Assessment of spatial air quality on the East Coast of Peninsular Malaysia utilizing environmetric techniques.

The presence of harmful substances in the atmosphere poses significant risks to the environment and public health. These pollutants can come from natural sources like dust and wildfires, or from human activities such as industrial, transportation, and agricultural practices. The objective of this study was to assess air quality on the East Coast of Peninsular Malaysia by analyzing historical data from the Department of Environment, Malaysia. Daily measurements of PM10, O3, SO2, NO2, and CO were collected from eight monitoring stations over 11 years (2011-2021) and analyzed using environmetric techniques. Hierarchical agglomerative cluster analysis (HACA) classified two stations as belonging to the high pollution cluster (HPC), three stations as part of the moderate pollution cluster (MPC), and three stations as the low pollution cluster (LPC). Discriminant analysis revealed a correct assignment rate of 90.50%, indicating that all five parameters were able to differentiate pollution levels with high significance (p < 0.0001). Principal component analysis (PCA) was conducted to validate the pattern of air quality variables in relation to the identified clusters (HPC, MPC, and LPC). The results showed that two verifactors (VFs) were extracted in HPC and LPC, while three VFs were identified in MPC. The cumulative variance explained by the PCA for HPC, MPC, and LPC was 69.43%, 82.32%, and 62.16%, respectively. Finally, an artificial neural network (ANN) was used to forecast the air pollutant index (API) levels, using the R2 and RMSE performance metrics. The PCA-MLP Model A yielded an R2 value of 0.8470 and an RMSE of 6.6470, while PCA-MLP Model B achieved an R2 value of 0.8591 and an RMSE of 6.3000, both indicating a significant and strong correlation.

Comparison of rainwater quality before and during the MCO using chemometric analyses.

This study aimed to classify the spatiotemporal analysis of rainwater quality before and during the Movement Control Order (MCO) implementation due to the COVID-19 pandemic. Chemometric analysis was carried out on rainwater samples collected from 24-gauge stations throughout Malaysia to determine the samples' chemical content, pH, and conductivity. Other than that, hierarchical agglomerative cluster analysis (HACA) and discriminant analysis (DA) were used to classify the quality of rainwater at each location into four clusters, namely good, satisfactory, moderate, and bad clusters. Note that DA was carried out on the predefined clusters. The reduction in acidity levels occurred in 11 stations (46% of overall stations) after the MCO was implemented. Chemical content and ion abundance followed a downward trend, indicating that Cl- and Na+ were the most dominant among the anions and cations. Apart from that, NH4+, Ca2+, NO3-, and SO42- concentrations were evident in areas with significant anthropogenic activity, as there was a difference in the total chemical content in rainwater when compared before and during the MCO. Based on the dataset before the MCO, 75% of gauge stations were in the good cluster, 8.3% in the satisfactory cluster, 12.5% in the moderate cluster, and 4.2% in the bad cluster. Meanwhile, the dataset during the MCO shows that 72.7% of gauge stations were in the good cluster, 9.1% in the satisfactory cluster, 9.1% in the moderate, and 4.5% in the bad cluster. From this study, the chemometric analysis of the year 2020 rainwater chemical composite dataset strongly indicates that reduction of human activities during MCO affected the quality of rainwater.

Water quality modelling using principal component analysis and artificial neural network.

The study investigates the latent pollution sources and most significant parameters that cause spatial variation and develops the best input for water quality modelling using principal component analysis (PCA) and artificial neural network (ANN). The dataset, 22 water quality parameters were obtained from Department of Environment Malaysia (DOE). The PCA generated six significant principal component scores (PCs) which explained 65.40 % of the total variance. Parameters for water quality variation are mainlyrelated to mineral components, anthropogenic activities, and natural processes. However, in ANN three input combination models (ANN A, B, and C) were developed to identify the best model that can predict water quality index (WQI) with very high precision. ANN A model appears to have the best prediction capacity with a coefficient of determination (R2) = 0.9999 and root mean square error (RMSE) = 0.0537. These results proved that the PCA and ANN methods can be applied as tools for decision-making and problem-solving for better managing of river quality.

Development of COVID-19 Health-Risk Assessment and Self-Evaluation (CHaSe): a health screening system for university students and staff during the movement control order (MCO).

