Water monitoring sites discrimination using clustering water variables time series data and main latent factors identification

Abstract

Application of multivariate methodologies for the evaluation and interpretation of space-time variations in an environmental monitoring data set from an hydrological basin is presented in this study. The results obtained allowed detecting natural clusters of monitoring sites with similar water quality type and identifying important discriminant variables for each cluster. Furthermore, this type of analysis allows reducing the number of models in the variables future modelling process.