Assessment of physico-chemical and microbiological surface water quality using multivariate statistical techniques: a case study of the Wadi El-Bey River, Tunisia

Located in the northeastern part of Tunisia, Wadi El Bey drains the watershed through farmland, industrial, and urban areas of the region. It serves to discharge treated waste-water of different types. In this work, the variations of the water quality of Wadi El Bey were studied and evaluated, during 2 years (2012-2013), using multivariate statistical techniques such as principal component analysis (PCA) and cluster analysis (CA). In addition, the similarities or dissimilarities among the sampling points were as well analyzed to identify spatial and temporal variations. The results obtained based on the cluster analysis, led to identify three similar water quality zones: relatively polluted (LP), moderately polluted (MP), and highly polluted (HP). The inorganic and organic parameters, temperature, conductivity, dissolved oxygen, chemical oxygen demand, salmonella, and enterococcus, seemed to be the most significant parameters of water quality. Three factors were identified as responsible for the data structure, explaining 60.95% of the total variance. The first factor is the physical and non-organic chemical parameters explaining 23.48% of the total variance. The second and third factors are, respectively, the microbiological (21.26%) and organic-nutrient (16.2%). This study shows that multivariate statistical methods can help the water managers to understand the factors affecting the water quality.