COVID-19 has triggered a global health crisis. Death from severe respiratory failure and symptoms, including fever, dry cough, sore throat, anosmia, and gastrointestinal disturbances, has been attributed to the disease. Development of screening and diagnosis methods prove to be challenging due to shared clinical features between COVID-19 and other pathologies, such as Middle Eastern respiratory syndrome, severe acute respiratory syndrome, and common colds. This study aims to develop a comprehensive one-stop online public health screening system based on clinical and epidemiological criteria. The immediate target populations are the university students and staff of University Sultan Zainal Abidin and the civil servants of the Malaysian Ministry of Science, Technology, and Innovation. Forty-nine (49) clinical and epidemiological factors associated with COVID-19 were identified and prioritized based on their prevalence via rigorous review of the literature and vetting sessions. A pilot study of 200 volunteers was conducted to assess the extent of risk mitigation of COVID-19 infection among the university students and civil servants using the prototyped model. Consequently, twelve (12) clinical parameters were identified and validated by the medical experts as essential variables for COVID-19 risk-screening. The updated model was then revalidated via real mass-screening of 5000 resulting in the final adopted CHaSe system. Principal component analysis (PCA) was used to confirm the weightage of risk level toward COVID-19 to procures the optimal accuracy, reliability, and efficiency of this system. Twelve (12) factor loadings accountable for 58.287% of the clinical symptoms and clinical history variables with forty-nine (49) parameters of COVID-19 were identified through PCA. The variables of the clinical and epidemiological aspects identified are the C6 (History of joining high-risk gathering (where confirmed cases had been recorded), CH11 [History of contact with confirmed cases (close contact)], CH13 [Duration of exposure with confirmed cases (minutes)] with substantial positive factors of 0.7053, 0.706 and 0.5086, respectively. The contribution toward high-risk infection of COVID-19 was firmly attributable to the variables CH14 [Last contact with confirmed cases (days)], CH13 [Duration of exposure with confirmed cases (minutes)], and S1 (Age). The revalidated PCA for 5000 respondents also yielded twelve significant PCs with a cumulative variance of 58.288%. Importantly, the medical experts have revalidated the CHaSe system for accuracy of all clinical aspects (clinical symptoms and clinical history) and epidemiological links to COVID-19 infection. After revalidating the model for 5000 respondents, the PC variance for PC1, PC2, PC3, and PC4 was 27.36%, 11.79%, 10.347%, and 8.785%, respectively, with the cumulative explanation of 58.288% in data variability. The level of risks detected using the CHaSe system toward COVID-19 provides optimal accuracy, reliability, and efficiency to conduct mass-screening of students and government servants for COVID-19 infection.

Estimation of rainwater harvesting by the reflectance of the purity index of rainfall.

Rainwater harvesting is an effective alternative practice, particularly within urban regions, during periods of water scarcity and dry weather. The collected water is mostly utilized for non-potable household purposes and irrigation. However, due to the increase in atmospheric pollutants, the quality of rainwater has gradually decreased. This atmospheric pollution can damage the climate, natural resources, biodiversity, and human health. In this study, the characteristics and physicochemical properties of rainfall were assessed using a qualitative approach. The three-year (2017-2019) data on rainfall in Peninsular Malaysia were analysed via multivariate techniques. The physicochemical properties of the rainfall yielded six significant factors, which encompassed 61.39% of the total variance as a result of industrialization, agriculture, transportation, and marine factors. The purity of rainfall index (PRI) was developed based on subjective factor scores of the six factors within three categories: good, moderate, and bad. Of the 23 variables measured, 17 were found to be the most significant, based on the classification matrix of 98.04%. Overall, three different groups of similarities that reflected the physicochemical characteristics were discovered among the rain gauge stations: cluster 1 (good PRI), cluster 2 (moderate PRI), and cluster 3 (bad PRI). These findings indicate that rainwater in Peninsular Malaysia was suitable for non-potable purposes.

Support vector machines for oil classification link with polyaromatic hydrocarbon contamination in the environment.

