A Study of Efficiency of the Hybrid model Artificial Neural Network Models - Stochastic in Hydrological Drought Forecasting Using kappa Statistics (Case Study: Gamasiab Watershed Basin)
|
|
|
|
Abstract: (13505 Views) |
Drought
is a natural occurrence caused by repetitive and ephemeral that it is less
rainfall than average long term and can occur in any climate. Since the drought
phenomenon is stochastic and nonlinear, stochastic linear models, neural
networks and hybrid models can be useful in the development forecasting
results. This study models the performance of ARIMA, neural networks and hybrid
models ARIMA prediction of hydrological drought in both monthly and seasonal
time scale deals and SDI index is as a predictor of the watershed was selected
Gamasiab in period (1353-1387). The period (1353 - 1379) used for calibration
and the remaining 8 years used for verification in model. Results show that,
among the three models used to predict one time step neural network models -
stochastic (hybrid) models are suitable to the monthly and seasonal scales. So
Kappa statistic values and the relative error of the model at monthly time
scales Polchehr station (the outlet), respectively RME= 5/79 %, K= 0.565 and seasonal time scales Station
Doab (the middle) RME = 22% and is K=0.232.
|
|
Keywords: : Hydrological drought, forecasting, Hybrid models, SDI, River basin Gamasiab. |
|
Full-Text [PDF 851 kb]
(2062 Downloads)
|
Type of Study: Research |
Subject:
Special Received: 2015/06/1 | Accepted: 2015/06/1 | Published: 2015/06/1
|
|
|
|
|
Add your comments about this article |
|
|