River health assessment in pen-urban landscapes: An application of multivariate analysis to identify the key variables

An array of river health assessment approaches and water quality variables have been suggested in the past for assessing the level of river health. However, the selection of suitable variables to be monitored for the assessment remains ambiguous and often it is not practical to monitor all the suggested variables. In this study, we employ a multivariate data reduction technique, called Factor Analysis (FA), to identify the key river health variables for a peri-urban river system, viz., the Hawkesbury-Nepean River system in New South Wales, Australia. Out of 40 water quality variables included in the analysis, the FA identified nine key variables, under three varifactors (VFs), explaining 50% of the variance in the river water quality. Variables in the first, second and third VFs revealed anaerobic conditions, microbial quality and effects of eutrophication in the Hawkesbury-Nepean River. Thus, the present work shows a notable reduction in the number of variables and the application of FA for identification of key variables was found promising. The finding of this study has potential application in designing a cost-effective river health monitoring program by reducing the number of variables to be monitored in a pen-urban situation. It can also assist in partitioning variables according to their unique contribution to the total variance. (C) 2011 Elsevier Ltd. All rights reserved.