The main focus of this study is exploring the spatial distribution of polyaromatics hydrocarbon links between oil spills in the environment via Support Vector Machines based on Kernel-Radial Basis Function (RBF) approach for high precision classification of oil spill type from its sample fingerprinting in Peninsular Malaysia. The results show the highest concentrations of Σ Alkylated PAHs and Σ EPA PAHs in ΣTAH concentration in diesel from the oil samples PP3_liquid and GP6_Jetty achieving 100% classification output, corresponding to coherent decision boundary and projective subspace estimation. The high dimensional nature of this approach has led to the existence of a perfect separability of the oil type classification from four clustered oil type components; i.e diesel, bunker C, Mixture Oil (MO), lube oil and Waste Oil (WO) with the slack variables of ξ ≠ 0. Of the four clusters, only the SVs of two are correctly predicted, namely diesel and MO. The kernel-RBF approach provides efficient and reliable oil sample classification, enabling the oil classification to be optimally performed within a relatively short period of execution and a faster dataset classification where the slack variables ξ are non-zero.

Tracing sewage contamination based on sterols and stanols markers within the mainland aquatic ecosystem: a case study of Linggi catchment, Malaysia.

Sewage contamination is a principal concern in water quality management as pathogens in sewage can cause diseases and lead to detrimental health effects in humans. This study examines the distribution of seven sterol compounds, namely coprostanol, epi-coprostanol, cholesterol, cholestanol, stigmasterol, campesterol, and ß-sitosterol in filtered and particulate phases of sewage treatment plants (STPs), groundwater, and river water. For filtered samples, solid-phase extraction (SPE) was employed while for particulate samples were sonicated. Quantification was done by using gas chromatography-mass spectrometer (GC-MS). Faecal stanols (coprostanol and epi-coprostanol) and ß-sitosterol were dominant in most STP samples. Groundwater samples were influenced by natural/biogenic sterol, while river water samples were characterized by a mixture of sources. Factor loadings from principal component analysis (PCA) defined fresh input of biogenic sterol and vascular plants (positive varimax factor (VF)1), aged/treated sewage sources (negative VF1), fresh- and less-treated sewage and domestic sources (positive VF2), biological sewage effluents (negative VF2), and fresh-treated sewage sources (VF3) in the samples. Association of VF loadings and factor score values illustrated the correlation of STP effluents and the input of biogenic and plant sterol sources in river and groundwater samples of Linggi. This study focuses on sterol distribution and its potential sources; these findings will aid in sewage assessment in the aquatic environment.

Water corrosivity of polluted reservoir and hydropower sustainability.

Reservoirs play a strategic role in the context of sustainable energy supply. Unfortunately, the majority of the reservoirs are facing water-quality degradation due to complex pollutants originating from activities both in the catchment and inside the reservoir. This research was aimed at assessing the extent of the water degradation, in terms of corrosivity level, and at examining its impacts on hydropower capacity and operation. Water quality data (total dissolved solids, pH, calcium, bicarbonate, and temperature) were obtained from 20 sampling stations in the Cirata Reservoir from 2007 to 2016. The results show that the river water is already corrosive (Langelier Saturation Index, LSI = - 0.21 to - 1.08), and, the corrosiveness becoming greater when entering the reservoir (LSI = - 0.52 to - 1.49). The water corrosivity has caused damage to the hydro-mechanical equipment and lowering production capacity. The external environment of the catchment hosts complex human activities, such as agriculture, land conversion, urban and industrial discharge, which have all played a major role in the water corrosiveness. Meanwhile, the internal environment, such as floating net cage aquaculture, has intensified the problem. As the water corrosiveness has increased, the maintenance of the hydro-mechanical facilities has also increased. Strategies must be applied as current conditions are certainly a threat to the sustainability of the hydropower operation and, hence, the energy supply.

Occurrence of pesticides in surface water, pesticides removal efficiency in drinking water treatment plant and potential health risk to consumers in Tengi River Basin, Malaysia.

