Monthly Low-Flow Forecasting Using a Stochastic Model and Adaptive Network Based Fuzzy Inference System

Introduction Water resources systems management is directly influenced by streamflow forecasting. It is therefore necessary to develop appropriate and applicable models for streamflow forecasting, especially in the low-flow context. Both stochastic models and artificial intelligence based models are widely used for simulation and forecasting of hydrologic time series. The literature shows that both models have performed well in different cases (Mishra et al., 2007) and thus it is difficult to know a priori which particular model would be better suited for a given problem.