Multivariate Statistical Techniques For Evaluation Research Articles

Time-based and latitudinal assessment of contaminated and clean water quality on concrete strength

With increasing population and demand for infrastructural development in many developing countries, the demand for concrete has been on the increase and does not show any sign of slowing down in the nearest future. Existing concrete structures are also deteriorating and require repair or replacement. In this study, multivariate methods of factor analysis (FA) and cluster analysis (CA), were applied to analyze the liquefied samples datasets for clean and contaminated (sewage) water obtained in Ado- Odo Ota, Ogun State, Nigeria. FA clearly identified two groups of liquefied samples and indicated that the bacterial parameters are higher in fermented locust beans water which can be likened to presence of bacillus subtilis food type. Hierarchical cluster grouped 40 samples into two which are high and low levels of bacteria contents respectively. Descriptive statistics showed all parameters significantly (conductivity, TDS, BOD, COD, carbondioxide, Calcium, Chlorine, pH, Temperature, salinity) in Cluster A greater than in cluster B. The main self- healing parameter for crack sealing up, because when bacteria commence feeding on calcium lactate once activated, oxygen consumed as the bacteria feeds and insoluble limestone formed by conversion of the soluble calcium lactate is greater for contaminated water against portable water values. This study demonstrates the usefulness of multivariate statistical techniques for evaluation of presence of bacteria in liquefied samples before used as self-healing. Keywords— Carbondioxide, clean, self-healing concrete, water.

Pattern recognition techniques for evaluating the spatial impact of copper mining on surface waters

In this study, multivariate statistical approaches, namely hierarchical cluster analysis (CA) and principal component analysis (PCA), were employed to understand the impact of copper mining on surface waters located in Central-East India. The data set generated consisted of nine parameters, namely pH, dissolved oxygen (DO), alkalinity, total dissolved solids, copper, iron, manganese, zinc and fluoride, collected in forty sampling points covering all seasons. As delineated by CA, the entire data set for both the surface waters was bifurcated into groups, namely Banjar River inclusion of seepage points (BRISP) and Banjar River exclusion of seepage points (BRESP), Son River inclusion of seepage points (SRISP) and Son River exclusion of seepage points (SRESP). Four latent factors were identified, namely copper, iron, fluoride and manganese, explaining 84.7 % of variance for BRISP, 71.9 % of variance for BRESP, 66.7 % of variance for SRISP and 68 % of variance for SRESP. The extensive application of PCA on BRISP, BRESP, SRISP and SRESP reveals that the main stream of both the rivers remains unaffected by mining operations when seepage points were excluded. Additionally, iron content is considerably significant throughout the stream due to the geogenic sources and it is considered as a major factor for the depletion of DO level in the streams. This study reveals the level of contamination in the studied surface waters and the effectiveness of multivariate statistical techniques for evaluation and interpretation of complex data matrix in understanding the spatial variations and identification of pollution sources.

Assessment of heavy metals pollution using multivariate statistical analysis methods in Wadi El Bey (Tunisia)

Heavy metal pollution is a major environmental problem worldwide because of the longstanding toxicity and bioaccumulation of metals. The risk is pronounced in the environment adjacent to large industrial complexes and cities historically located along rivers. The aim of this paper was the application of multivariate statistical techniques: cluster analysis (CA), principal component analysis (PCA), and discriminant analysis (DA) to evaluate spatial and temporal variations of the heavy metals fraction of Pb, Cu, Zn, Fe, Ni, Cr, and Al during monitoring of surface water of Wadi El Bey in northern part of Tunisia. Water samples were collected seasonally from 13 sites along the Wadi during 2 years (2012–2013). Results indicated that the concentrations and distribution of heavy metals appear to be largely controlled by natural processes, anthropogenic activities, and climatic conditions. CA classified the sampling sites into three clusters: Lowly Polluted sites “LP” (S2, S3 and S6–S11), Moderately Polluted sites “MP” (S4 and S5), and Highly Polluted Site “HP” (S1) based on similarities of water quality characteristics. PCA applied to the data-sets indicated that the total variance of water quality in the HP, MP, and LP sites were about 94.91, 91.06, and 80.14%, respectively. DA results seem to identify Cu, Fe, Zn, and Al as the most significant parameters for discrimination between seasons; whereas, Pb, Cu, Ni, Cr, and Al were the most significant parameters used to control the spatial variation. Thus, DA allowed reduction in dimensionality of the large data-set, delineating a few indicator parameters responsible for large variations in water quality. This study presents necessity and usefulness of multivariate statistical techniques for evaluation and interpretation of large complex data-sets with a view to get better information about the water quality and design of monitoring network for effective management of water resources.