Agricultural activities have been arising along with the use of pesticides. The use of pesticides can impact not only on vector or other pest but also able to harm human health. Pesticide may leach from the irrigation of plant into the groundwater and in surface water. These waters could be sources of drinking water in a pesticides polluted area. This study aims to determine the occurrence pesticides in surface water and pesticides removal efficiency in a conventional drinking water treatment plant (DWTP) and the potential health risk to consumers. The study was conducted in Tanjung Karang, Selangor, Malaysia. Thirty river water samples and eighteen water samples from DWTP were collected. The water samples were extracted using solid phase extraction (SPE) before injected to the ultra-high performance liquid chromatography tandem mass spectrometry (UHPLC-MS/MS). Five hundreds and ten respondents were interviewed using questionnaires to obtain information for health risk assessments. The results showed that propiconazole had the highest mean concentration (4493.1 ng/L) while pymetrozine had the lowest mean concentration (1.3 ng/L) in river water samples. The pesticides removal efficiencies in the conventional DWTP were 77% (imidacloprid), 86% (propiconazole and buprofezin), 88% (tebuconazole) and 100% (pymetrozine, tricyclazole, chlorantraniliprole, azoxystrobin and trifloxystrobin), respectively. The hazard quotients (HQs) and hazard index (HI) for all target pesticides were <1, indicating there was no significant chronic non-carcinogenic health risk due to consumption of the drinking water. Conventional DWTP was not able to completely remove four pesticide; thus, advanced treatment systems need to be considered to safeguard the health of the community in future.

Combination of Sensory, Chromatographic, and Chemometrics Analysis of Volatile Organic Compounds for the Discrimination of Authentic and Unauthentic Harumanis Mangoes.

This study analyzed the volatile organic compounds (VOCs) of three mango varieties (Harumanis, Tong Dam and Susu) for the discrimination of authentic Harumanis from other mangoes. The VOCs of these mangoes were extracted and analysed nondestructively using Head Space-Solid Phase Micro Extraction (HS-SPME) coupled to Gas Chromatography-Mass Spectrometry (GC-MS). Prior to the analytical method, two simple sensory analyses were carried out to assess the ability of the consumers to differentiate between the Harumanis and Tong Dam mangoes as well as their preferences towards these mangoes. On the other hand, chemometrics techniques, such as principal components analysis (PCA), hierarchical clustering analysis (HCA), and discriminant analysis (DA), were used to visualise grouping tendencies of the volatile compounds detected. These techniques were successful in identifying the grouping tendencies of the mango samples according to the presence of their respective volatile compounds, thus enabling the identification of the groups of substances responsible for the discrimination between the authentic and unauthentic Harumanis mangoes. In addition, three ocimene compounds, namely beta-ocimene, trans beta-ocimene, and allo-ocimene, can be considered as chemical markers of the Harumanis mango, as these compounds exist in all Harumanis mango, regardless the different sources of the mangoes obtained.

Consumption of water from ex-mining ponds in Klang Valley and Melaka, Malaysia: A health risk study.

Evaluation of health risks due to heavy metals exposure via drinking water from ex-mining ponds in Klang Valley and Melaka has been conducted. Measurements of As, Cd, Pb, Mn, Fe, Na, Mg, Ca, and dissolved oxygen, pH, electrical conductivity, total dissolved solid, ammoniacal nitrogen, total suspended solid, biological oxygen demand were collected from 12 ex-mining ponds and 9 non-ex-mining lakes. Exploratory analysis identified As, Cd, and Pb as the most representative water quality parameters in the studied areas. The metal exposures were simulated using Monte Carlo methods and the associated health risks were estimated at 95th and 99th percentile. The results revealed that As was the major risk factor which might have originated from the previous mining activity. For Klang Valley, adults that ingested water from those ponds are at both non-carcinogenic and carcinogenic risks, while children are vulnerable to non-carcinogenic risk; for Melaka, only children are vulnerable to As complications. However, dermal exposure showed no potential health consequences on both adult and children groups.

Tracing the sources of lead (Pb) in Brunei Bay, Borneo by using integrated spectrometry ICP-MS and chemometric techniques.

The present study aims to define the possible sources that contribute to the level of Pb into the Brunei Bay, Borneo. The cluster analysis has classified the bay into the northern part with heavy and agriculture-related industries; the southern area with a moderate rural human settlement as well as the southwestern area with a more pristine environment and a low level of human settlement. The score plot of spatial discriminant analysis verified a significant influence of the river system toward the estuary, whereas the temporal discriminant analysis has discriminated the seasonal changes. In comparison to elsewhere, the stable Pb isotopic ratios in Brunei Bay showed a fingerprint similar to coal-related sources and of aerosol input. Briefly, even though Pb in the Brunei Bay ecosystem proved to be at a low level, the stable Pb isotopic ratios showed that human and industrial activities are slowly contributing Pb into the bay ecosystem.

