal component analysis
air
Discriminant Analysis
Neural networks
Particulate Matter
haze
Factor analysis

ASJC Scopus subject areas

  • Environmental Chemistry
  • Public Health, Environmental and Occupational Health
  • Management, Monitoring, Policy and Law

Cite this

Spatial and temporal air quality pattern recognition using environmetric techniques : A case study in Malaysia. / Syed Abdul Mutalib, Sharifah Norsukhairin; Juahir, Hafizan; Azid, Azman; Mohd Sharif, Sharifah; Latif, Mohd Talib; Aris, Ahmad Zaharin; Zain, Sharifuddin M.; Dominick, Doreena.

In: Environmental Sciences: Processes and Impacts, Vol. 15, No. 9, 09.2013, p. 1717-1728.

Research output: Contribution to journalArticle

Syed Abdul Mutalib, SN, Juahir, H, Azid, A, Mohd Sharif, S, Latif, MT, Aris, AZ, Zain, SM & Dominick, D 2013, 'Spatial and temporal air quality pattern recognition using environmetric techniques: A case study in Malaysia', Environmental Sciences: Processes and Impacts, vol. 15, no. 9, pp. 1717-1728. https://doi.org/10.1039/c3em00161j
Syed Abdul Mutalib, Sharifah Norsukhairin ; Juahir, Hafizan ; Azid, Azman ; Mohd Sharif, Sharifah ; Latif, Mohd Talib ; Aris, Ahmad Zaharin ; Zain, Sharifuddin M. ; Dominick, Doreena. / Spatial and temporal air quality pattern recognition using environmetric techniques : A case study in Malaysia. In: Environmental Sciences: Processes and Impacts. 2013 ; Vol. 15, No. 9. pp. 1717-1728.
@article{8c939086c4a74e2b9bbee42eb0096211,
title = "Spatial and temporal air quality pattern recognition using environmetric techniques: A case study in Malaysia",
abstract = "The objective of this study is to identify spatial and temporal patterns in the air quality at three selected Malaysian air monitoring stations based on an eleven-year database (January 2000-December 2010). Four statistical methods, Discriminant Analysis (DA), Hierarchical Agglomerative Cluster Analysis (HACA), Principal Component Analysis (PCA) and Artificial Neural Networks (ANNs), were selected to analyze the datasets of five air quality parameters, namely: SO 2, NO2, O3, CO and particulate matter with a diameter size of below 10 μm (PM10). The three selected air monitoring stations share the characteristic of being located in highly urbanized areas and are surrounded by a number of industries. The DA results show that spatial characterizations allow successful discrimination between the three stations, while HACA shows the temporal pattern from the monthly and yearly factor analysis which correlates with severe haze episodes that have happened in this country at certain periods of time. The PCA results show that the major source of air pollution is mostly due to the combustion of fossil fuel in motor vehicles and industrial activities. The spatial pattern recognition (S-ANN) results show a better prediction performance in discriminating between the regions, with an excellent percentage of correct classification compared to DA. This study presents the necessity and usefulness of environmetric techniques for the interpretation of large datasets aiming to obtain better information about air quality patterns based on spatial and temporal characterizations at the selected air monitoring stations.",
author = "{Syed Abdul Mutalib}, {Sharifah Norsukhairin} and Hafizan Juahir and Azman Azid and {Mohd Sharif}, Sharifah and Latif, {Mohd Talib} and Aris, {Ahmad Zaharin} and Zain, {Sharifuddin M.} and Doreena Dominick",
year = "2013",
month = "9",
doi = "10.1039/c3em00161j",
language = "English",
volume = "15",
pages = "1717--1728",
journal = "Environmental Sciences: Processes and Impacts",
issn = "2050-7887",
publisher = "Royal Society of Chemistry",
number = "9",

}

TY - JOUR

T1 - Spatial and temporal air quality pattern recognition using environmetric techniques

T2 - A case study in Malaysia

AU - Syed Abdul Mutalib, Sharifah Norsukhairin

AU - Juahir, Hafizan

AU - Azid, Azman

AU - Mohd Sharif, Sharifah

AU - Latif, Mohd Talib

AU - Aris, Ahmad Zaharin

AU - Zain, Sharifuddin M.

AU - Dominick, Doreena

PY - 2013/9

Y1 - 2013/9

N2 - The objective of this study is to identify spatial and temporal patterns in the air quality at three selected Malaysian air monitoring stations based on an eleven-year database (January 2000-December 2010). Four statistical methods, Discriminant Analysis (DA), Hierarchical Agglomerative Cluster Analysis (HACA), Principal Component Analysis (PCA) and Artificial Neural Networks (ANNs), were selected to analyze the datasets of five air quality parameters, namely: SO 2, NO2, O3, CO and particulate matter with a diameter size of below 10 μm (PM10). The three selected air monitoring stations share the characteristic of being located in highly urbanized areas and are surrounded by a number of industries. The DA results show that spatial characterizations allow successful discrimination between the three stations, while HACA shows the temporal pattern from the monthly and yearly factor analysis which correlates with severe haze episodes that have happened in this country at certain periods of time. The PCA results show that the major source of air pollution is mostly due to the combustion of fossil fuel in motor vehicles and industrial activities. The spatial pattern recognition (S-ANN) results show a better prediction performance in discriminating between the regions, with an excellent percentage of correct classification compared to DA. This study presents the necessity and usefulness of environmetric techniques for the interpretation of large datasets aiming to obtain better information about air quality patterns based on spatial and temporal characterizations at the selected air monitoring stations.

AB - The objective of this study is to identify spatial and temporal patterns in the air quality at three selected Malaysian air monitoring stations based on an eleven-year database (January 2000-December 2010). Four statistical methods, Discriminant Analysis (DA), Hierarchical Agglomerative Cluster Analysis (HACA), Principal Component Analysis (PCA) and Artificial Neural Networks (ANNs), were selected to analyze the datasets of five air quality parameters, namely: SO 2, NO2, O3, CO and particulate matter with a diameter size of below 10 μm (PM10). The three selected air monitoring stations share the characteristic of being located in highly urbanized areas and are surrounded by a number of industries. The DA results show that spatial characterizations allow successful discrimination between the three stations, while HACA shows the temporal pattern from the monthly and yearly factor analysis which correlates with severe haze episodes that have happened in this country at certain periods of time. The PCA results show that the major source of air pollution is mostly due to the combustion of fossil fuel in motor vehicles and industrial activities. The spatial pattern recognition (S-ANN) results show a better prediction performance in discriminating between the regions, with an excellent percentage of correct classification compared to DA. This study presents the necessity and usefulness of environmetric techniques for the interpretation of large datasets aiming to obtain better information about air quality patterns based on spatial and temporal characterizations at the selected air monitoring stations.

UR - http://www.scopus.com/inward/record.url?scp=84882963012&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84882963012&partnerID=8YFLogxK

U2 - 10.1039/c3em00161j

DO - 10.1039/c3em00161j

M3 - Article

VL - 15

SP - 1717

EP - 1728

JO - Environmental Sciences: Processes and Impacts

JF - Environmental Sciences: Processes and Impacts

SN - 2050-7887

IS - 9

ER -