By comparing diatom communities in natural and disturbed sites, indicators for different types and levels of anthropogenic disturbance can be found. As a first step, this study aims to describe the different natural and disturbed community types found throughout the French hydrosystem. 836 diatom samples were analysed with an unsupervised neural network, the self-organising-map, a well accepted method for community ordination. 11 different communities were identified, 5 corresponding to non-impacted or slightly impacted conditions and representing the diatom natural variability of our dataset. These 5 communities corresponded to 5 different hydro-ecoregions, i.e. 5 river types with similar geological context and range in altitude. The 6 other communities were typical of rivers under anthropogenic pressure. The influence of natural conditions within the hydro-ecoregions was overwhelmed by the nature and the intensity of the pollution at the sampling stations. This work was done in the context of the application and enforcement of the Water Framework Directive.