Résumé
Rapid population growth and human activities (such as agriculture, industry, transports...) development have increased vulnerability risk for water resources. Due to the nature of river networking distribution, the interactions between hydrosystems and human pressures are difficult understand. In addition, many hypotheses about river water pollution can be formulated. In this context, knowledge discovery is a promising process to better understand and manage such phenomenon. We have combined the results of several data mining methods to extract actionable knowledge from data collected by stations located along several rivers. First, data are pre processed (aggregated) according to different spatial relationships, which leads to the extraction of semantically different patterns in the second phase of the process. Then, the resulting datasets are mined to extract sequential and spatio-sequential patterns. Finally, patterns are filtered using a new quality measure based on the notion of contradiction. Such elements can be used to assess specialized indicators to assist the experts in river water quality restoration.