Temporal and spatial assessment of river surface water quality using multivariate statistical techniques: a study in Can Tho City, a Mekong Delta area, Vietnam.

The present study is an evaluation of temporal/spatial variations of surface water quality using multivariate statistical techniques, comprising cluster analysis (CA), principal component analysis (PCA), factor analysis (FA) and discriminant analysis (DA). Eleven water quality parameters were monitored at 38 different sites in Can Tho City, a Mekong Delta area of Vietnam from 2008 to 2012. Hierarchical cluster analysis grouped the 38 sampling sites into three clusters, representing mixed urban-rural areas, agricultural areas and industrial zone. FA/PCA resulted in three latent factors for the entire research location, three for cluster 1, four for cluster 2, and four for cluster 3 explaining 60, 60.2, 80.9, and 70% of the total variance in the respective water quality. The varifactors from FA indicated that the parameters responsible for water quality variations are related to erosion from disturbed land or inflow of effluent from sewage plants and industry, discharges from wastewater treatment plants and domestic wastewater, agricultural activities and industrial effluents, and contamination by sewage waste with faecal coliform bacteria through sewer and septic systems. Discriminant analysis (DA) revealed that nephelometric turbidity units (NTU), chemical oxygen demand (COD) and NH₃ are the discriminating parameters in space, affording 67% correct assignation in spatial analysis; pH and NO₂ are the discriminating parameters according to season, assigning approximately 60% of cases correctly. The findings suggest a possible revised sampling strategy that can reduce the number of sampling sites and the indicator parameters responsible for large variations in water quality. This study demonstrates the usefulness of multivariate statistical techniques for evaluation of temporal/spatial variations in water quality assessment and management.

Assessment of ground and surface water quality along the river Varuna, Varanasi, India.

Multivariate statistical techniques were employed for monitoring of ground-surface water interactions in rivers. The river Varuna is situated in the Indo-Gangetic plain and is a small tributary of river Ganga. The study area was monitored at seven sampling sites for 3 years (2010-12), and eight physio-chemical parameters were taken into account for this study. The data obtained were analysed by multivariate statistical techniques so as to reveal the underlying implicit information regarding proposed interactions for the relevant area. The principal component analysis (PCA) and cluster analysis (CA), and the results of correlations were also studied for all parameters monitored at every site. Methods used in this study are essentially multivariate statistical in nature and facilitate the interpretation of data so as to extract meaningful information from the datasets. The PCA technique was able to compress the data from eight to three parameters and captured about 78.5% of the total variance by performing varimax rotation over the principal components. The varifactors, as yielded from PCA, were treated by CA which grouped them convincingly into three groups having similar characteristics and source of contamination. Moreover, the loading of variables on significant PCs showed correlations between various ground water and surface water (GW-SW) parameters. The correlation coefficients calculated for various physiochemical parameters for ground and surface water established the correlations between them. Thus, this study presents the utility of multivariate statistical techniques for evaluation of the proposed interactions and effective future monitoring of potential sites.

Descriptive and multivariable analysis of the physico-chemical and biological parameters of Sfax wastewater treatment plant

A set of quantitative descriptive and analytical data from the wastewater treatment plant (WWTP) of Sfax, located on the south-east of Tunisia, has been processed by multivariate statistical techniques in order to investigate the evolution of the wastewater quality over a period of 12 years (1984–1996) for six physico-chemical and biological parameters. The experimental 6×12 matrix was analysed by principal component analysis (PCA). The exploration of the correlation matrix allowed to uncover strong associations between some variables (BODi CODi, SSi BDOo, CODo SSo) as well as a lack of association between the others (Twater and SSo). PCA showed the existence of up to three significant PCs which account for 74% of the variance. The first one assigned to water with relatively low organic load, whereas the second and the third assigned to water with an average and high organic and mineral loads. This study presents necessity and usefulness of multivariate statistical techniques for evaluation and interpretation of large complex data sets with view to get better information about the water quality and design of monitoring network for effective management of water resources.

