Reliable prediction of wave overtopping volumes using Bayesian neural networks

Reliable prediction of wave overtopping volumes using Bayesian neural networks.
Kingston, G.and Robinson, D. and Gouldby, B.P. and Pullen, T.A.
In: FLOODrisk 2008, 30 September - 2 October 2008, Keble College, Oxford, UK. (2008)

Download:[img]
Preview
document citation PDF (1497Kb)
Abstract:Artificial neural networks have been used successfully for generating predictions of wave overtopping volumes, which are required to appropriately design coastal structures as well as support associated flood risk analyses. It is particularly important to assess the uncertainty associated with such predictions, given the complexity of the modelling problem and the difficulty in obtaining accurate measurements of the large number of variables needed to estimate wave overtopping. The bootstrapping method previously used to estimate the uncertainty associated with ANN overtopping predictions does not, however, fully capture the total prediction variance. In this paper, Bayesian ANN methods are used to improve the reliability and robustness of wave overtopping predictions and to provide accurate estimates of the associated prediction uncertainty.
Item Type:Conference or Workshop Item (Paper)
Subjects:Floods > Flood risk assessment and mapping
Coasts > Overtopping
Coasts > General
ID Code:232
Deposited On:30 Oct 2008 18:18
Last Modified:08 Aug 2014 09:15

Repository Staff Only: item control page