Combining geostatistics and Kalman filtering for data assimilation in an estuarine system

Data assimilation (DA) has been applied in an estuarine system in order to implement operational analysis in the management of a coastal zone. The dynamical evolution of the estuarine variables and corresponding observations are modelled with a nonlinear state-space model. Two DA methods are used for controlling the evolution of the model state by integrating information from observations. These are the reduced rank square root (RRSQRT) Kalman filter, which is a suboptimal implementation of the extended Kalman filter, and the ensemble Kalman filter which allows for nonlinear evolution of error statistics while still applying a linear equation in the analysis. First, these methods are applied and examined with a simple 1D ecological model. Then the RRSQRT Kalman filter is applied to the 3D hydrodynamics of the Odra lagoon using the model TRIM3D and water elevation measurements from fixed pile stations. Geostatistical modelling ideas are discussed in the application of these algorithms.