Assessment of heavy metal pollution in water using multivariate statistical techniques in an industrial area: A case study from Patancheru, Medak District, Andhra Pradesh, India

Application of different multivariate statistical approaches for the interpretation of data obtained during a monitoring programme of surface and groundwater in Patancheru industrial town near Hyderabad (India) is presented in this study. A number of chemical and pharmaceutical industries have been established since past three decades. Effluents from these industries are reportedly being directly discharged onto surrounding land, irrigation fields and surface water bodies forming point and non-point sources of contamination for groundwater in the study area. Thirteen parameters including trace elements (B, Cr, Mn, Fe, Co, Ni, Zn, As, Sr, Ba and Pb) have been monitored on 53 sampling points from a hydrogeochemical survey conducted in surface and groundwater. Data set thus obtained was treated using R-mode factor analysis (FA) and principal component analysis (PCA). FA identified four factors responsible for data structure explaining 75% of total variance in surface water and two factors in groundwater explaining 85%, and allowed to group selected parameters according to common features. Sr, Ba, Co, Ni and Cr were associated and controlled by mixed origin with similar contribution from anthropogenic and geogenic sources whereas Fe, Mn, As, Pb, Zn, B and Co were derived from anthropogenic activities. This study indicates the necessity and usefulness of multivariate statistical techniques for evaluation and interpretation of the data with a view to get better information about the water quality and design some remedial techniques to prevent the pollution caused by hazardous toxic elements in future.

Spatial-Temporal Monitoring of Groundwater Using Multivariate Statistical Techniques in Bareilly District of Uttar Pradesh, India

Monitoring of groundwater quality in Bareilly district, Uttar Pradesh, India, was performed at 10 different sites during the years 2005-2006. Obtained quality parameters were treated using principal component analysis (PCA) and cluster analysis (CA). The study shows usefulness of multivariate statistical techniques for evaluation and interpretation of groundwater quality data sets.

Analysis of heavy metal concentrations in sediments of selected estuaries of Malaysia—a statistical assessment

Statistical analysis of heavy metal concentrations in sediment was studied to understand the interrelationship between different parameters and also to identify probable source component in order to explain the pollution status of selected estuaries. Concentrations of heavy metals (Cu, Zn, Cd, Fe, Pb, Cr, Hg and Mn) were analyzed in sediments from Juru and Jejawi Estuaries in Malaysia with ten sampling points of each estuary. The results of multivariate statistical techniques showed that the two regions have different characteristics in terms of heavy metals selected and indicates that each region receives pollution from different sources. The results also showed that Fe, Mn, Cd, Hg, and Cu are responsible for large spatial variations explaining 51.15% of the total variance, whilst Zn and Pb explain only 18.93 of the total variance. This study illustrates the usefulness of multivariate statistical techniques for evaluation and interpretation of large complex data sets to get better information about the heavy metal concentrations and design of monitoring network.

Application of factor and cluster analysis for characterization of river and estuarine water systems – A case study: Mahanadi River (India)

In order to establish the natural and anthropogenic processes and factors responsible for enrichment of hydrological features, R-mode factor analysis and cluster analysis are applied for three different sets of data i.e. total, fresh and saline influenced stations in Mahanadi river systems. The results of R-mode factor analyses reveal that anthropogenic contribution of nutrients is responsible for lowering DO and pH level of water, though its intensity is different in fresh and saline systems as well as in different seasons. The different magnitude of biochemical oxygen demand (BOD) loading with respect to total nitrogen and phosphorus demonstrated the intensity of organic pollution in different water systems. The removal of silicate in saline system is clearly visible through factor analysis and different mode of association of TSS is reflected seasonally. The relationships among the stations are highlighted by cluster analysis represented in dendrograms to categorize different level of contamination. Considering the diversity of the mechanisms played in estuarine and river water systems, it is felt that statistically their data should be treated separately on the basis of influence of salinity. It is confirmed from our results that the relative importance water quality characteristics varies with specific system. This study presents necessity and usefulness of multivariate statistical techniques for evaluation and monitoring network for effective management of fresh and estuarine systems.

A long-term study of temporal hydrochemical data in a shallow lake using multivariate statistical techniques

The multivariate statistical techniques R- and Q-mode factor analysis and discriminant analysis were applied to a dataset containing physicochemical parameters in lake water samples collected from a shallow (∼4 m) lake located in northwest Greece during a 10-years (1981–1991) monitoring program. Multivariate statistical methods were applied to separate datasets of Pamvotis Lake in order to identify the environmental factors associated with the physicochemical temporal variability. R-mode factor analysis was applied on raw and log-transformed datasets and has allowed the identification of a reduced number of factors with a hydrochemical meaning. R-mode factor analysis has shown that the temporal variability in the Lake Pamvotis depends on six main factors associated to evaporoconcentration processes, natural inflows, anthropogenic influences and phytoplaktonic biomass. The sinusoidal shape of the six factors scores plots has shown that the temporal variations caused by natural and human factors are linked to seasonality. Q-mode factor analysis and discriminant analysis were sequentially applied to (i) the log-transformed full data set of Lake Pamvotis and (ii) a subset contains variables (D.O., SAT, NO 3 −, NO 2 −, NH 4 + and T.P.) which are related to the water quality of lake water samples. In both cases, three clusters of water samples were identified representing (i) a clear seasonal flocculation of the lake waters and (ii) a clustering of the water samples on the basis of water quality showing a seasonal eutrophication of the lake waters. Discriminant analysis showed four parameters (T.P., Na +, Mg 2+ and Ca 2+) affording more than 86% right assignations in temporal analysis of full dataset and one parameter (NO 3 −) to afford 96% right assignations of the subset contained water quality parameters. The application of Q-mode analysis and discriminant analysis has achieved a meaningful classification of lake water samples based on seasonal criteria. Overall, the results of this study present effectiveness of multivariate statistical techniques for evaluation of temporal changes in governing hydrochemical processes and water quality of lake waters.

