Two decades of anarchy? Emerging themes and outstanding challenges for neural network river forecasting

Auteur(s) et Affiliation(s)

ABRAHART, R.J.

Univ. of Nottingham, Nottingham, Royaume-Uni

ANCTIL, F.

Univ., Laval, Canada

COULIBALY, P.

McMaster University, Hamilton, Canada

DAWSON, C.W.

Univ., Loughborough, Royaume-Uni

MOUNT, N.J.

Univ. of Nottingham, Nottingham, Royaume-Uni

SEE, L.M.

International Inst. of Applied Systems Analysis, Autriche

SHAMSELDIN, A.Y.

Univ., Auckland, Nouvelle-Zelande

SOLOMATINE, D.P.

UNESCO-IHE, and Univ. of Technology, Delft, Pays-Bas

WILBY, R.L.

Univ., Loughborough, Royaume-Uni

Description :
This paper traces two decades of neural network rainfall-runoff (NNRF) and streamflow modelling, collectively termed river forecasting, providing an analysis of recent and ongoing computational hydrological modelling developments in NNRF, thereby shaping a coherent research agenda for NNRF over the next decade. It is clear that neural network river forecasting solutions will have limited appeal for operational purposes until confidence intervals can be attached to forecasts. Modular design, ensemble experiments, and hybridization with conventional hydrological models are yielding new tools for decision-making. The full potential for modelling complex hydrological systems, and for characterizing uncertainty, has yet to be realized.

Type de document :
Article de périodique

Source :
Progress in physical geography, issn : 0309-1333, 2012, vol. 36, n°. 4, p. 480-513, nombre de pages : 34, Références bibliographiques : 10 p.

Date :
2012

Editeur :
Pays édition : Royaume-Uni, London, Sage Publications

Langue :
Anglais