Articles | Volume 19, issue 7
Research article
01 Jul 2015
Research article |  | 01 Jul 2015

Propagation of hydro-meteorological uncertainty in a model cascade framework to inundation prediction

J. P. Rodríguez-Rincón, A. Pedrozo-Acuña, and J. A. Breña-Naranjo

Abstract. This investigation aims to study the propagation of meteorological uncertainty within a cascade modelling approach to flood prediction. The methodology was comprised of a numerical weather prediction (NWP) model, a distributed rainfall–runoff model and a 2-D hydrodynamic model. The uncertainty evaluation was carried out at the meteorological and hydrological levels of the model chain, which enabled the investigation of how errors that originated in the rainfall prediction interact at a catchment level and propagate to an estimated inundation area and depth. For this, a hindcast scenario is utilised removing non-behavioural ensemble members at each stage, based on the fit with observed data. At the hydrodynamic level, an uncertainty assessment was not incorporated; instead, the model was setup following guidelines for the best possible representation of the case study. The selected extreme event corresponds to a flood that took place in the southeast of Mexico during November 2009, for which field data (e.g. rain gauges; discharge) and satellite imagery were available. Uncertainty in the meteorological model was estimated by means of a multi-physics ensemble technique, which is designed to represent errors from our limited knowledge of the processes generating precipitation. In the hydrological model, a multi-response validation was implemented through the definition of six sets of plausible parameters from past flood events. Precipitation fields from the meteorological model were employed as input in a distributed hydrological model, and resulting flood hydrographs were used as forcing conditions in the 2-D hydrodynamic model. The evolution of skill within the model cascade shows a complex aggregation of errors between models, suggesting that in valley-filling events hydro-meteorological uncertainty has a larger effect on inundation depths than that observed in estimated flood inundation extents.

Short summary
The study is an investigation on the propagation of hydro-meteorological uncertainty within a model cascade applied to flood prediction. Uncertainty is evaluated at meteorological and hydrological levels in a hindcast scenario, which allows for its generation from the rainfall prediction to its interaction at a catchment level, and propagation to an estimated inundation area and depth. A complex aggregation of errors is demonstrated with larger effect on inundation depths than flood extents.