Ahmad Shakir Mohd Saudi

Spatial analysis of the air pollutant index in the southern region of Peninsular Malaysia using environmetric techniques

Air pollution is becoming a major environmental issue in the southern region of Peninsular Malaysia. Environmetric techniques (HACA, DA, and PCA/FA) were used to evaluate the spatial variations in the southern region of Peninsular Malaysia, followed by API prediction comparison using ANN and MLR models. The datasets of air pollutant parameters for 3 years (2005–2007) were applied in this study. HACA clustered three different groups of similarity based on the characteristics of air quality parameters. DA shows all seven parameters (CO, O3, PM10, SO2, NOx, NO, and NO2) gave the most significant variables after stepwise backward mode. PCA/FA identify that the major source of air pollution is due to combustion of fossil fuels in motor vehicles and industrial activities. The ANN model shows a better prediction compared to the MLR model with R2 values equal to 0.819 and 0.773 respectively. This study concluded that the environmetric techniques and modelling become an excellent tool in API assessment, air pollution source identification, apportionment, and interpretation of complex dataset with a view to get better information about the air quality, and can be setbacks in designing an API monitoring network for effective air pollution resources management.

Selection of the Most Significant Variables of Air Pollutants Using Sensitivity Analysis

This study was conducted to determine the most significant parameters for the air-pollutant index (API) prediction in Malaysia using data covering a 7-year period (2006–2012) obtained from the Malaysian Department of Environment (DOE). The sensitivity analysis method coupled with the artificial neural network (ANN) was applied. Nine models (ANN-API-AP, ANN-API-LCO, ANN-API-LO3, ANN-API-LPM10, ANN-API-LSO2, ANN-API-LNO2, ANN-API-LCH4, ANN-API-LNmHC and ANN-API-LTHC) were carried out in the sensitivity analysis test. From the findings, PM10 and CO were identified as the most significant parameters in Malaysia. Three artificial neural network models (ANN-API-AP, ANN-API-LO, and ANN-API-DOE) were compared based on the performance criterion [R2, root-mean-square error (RMSE), and squared sum of all errors (SSE)] for the best prediction model selection. The ANN-API-AP, ANN-API-LO, and ANN-API-DOE models have R2 values of 0.733, 0.578, and 0.742, respectively; RMSE values of 8.689, 10.858, and 8.357, respectively; SSE values of 762,767.22, 1,191,280.60, and 705,600.05, respectively. The findings exhibit the ANN-API-LO model has a lower value in R2 and higher values in RMSE and SSE than others. ANN-API-LO model was considered as the best model of prediction because of fewer variables was utilized as input and far less complex than others. Hence, the use of fewer parameters of the API prediction has been highly practicable for air resource management because of its time and cost efficiency.

Spatial Assessment of Water Quality Affected by the Land-Use Changes Along Kuantan River Basin

This study addresses the effects of development on water quality in the Kuantan River Basin from 2003 to 2008. Chemometrics analysis namely MLR, HACA, DA and PCA was utilised as part of the methods for this study. From the result, MLR was irrefutably proven as an efficient predicting method for missing data. HACA classified seven stations as Low Polluted Stations (LPS), six stations as Moderate Polluted Stations (MPS) and two stations as High Polluted Stations (HPS). DA result depicted the accuracy rate for all reclassified data was 83.61 % respectively, while the constituting parameters namely Dissolved Oxygen (DO), Escherichia coli (E. coli), pH, Phosphate (PO4), Chemical Oxygen Demand (COD), and Chloride (Cl), gave the biggest impacts towards water quality by means of forward and backward stepwise methods. The PCA result after varimax rotation indicated that five varimax factors have presented strong parameter coefficient exceeding 0.7 by E. coli, coliform, Dissolved Solids (DS), Total Solids (TS), Chlorine (Cl), Ammonical Nitrogen (NH3NL), nitrate and pH. The relationship between land use and water quality denoted that after applying Spearman correlation based on 90 % interval population distribution, aspects influencing the rate of DO was successfully identified.