Spatial Analysis of the Certain Air Pollutants Using Environmetric Techniques

Abstract

This study aims to identify the spatial variation of air pollutant and its pattern in the northern part of Peninsular Malaysia for four years monitoring observation (2008-2011) based on the seven air monitoring stations. Air pollutant variables that used in this study were Nitrogen Dioxide (NO2), Ozone (O3), Carbon Monoxide (CO), and Particulate Matter (PM10) data and had been supplied by Department Of Environment Malaysia (DOE). ANOVA, environmetric techniques (HACA and Descriptive Analysis) and Artificial Neural Network (ANN) approach were used in data analysed. According to ANOVA single test, significance p-value of PM10 (p= 2.5E-268) is smaller than significance alpha level (p=0.05) and it suitable parameter for further analysis in construct the prevention actions compared to O3, NO2 and CO. HACA categorized seven air monitoring station into three cluster group of station such as High Concentrated Site (HCS), Moderate Concentrated Site (MCS), and Low Concentrated Site (LCS). Descriptive statistics show the 25th percentile, median, and 75th percentile boxplot and identified the greater (>500 µg/m3) and smaller (<0.05ppm) outliers, and comparing distributions between each air pollutant. The findings from ANN have verified that the R2 and RMSE value (0.7981 and 5.734, respectively) were categorized as a significant value for the future prediction. In contrast, PM10 levels in Air Pollutant Index equal to 43.59 were 67.91 ug/m3, O3 (0.038 ppm), NO2 (0.019 ppm), and then CO (1.27 ppm) concentration values. This proved that the PM10 concentration was categorized as a main contributor to the air pollutant measurement of statistical method compared with other pollutants.

Application of chemometrics techniques to solve environmental issues in Malaysia

“…(2015a)8.Selection of the most significant variables of air pollutants using sensitivity analysis at ten selected Malaysian monitoring stations based on database for a 7 year period (2006–2012).ANN-API-AP, ANN-API-LCO, ANN-API-LO 3 , ANN-API-LPM 10 , ANN-API-LSO 2 , ANN-API-LNO 2 , ANN-API-LCH 4 , ANN-API-LNmHC, ANN-API-LTHC, ANN-API-LO, and ANN-API-DOEANN-API-LO model was the best predictor model as only two parameters utilized as input for API prediction.API prediction with the use of fewer parameters has been highly practicable for air quality management due to its time and cost efficiency.Azid et al. (2015b)9.Identification of the spatial variation of air pollutants and its pattern at seven air monitoring stations in the northern part of Peninsular Malaysia for 4 years (2008–2011).HACA, DA and ANNThe predictive ability of chemometrics is at least as good as the standard model.The feed-forward ANN model could predict API values from all existing input with slight precision and could save time and cost of monitoring purposes.Amran et al. (2015)10.Determination of air quality pattern at Putrajaya monitoring station based on three years observation (2011–2013).PCA, FA and SPCPCA and FA model identified five pollutants that affected air quality.SPC analysis verified that SO 2 was the main pollutant.Kamaruzzaman et al.…”

Assessment on air quality pattern: a case study in Putrajaya, Malaysia

“…However, the maximum value of API was 199 which indicate that the air status in unhealthy condition with mild aggravation of symptoms among high risks group such as those with heart or lung diseases. The maximum value of API increased was probably reflected from the PM 10 maximum reading as proven that PM 10 give high impact on API value [9].…”

“…This indicates that the concentration of PM 10 dispersed in the air proven to give high impact on the API as compared to other pollutants [9]. The pattern of air pollutant (SO 2 ) and API were computed via time series analysis by using SPC.…”

Identification Source of Variation on Regional Impact of Air Quality Pattern using Chemometric Techniques in Kuching, Sarawak

“…ANN was used to identify nonlinear pattern in the database [17]. It is also a technique that provides a better flexibility, efficiency, consistency and accuracy as it follows the great feature of human brain neurons [17][18]. ANN can be a great tool to estimate the long term impact and can be used to monitor the concentration of air pollutants [17].…”