Improving oil classification quality from oil spill fingerprint beyond six sigma approach.

This study involves the use of quality engineering in oil spill classification based on oil spill fingerprinting from GC-FID and GC-MS employing the six-sigma approach. The oil spills are recovered from various water areas of Peninsular Malaysia and Sabah (East Malaysia). The study approach used six sigma methodologies that effectively serve as the problem solving in oil classification extracted from the complex mixtures of oil spilled dataset. The analysis of six sigma link with the quality engineering improved the organizational performance to achieve its objectivity of the environmental forensics. The study reveals that oil spills are discriminated into four groups' viz. diesel, hydrocarbon fuel oil (HFO), mixture oil lubricant and fuel oil (MOLFO) and waste oil (WO) according to the similarity of the intrinsic chemical properties. Through the validation, it confirmed that four discriminant component, diesel, hydrocarbon fuel oil (HFO), mixture oil lubricant and fuel oil (MOLFO) and waste oil (WO) dominate the oil types with a total variance of 99.51% with ANOVA giving Fstat>Fcritical at 95% confidence level and a Chi Square goodness test of 74.87. Results obtained from this study reveals that by employing six-sigma approach in a data-driven problem such as in the case of oil spill classification, good decision making can be expedited.

Chemometric techniques in oil classification from oil spill fingerprinting.

Extended use of GC-FID and GC-MS in oil spill fingerprinting and matching is significantly important for oil classification from the oil spill sources collected from various areas of Peninsular Malaysia and Sabah (East Malaysia). Oil spill fingerprinting from GC-FID and GC-MS coupled with chemometric techniques (discriminant analysis and principal component analysis) is used as a diagnostic tool to classify the types of oil polluting the water. Clustering and discrimination of oil spill compounds in the water from the actual site of oil spill events are divided into four groups viz. diesel, Heavy Fuel Oil (HFO), Mixture Oil containing Light Fuel Oil (MOLFO) and Waste Oil (WO) according to the similarity of their intrinsic chemical properties. Principal component analysis (PCA) demonstrates that diesel, HFO, MOLFO and WO are types of oil or oil products from complex oil mixtures with a total variance of 85.34% and are identified with various anthropogenic activities related to either intentional releasing of oil or accidental discharge of oil into the environment. Our results show that the use of chemometric techniques is significant in providing independent validation for classifying the types of spilled oil in the investigation of oil spill pollution in Malaysia. This, in consequence would result in cost and time saving in identification of the oil spill sources.

Development of Chromatographic Fingerprints of Eurycoma longifolia (Tongkat Ali) Roots Using Online Solid Phase Extraction-Liquid Chromatography (SPE-LC).

E. longifolia is attracting interest due to its pharmacological properties and pro-vitality effects. In this study, an online SPE-LC approach using polystyrene divinyl benzene (PSDVB) and C18 columns was developed in obtaining chromatographic fingerprints of E. longifolia. E. longifolia root samples were extracted using pressurized liquid extraction (PLE) technique prior to online SPE-LC. The effects of mobile phase compositions and column switching time on the chromatographic fingerprint were optimized. Validation of the developed method was studied based on eurycomanone. Linearity was in the range of 5 to 50 µg∙mL(-1) (r² = 0.997) with 3.2% relative standard deviation of peak area. The developed method was used to analyze 14 E. longifolia root samples and 10 products (capsules). Selected chemometric techniques: cluster analysis (CA), discriminant analysis (DA), and principal component analysis (PCA) were applied to the fingerprint datasets of 37 selected peaks to evaluate the ability of the chromatographic fingerprint in classifying quality of E. longifolia. Three groups were obtained using CA. DA yielded 100% correlation coefficient with 19 discriminant compounds. Using PCA, E. longifolia root samples were clearly discriminated from the products. This study showed that the developed online SPE-LC method was able to provide comprehensive evaluation of E. longifolia samples for quality control purposes.

Spatial assessment and source identification of heavy metals pollution in surface water using several chemometric techniques.

