Climate change impacts on the flow regime and water quality indicators using an artificial neural network (ANN): a case study in Saskatchewan, Canada

Abstract In this study, the artificial neural network (ANN) method was applied to investigate impacts of climate change on water quantity and quality Qu'Appelle River in Saskatchewan, Canada. First, second-generation Canadian earth system model (CanESM2) adopted predict future conditions. The Statistical DownScaling Model (SDSM) then downscale generated data. To analyze river, concentrations dissolved oxygen (DO) total solids (TDSs) from river were collected. Using collected hydrometric data, ANNs trained simulate (i) ratio snowfall-to-total precipitation based temperature, (ii) flow rate temperature precipitation; (iii) DO TDS temperature. Finally, data used as inputs ANN well within selected region. Hydrologic alteration evaluated via Range Variability Approach (RVA) under historical scenarios. results scenarios compared with those indicated that would lead a heterogeneous patterns. These changes have serious degrading discharge concentration levels, causing deterioration sustainability ecological health