Mathematics – Logic
Scientific paper
Jun 2005
adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=2005jhyd..307..164c&link_type=abstract
Journal of Hydrology, Volume 307, Issue 1-4, p. 164-174.
Mathematics
Logic
10
Scientific paper
Recent evidence of nonstationary trends in water resources time series as result of natural and/or anthropogenic climate variability and change, has raised more interest in nonlinear dynamic system modeling methods. In this study, the effectiveness of dynamically driven recurrent neural networks (RNN) for complex time-varying water resources system modeling is investigated. An optimal dynamic RNN approach is proposed to directly forecast different nonstationary hydrological time series. The proposed method automatically selects the most optimally trained network in any case. The simulation performance of the dynamic RNN-based model is compared with the results obtained from optimal multivariate adaptive regression splines (MARS) models. It is shown that the dynamically driven RNN model can be a good alternative for the modeling of complex dynamics of a hydrological system, performing better than the MARS model on the three selected hydrological time series, namely the historical storage volumes of the Great Salt Lake, the Saint-Lawrence River flows, and the Nile River flows.
Baldwin Connely K.
Coulibaly Paulin
No associations
LandOfFree
Nonstationary hydrological time series forecasting using nonlinear dynamic methods does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Nonstationary hydrological time series forecasting using nonlinear dynamic methods, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Nonstationary hydrological time series forecasting using nonlinear dynamic methods will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-1399149