Assessing anthropogenic pressures on streams: A random forest approach based on benthic diatom communities

• Published in: The Science of the total environment 2017-05, Vol.586, p.1101-1112
• Main Authors: Larras, Floriane, Coulaud, Romain, Gautreau, Edwige, Billoir, Elise, Rosebery, Juliette, Usseglio-Polatera, Philippe
• Format: Article
• Language: English
• Subjects: Biodiversity and Ecology; Environment and Society; Environmental Sciences; Global Changes; Hydromorphological pressures; Land-use; Nutrients; Risk assessment; Toxics; Traits
• ISSN: 0048-9697; 1879-1026
• DOI: 10.1016/j.scitotenv.2017.02.096

Benthic diatoms have been widely used to assess the ecological status of freshwater ecosystems, especially in the context of recent international water framework directive policies (e.g. the WFD). Despite diatom-based indices are known to respond fastly to water quality degradation, they are not designed to precisely identify the nature of pressures co-occurring in the environment. Based on large scale monitoring data, we aimed at building models able to estimate the risk of stream impairment by many types of anthropogenic pressures from taxonomy-based and trait-based characteristics of diatom assemblages. Random forest models were built to individually evaluate the impairment risk of diatom assemblages for six chemical and five hydromorphological or land-use related pressure categories. Eight models provided good impairment risk assessment (Area Under the Curve≥0.70). Under multi-pressure scenarios, models built for chemical pressures exhibited a better accuracy than hydromorphological or land-use related ones. Models were able to detect both ecological restoration and degradation, based on long-term surveys. These models have been implemented in a R user-friendly routine, to help stream managers to early identify degrading processes and prioritize management actions. [Display omitted] •River impairment risk was modeled based on traits and taxonomy of diatoms.•11 models were built to assess the specific risk of each pressure category.•Models provided good impairment risk assessment for 8 pressure categories.•Only chemical pressures were accurately assessed under multi-stress scenarios.•This promising tool should be used to diagnose stream ecological status.