Water quality assessment and apportionment of pollution sources of Gomti river (India) using multivariate statistical techniques—a case study

Multivariate statistical techniques, such as cluster analysis (CA), factor analysis (FA), principal component analysis (PCA) and discriminant analysis (DA) were applied to the data set on water quality of the Gomti river (India), generated during three years (1999–2001) monitoring at eight different sites for 34 parameters (9792 observations). This study presents usefulness of multivariate statistical techniques for evaluation and interpretation of large complex water quality data sets and apportionment of pollution sources/factors with a view to get better information about the water quality and design of monitoring network for effective management of water resources. Three significant groups, upper catchments (UC), middle catchments (MC) and lower catchments (LC) of sampling sites were obtained through CA on the basis of similarity between them. FA/PCA applied to the data sets pertaining to three catchments regions of the river resulted in seven, seven and six latent factors, respectively responsible for the data structure, explaining 74.3, 73.6 and 81.4% of the total variance of the respective data sets. These included the trace metals group (leaching from soil and industrial waste disposal sites), organic pollution group (municipal and industrial effluents), nutrients group (agricultural runoff), alkalinity, hardness, EC and solids (soil leaching and runoff process). DA showed the best results for data reduction and pattern recognition during both temporal and spatial analysis. It rendered five parameters (temperature, total alkalinity, Cl, Na and K) affording more than 94% right assignations in temporal analysis, while 10 parameters (river discharge, pH, BOD, Cl, F, PO 4, NH 4–N, NO 3–N, TKN and Zn) to afford 97% right assignations in spatial analysis of three different regions in the basin. Thus, DA allowed reduction in dimensionality of the large data set, delineating a few indicator parameters responsible for large variations in water quality. Further, receptor modeling through multi-linear regression of the absolute principal component scores (APCS-MLR) provided apportionment of various sources/factors in respective regions contributing to the river pollution. It revealed that soil weathering, leaching and runoff; municipal and industrial wastewater; waste disposal sites leaching were among the major sources/factors responsible for river quality deterioration.

Multivariate statistical techniques for the evaluation of spatial and temporal variations in water quality of Gomti River (India)—a case study

This case study reports different multivariate statistical techniques applied for evaluation of temporal/spatial variations and interpretation of a large complex water-quality data set obtained during monitoring of Gomti River in Northern part of India. Water quality of the Gomti River, a major tributary of the Ganga River was monitored at eight different sites selected in relatively low, moderate and high pollution regions, regularly over a period of 5 years (1994–1998) for 24 parameters. The complex data matrix (17,790 observations) was treated with different multivariate techniques such as cluster analysis, factor analysis/principal component analysis (FA/PCA) and discriminant analysis (DA). Cluster analysis (CA) showed good results rendering three different groups of similarity between the sampling sites reflecting the different water-quality parameters of the river system. FA/PCA identified six factors, which are responsible for the data structure explaining 71% of the total variance of the data set and allowed to group the selected parameters according to common features as well as to evaluate the incidence of each group on the overall variation in water quality. However, significant data reduction was not achieved, as it needed 14 parameters to explain 71% of both the temporal and spatial changes in water quality. Discriminant analysis showed the best results for data reduction and pattern recognition during both temporal and spatial analysis. Discriminant analysis showed five parameters (pH, temperature, conductivity, total alkalinity and magnesium) affording more than 88% right assignations in temporal analysis, while nine parameters (pH, temperature, alkalinity, Ca-hardness, DO, BOD, chloride, sulfate and TKN) to afford 91% right assignations in spatial analysis of three different regions in the basin. Thus, DA allowed reduction in dimensionality of the large data set, delineating a few indicator parameters responsible for large variations in water quality. This study presents necessity and usefulness of multivariate statistical techniques for evaluation and interpretation of large complex data sets with a view to get better information about the water quality and design of monitoring network for effective management of water resources.