Daily Streamflow Time Series Modeling by Using a Periodic Autoregressive Model (ARMA) Based on Fuzzy Clustering

The behavior of hydrological processes is periodic and stochastic due to the influence climatic factors. Therefore, it crucial develop models based on their periodicity nature for prediction. Furthermore, forecasting streamflow, as one main components cycle, a primary subject. In this study, statistical method, Fuzzy C-means clustering, was used find in daily discharge time series, whereas autoregressive moving average, ARMA, modeling every cluster. Dividing stream flow series into smaller groups similar by using method analyzing combination clustering ARMA innovation study. We draw data four different river stations Hesse state Germany. collected cover 18 years, from 2000 2017. Root mean square error (RMSE) evaluate accuracy. results revealed that performance predicting cluster reliable. addition, must be highlighted groups, days year will possible.