Data-driven modeling for water resource quality over long term trends

International audience; Since the 50 last years, the rapid development of modern agriculture in industrialised countries has considerably affected the quality of water resources, up to the point to jeopardise the capacity of rural territories to produce drinking water. Hence, there has been interest within the field of agronomy to study complex nitrogen biogeochemical interactions over a long time period. Nevertheless, if the agronomists are able to produce very accurate models at different scales, they have a limited number of available tools in order to cope with quality measurements in water sources for which very little information about the geological information is available. It prevents the specialists of being affirmative about the prediction of their current actions on the water quality. By opposition, system identification can deliver dynamical models from measured data: they cannot be generalised but offer strong insight without any a priori. This applicative paper introduces a data-driven model software for both modelling the nitrogen propagation in drinking water and offering new decision tools to stakeholders.