IAHR Document Library

« Back to Library Homepage « Proceedings of the 29th IAHR World Congress (Beijing, 2001)

A Gaussian Process Model Applied to Prediction of the Water Levels in Venice Lagoon

Author(s): Vladan Babovic; Maarten Keijzer

Linked Author(s): Vladan Babovic

Keywords: Data assimilation; Forecast; Gaussian process

Abstract: Forecasting the water level at Venice lagoon has been object of exten-sive studies in the past. For example, the numerical model (MIKE 21) based on deterministic equations has been setup for the purposes of the operational water level forecast. The model includes all the fundamental modelling components necessary for use in operational mode and model has been tested against a number of historical storms. This paper describes a somewhat alternative approach of combining observations and numerical model results in order to produce a more ac-curate forecast routine. The paper presents an approach where the errors made by a deterministic model are corrected by a gaussian process model. The paper concludes with the analysis of the forecast skill for resulting, hybrid model which provides rather good forecast skill that can be ex-tended over aforecasting horizon of considerable length


Year: 2001

Copyright © 2024 International Association for Hydro-Environment Engineering and Research. All rights reserved. | Terms and Conditions