Uncertainty Analysis of Monthly Streamflow Forecasting

نویسندگانDehghani, M - Saghafian, B - Rivaz, F - Khodadadi, A
نشریهCurrent World Environment
ارائه به نام دانشگاهDepartment of Civil Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
شماره صفحات894-902
شماره مجلد9
نوع مقالهFull Paper
تاریخ انتشار2014
رتبه نشریهISI
نوع نشریهچاپی
کشور محل چاپایالات متحدهٔ امریکا

چکیده مقاله

Stream flow forecasting is an important factor in water resources planning and management. In this study Feed Forward Artificial Neural Network (FFANN) was used for monthly streamflow forecasting. Three scenarios were considered for modeling. Principal Component Analysis (PCA) is used for reducing the model architecture complexity and input data reduction. Twelve statistical criteria were used to evaluate the model performance. Also for quantifying the accuracy of forecast, uncertainty analysis was conducted using Monte Carlo simulation. Results indicated that the model in general is capable to forecast monthly streamflow time series satisfactorily. However the model is underestimated in extreme values. Also, uncertainty analysis shows that the model forecasted monthly stream flow time series properly in the first two scenarios while in the third scenario most of the forecasted values lie out of the upper confidence interval.

لینک ثابت مقاله