Pattern recognition techniques for the evaluation of spatial and temporal variations in water quality. A case study: Suquía River Basin (Cordoba-Argentina).

摘要: We report a comparative study using three different chemometric techniques to evaluate both spatial and temporal changes in Suquia River water quality, with special emphasis on the improvement obtained discriminant analysis for such evaluation. have monitored 22 parameters at stations from upper, middle, beginning of lower river basin during least two years including 232 samples. complex data matrix, which was treated pattern recognition cluster (CA), factor analysis/principal components (FA/PCA), (DA). CA renders good results as first exploratory method differences, however it fails show details these differences. FA/PCA needs 13 point out 71% changes; consequently reduction this case is not considerable expected. However, allows group selected according common features well incidence each overall change specially changes. DA technique shows best analysis. an important 6 afford 87% right assignations Besides, uses only 5 yield 75% four areas. allowed us greatly reduce dimensionality starting pointing few that indicate biggest quality variation patterns associated seasonal variations, urban run-off, pollution sources, presenting novel approach assessments.