This study presents the determination of the spatial variation and source identification of heavy metal pollution in surface water along the Straits of Malacca using several chemometric techniques. Clustering and discrimination of heavy metal compounds in surface water into two groups (northern and southern regions) are observed according to level of concentrations via the application of chemometric techniques. Principal component analysis (PCA) demonstrates that Cu and Cr dominate the source apportionment in northern region with a total variance of 57.62% and is identified with mining and shipping activities. These are the major contamination contributors in the Straits. Land-based pollution originating from vehicular emission with a total variance of 59.43% is attributed to the high level of Pb concentration in the southern region. The results revealed that one state representing each cluster (northern and southern regions) is significant as the main location for investigating heavy metal concentration in the Straits of Malacca which would save monitoring cost and time. CAPSULE: The monitoring of spatial variation and source of heavy metals pollution at the northern and southern regions of the Straits of Malacca, Malaysia, using chemometric analysis.

Artificial neural network modeling of the water quality index using land use areas as predictors.

This paper describes the design of an artificial neural network (ANN) model to predict the water quality index (WQI) using land use areas as predictors. Ten-year records of land use statistics and water quality data for Kinta River (Malaysia) were employed in the modeling process. The most accurate WQI predictions were obtained with the network architecture 7-23-1; the back propagation training algorithm; and a learning rate of 0.02. The WQI forecasts of this model had significant (p < 0.01), positive, very high correlation (ρs = 0.882) with the measured WQI values. Sensitivity analysis revealed that the relative importance of the land use classes to WQI predictions followed the order: mining > rubber > forest > logging > urban areas > agriculture > oil palm. These findings show that the ANNs are highly reliable means of relating water quality to land use, thus integrating land use development with river water quality management.

Identification of the hydrogeochemical processes in groundwater using classic integrated geochemical methods and geostatistical techniques, in Amol-Babol Plain, Iran.

Hydrogeochemical investigations had been carried out at the Amol-Babol Plain in the north of Iran. Geochemical processes and factors controlling the groundwater chemistry are identified based on the combination of classic geochemical methods with geographic information system (GIS) and geostatistical techniques. The results of the ionic ratios and Gibbs plots show that water rock interaction mechanisms, followed by cation exchange, and dissolution of carbonate and silicate minerals have influenced the groundwater chemistry in the study area. The hydrogeochemical characteristics of groundwater show a shift from low mineralized Ca-HCO3, Ca-Na-HCO3, and Ca-Cl water types to high mineralized Na-Cl water type. Three classes, namely, C1, C2, and C3, have been classified using cluster analysis. The spatial distribution maps of Na(+)/Cl(-), Mg(2+)/Ca(2+), and Cl(-)/HCO3 (-) ratios and electrical conductivity values indicate that the carbonate and weathering of silicate minerals played a significant role in the groundwater chemistry on the southern and western sides of the plain. However, salinization process had increased due to the influence of the evaporation-precipitation process towards the north-eastern side of the study area.

Water quality assessment and analysis of spatial patterns and temporal trends.

This study investigated relationships of a water quality index (WQI) with multiple water quality variables (WQVs), explored variability in water quality over time and space, and established linear and non-linear models predictive of WQI from raw WQVs. Data were processed using Spearman's rank correlation analysis, multiple linear regression, and artificial neural network modeling. Correlation analysis indicated that from a temporal perspective, the WQI, temperature, and zinc, arsenic, chemical oxygen demand, sodium, and dissolved oxygen concentrations increased, whereas turbidity and suspended solids, total solids, nitrate nitrogen (NO3-N), and biochemical oxygen demand concentrations decreased with year. From a spatial perspective, an increase with distance of the sampling station from the headwater was exhibited by 10 WQVs: magnesium, calcium, dissolved solids, electrical conductivity, temperature, NO3-N, arsenic, chloride, potassium, and sodium. At the same time, the WQI; Escherichia coli bacteria counts; and suspended solids, total solids, and dissolved oxygen concentrations decreased with distance from the headwater. Lastly, regression and artificial neural network models with high prediction powers (81.2% and 91.4%, respectively) were developed and are discussed.

Spatial and temporal air quality pattern recognition using environmetric techniques: a case study in Malaysia.

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: SO2, 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.