 |
| Titel |
A novel approach to parameter uncertainty analysis of hydrological models using neural networks |
| VerfasserIn |
D. L. Shrestha, N. Kayastha, D. P. Solomatine |
| Medientyp |
Artikel
|
| Sprache |
Englisch
|
| ISSN |
1027-5606
|
| Digitales Dokument |
URL |
| Erschienen |
In: Hydrology and Earth System Sciences ; 13, no. 7 ; Nr. 13, no. 7 (2009-07-21), S.1235-1248 |
| Datensatznummer |
250011942
|
| Publikation (Nr.) |
 copernicus.org/hess-13-1235-2009.pdf |
|
|
|
|
|
| Zusammenfassung |
| In this study, a methodology has been developed to emulate a time consuming
Monte Carlo (MC) simulation by using an Artificial Neural Network (ANN) for
the assessment of model parametric uncertainty. First, MC simulation of a
given process model is run. Then an ANN is trained to approximate the
functional relationships between the input variables of the process model and
the synthetic uncertainty descriptors estimated from the MC realizations. The
trained ANN model encapsulates the underlying characteristics of the
parameter uncertainty and can be used to predict uncertainty descriptors for
the new data vectors. This approach was validated by comparing the
uncertainty descriptors in the verification data set with those obtained by
the MC simulation. The method is applied to estimate the parameter
uncertainty of a lumped conceptual hydrological model, HBV, for the Brue
catchment in the United Kingdom. The results are quite promising as the
prediction intervals estimated by the ANN are reasonably accurate. The
proposed techniques could be useful in real time applications when it is not
practicable to run a large number of simulations for complex hydrological
models and when the forecast lead time is very short. |
| |
|
| Teil von |
|
|
|
|
|
|
|
|