Evaluating the Performance of some Statistical and Soft Computing Models to Predict River Flow
Regarding the decrease in water resources especially in Iran, the river flow forecasting has gained a high importance and it is necessary to use the best methods for such forecasts. In this study the performance of some linear and nonlinear models was investigated for predicting the monthly flow of Jamishan River in Kermanshah province. The models include autoregressive integrated moving average (ARIMA), artificial neural networks (ANN) and adaptive neuro-fuzzy inference system (ANFIS). In using ARIMA model considering five parameters of any kind, all possible models were evaluated. For ANFIS and ANN models with determination of 14 different input combinations, the best models were identified. The capability of obtained models in long-term flow prediction was also assessed. The results revealed that ANFIS model is more capable in identifying the effective time delays in flow compared to ANN. This model is also more accurate than other models in peak values prediction. ARIMA model on the other hand has high capability in prediction of low values. Study indicated that all three models can be used for long-term predictions.
Monthly inflow , Prediction , Modeling , ARIMA , ANFIS
- حق عضویت دریافتی صرف حمایت از نشریات عضو و نگهداری، تکمیل و توسعه مگیران میشود.
- پرداخت حق اشتراک و دانلود مقالات اجازه بازنشر آن در سایر رسانههای چاپی و دیجیتال را به کاربر نمیدهد.